6th European Conference on Social Networks

12-16 September 2022 London

  • Registration now open!
  • Programme now available!
EUSN 2022 Logo Round
More Information

Welcome to EUSN 2022 in London

The 6th European Conference on Social Networks (EUSN 2022) is hosted by the Networks and Urban Systems Centre at the University of Greenwich and will be held in London, 12-16 September 2022.

Continuing the traditions of previous conferences in Barcelona (2014), Paris (2016), Mainz (2017), Zurich (2019), and Naples (2021), as well as the legacies of predecessors Applications of Social Network Analysis (ASNA) and UK Social Network Analysis (UKSNA), the conference brings together researchers and practitioners from the social sciences in the broad sense as well as statistics, computer science, data science, physics, economics, humanities, and other areas dealing with social networks.

 

EUSN 2022 is endorsed by INSNA, the International Network for Social Network Analysis.

INSNA Logo

Venue

The conference with be held at Greenwich Campus, University of Greenwich, London.

Greenwich Campus sits on a World Heritage Site and is located in the heart of Greenwich, south-east London. The campus is surrounded by historical landmarks and Greenwich Park. The Stockwell Street Building will host the organised and plenary sessions from Tuesday to Thursday of the conference week. The Devenport House Building will host the workshops on the Monday and Friday of the conference week.

Keynotes and Committees

Keynotes

Prof. Alessandro Lomi, Università della Svizzera italiana
Prof. Kerstin Sailer, University College London

Organising Committee

Guido Conaldi, University of Greenwich
Stefano Ghinoi, University of Greenwich
Francesca Pallotti, University of Greenwich

Program Committee

Viviana Amati, ETH Zürich
Spyros Angelopoulos, Durham University
Elisa Bellotti, University of Manchester
Per Block, Oxford
Zsófia Boda, University of Essex
Ulrik Brandes, ETH Zürich
Dimitris Christopoulos, Edinburgh Business School
Bruce Cronin, University of Greenwich
Mario Diani, University of Trento
Marten Düring, Luxembourg Centre for Contemporary and Digital History
Alexandra Gerbasi, Exeter Business School
Marina Hennig, Johannes Gutenberg University of Mainz
Bernie Hogan, University of Oxford
Luka Kronegger, University of Ljubljana Faculty of social sciences
Miranda Lubbers, Autonomous University of Barcelona
Matteo Magnani, Uppsala University
Sophie Mützel, UniLu
Anna Piazza, University College London
Juergen Pfeffer, Technical University of Munich
Giancarlo Ragozini, University of Naples Federico II
Yasaman Sarabi, Edinburgh Business School Heriot-Watt University
Termeh Shafie, University of Manchester
Matthew Smith, Edinburgh Napier University
Tom Snijders, University of Groningen and University of Oxford
Christoph Stadtfeld, ETH Zürich
Paola Tubaro, CNRS
Maria Prosperina Vitale, University of Salerno
Srinidhi Vasudevan, University of Greenwich
Susanna Zaccarin, University of Trieste
Paola Zappa, Maynooth University

Important Dates

25th February 2022

25th February 2022

Workshops and sessions proposals due (Notification 4th March)

8th May 2022

8th May 2022

Presesentation proposals due (Notification 6th June)

12th June 2022

12th June 2022

Poster Proposals due (Notification 20th June)

1st June 2022

1st June 2022

Registration opens

31st July 2022

31st July 2022

Early bird registation closes

31st August 2022

31st August 2022

Regular registration closes

1st September 2022

1st September 2022

Last-minute registration opens

12-16th September 2022

12-16th September 2022

Conference week

Registration

To register for the conference and workshops, please follow this link to the registration site. After having chosen the main ticket for the conference you will have the chance to select workshops, the gala dinner, and other social events as additional items.

 

Please use the same email of your INSNA account if choosing the INSNA-member fees.

 

Early Bird Fees (12th June - 31st July)

Ticket Options:
Student£100
Academic - INSNA Member£200
Academic - Non-INSNA Member£250
Industry / Non-researching Institution£1,000
Additional Items:
Workshop (Full-day) - Student£50
Workshop (Full-day) - Academic/Industry£100
Workshop (Half-day) - Student£25
Workshop (Half-day) - Academic/Industry£50
Conference Gala Dinner£40

 

Regular Fees (1st August - 31st August)

Ticket Options:
Student£150
Academic - INSNA Member£250
Academic - Non-INSNA Member£300
Industry / Non-researching Institution£1,500
Additional Items:
Workshop (Full-day) - Student£50
Workshop (Full-day) - Academic/Industry£100
Workshop (Half-day) - Student£25
Workshop (Half-day) - Academic/Industry£50
Conference Gala Dinner£40

 

Last-minute Fees (1st September - 9th September)

Ticket Options:
Student£200
Academic - INSNA Member£300
Academic - Non-INSNA Member£350
Industry / Non-researching Institution£2,000
Additional Items:
Workshop (Full-day) - Student£50
Workshop (Full-day) - Academic/Industry£100
Workshop (Half-day) - Student£25
Workshop (Half-day) - Academic/Industry£50
Conference Gala Dinner£40

 

Calls for Proposals

Organised sessions


Deadline 25 February 202, 12 midnight AoE


If you would like to contribute by organizing a session focused on a particular topic, please submit a proposal including a description of that topic. Accepted sessions will be included in the submission form for presentations.

 

Workshops


Deadline 25 February 2022, 12 midnight AoE


Workshops will take place on the first (12th September) and last day (16th September) of the conference. If you are interested in offering either a 3-hour or 6-hour workshop, please submit a proposal including a description of the content and target audience.

 

Presentations


Deadline 8 May 2022, 12 midnight AoE


Presentations will be allocated 15 minutes plus 5 minutes for discussion. Any topic relevant to social network analysis, including theory, methods, and empirical applications will be considered. Abstracts are limited to 500 words, not including the title, and should not contain references.

When submitting their presentation proposal, authors will be asked to indicate the organised session to which they are submitting by selecting one (only) subject area and to designate a primary contact. The primary contact will become the corresponding author and will be considered the designated presenter at the conference. Please be reminded that at EUSN 2022 participants are restricted to one presentation but may be co-authors of multiple submissions.

 

Posters


Deadline 12 June 2022, 12 midnight AoE


Posters will be exhibited during a poster session and reception at the conference. All posters will take part in the EUSN 2022 Poster Competition. The winner will receive a prize of £500. The evaluation criteria the selected judges will adopt are: clarity of objectives and research questions; appropriateness of research design and methods; quality and impact of the research presented; poster design and overall visual appeal.

 

Submission Guidelines


EUSN 2022 uses Microsoft Conference Management Toolkit (CMT) for all submissions.
Authors will need a free CMT account to log in and submit their proposals at https://cmt3.research.microsoft.com/EUSN2022.

All deadlines are at 12 midnight AoE (Anywhere on Earth).

Please do not hesitate to email us at eusn2022@gre.ac.uk if you have any questions.

Organised Sessions

Click anywehre on the session titles to see the organisers and details.

Organised Session 01: Advanced Methods for Multilayer and Feature-Rich Networks and Their Applications

 

Giancarlo G. Ragozini, University of Naples Federico II (giragoz@unina.it)
Matteo Magnani, Uppsala University
Roberto Interdonato, CIRAD
Maria Prosperina Vitale, University of Salerno
Giuseppe Giordano, University of Salerno

 

In recent years it has become more and more frequent to use network models going beyond simple directed/undirected and weighted/unweighted networks, to capture the complexity of old and new fields of application of network analysis. Multilayer networks are an example of such models, extending graphs with the concept of layer, that allows us to represent a multitude of scenarios from the different types of ties we find in a multiplex network, to different types of actors, to different temporal snapshots of the relations between the same group of actors. Multilayer network models can themselves be enriched with additional features, such as attributes and edge probabilities, with the aim of describing real phenomena in more detail.

 

Multilayer and feature-rich networks allow us to introduce new research questions (and corresponding social network analysis measures and methods). For example, instead of asking how central an actor is, we can focus on the role of the different layers in determining the centrality of the actors. Second, existing social network analysis concepts do not always have a clear corresponding extension in complex networks. For example, it is still unclear how communities spanning multiple layers should look like, or how different features should contribute to the definition of communities, or how to effectively visualise multilayer and feature-rich networks, e.g. layers, features or modes, in the same sociogram. In addition, multilayer networks allow to use multiple types of layers (e.g., in temporal multiplex networks), which requires the joint application of methods developed for simpler models (e.g., only temporal, or only multiplex).

 

This session focuses on recent advances in the analysis of multilayer and feature-rich networks, either in terms of new research questions, or new methods, or new applications. More specifically, topics for this session include but are not limited to:

 

• New models for multilayer and feature-rich networks, or comparison of alternative models;
• Measures for multilayer and feature-rich network;
• Community discovery in multilayer and feature-rich networks;
• Multilayer and feature-rich network embedding;
• Visualisation of multilayer and feature-rich network;
• Multilayer and feature-rich network simplification (e.g., sampling, filtering, flattening, projections);
• Applications;
• Software.

Organised Session 02: Collaboration Networks

 

Giancarlo G. Ragozini, University of Naples Federico II (giragoz@unina.it)
Maria Prosperina Vitale, University of Salerno
Giuseppe Giordano, University of Salerno

 

Collaboration networks attract a lot of attention in many scientific domains. The session focuses on presenting methodological developments and novel applications related to the session topics.

 

Special interest is on the analysis of collaboration networks in presence of complex data structure, and on collaboration data extraction and empirical data collection.

 

The organizers solicit the submission of abstracts dealing with the following topics:

 

• Academic and scientific networks;
• Analysis of collaboration networks in economics, cultural and social environments;
• Co-authorship networks;
• Collaborative innovation networks;
• Community detection in collaboration networks;
• Dynamics and evolution patterns of collaboration networks;
• Empirical data collection;
• Mixed methods for data collection and data analysis.

Organised Session 03: Ecosystem of Entrepreneurs

 

Hetty Wenxian Sun, Greenwich Business School (w.sun@gre.ac.uk)
Petros Ieromonachou, University of Greenwich
Aaron Tan, University of Greenwich

 

As a network, ecosystems are present and thriving in the world in various forms. This track looks specifically at entrepreneurial ecosystems which relies on people, the culture they bring in and the way they interact with each other. People, as one of the most central parts to support entrepreneurial ecosystems, plays many different roles: policymakers, lawyers, community leaders, investors and so on, and indeed, “entrepreneurship is a community sport” (Whitters, 2014). Great businesses are built by great people, and without high-skilled workers, they would not have surfaced. To continuously supply the entrepreneurial talent, the ecosystem would need to attract, engage and nurture people, especially young people, with skills that could allow them to be more responsive to the business requirements.

 

A diverse culture is the fertilised soil for ecosystems, which enables the production of a broad range of entrepreneurial solutions to issues present in the world and society. This leads to initiatives to solve wider problems such as climate change, global warming and personal security, as well as reducing the unemployment rate, improving public services and boosting mental health. A diverse team often brings in better results (Rock & Grant, 2016) and hence truly drives the growth of the ecosystem. Economic progress is the result of innovations (Holcombe, 2007) and market share is constantly taken by new businesses and ideas. An ecosystem should allow entrepreneurs to experiment with new business models and technologies to achieve growth and during which, plenty of interactions among entrepreneurs, policymakers, investors and competitors will provide a rich context for social network analysis.

 

Sample topics
The EU Social Networks Conference Ecosystem of Entrepreneur track encourages and welcomes researchers who recognise the difference of ecosystem elements and take particular interest in examining their interactions in the entrepreneurial world contributing to the following themes (but not limited to):

 

• Cultivate ecosystem
• Cultural and interactive aspects of relationship with policymaker
• Human capital in the entrepreneurial ecosystem
• Building community capacity for ecosystem development
• Entrepreneurship education from an ecosystem perspective
• Millennial entrepreneur and talent
• Innovation-driven entrepreneurship ecosystem
• The role of open innovation
• Investment ecosystem for start-ups
• Global ecosystem from a financial and technological perspective
• Competition and cooperation in entrepreneurial ecosystems

Organised Session 04: Family Networks and Personal Networks Through the Life-course

 

Vera de Bel, University of Turku, Netherlands Interdisciplinary Demographic Institute (vera.debel@utu.fi)
Thomas Leopold, University of Cologne
Marlène Sapin, LIVES & FORS, University of Lausanne
Eric Widmer, LIVES, University of Geneva

 

Life-course trajectories and transitions are intertwined within the complex webs of family and personal relationships. These networks may provide individual network members with resources, supporting them through life-course events and transitions. However, these networks, depending on their composition or the pattern of interactions, do not only exert a positive influence on the individual members of the network. Family and personal networks may also cause stress or strain on the individual and the network level. In addition, family and personal networks change over time, which may have consequences on the access to resources and may for example affect individual network members’ well-being, behaviour, and life chances.

 

This session invites papers on personal and family networks during the different stages of the life course. Papers focusing on the transition into adulthood, family formation, union dissolution, transition to retirement, and ageing are encouraged to be submitted, but studies on other life-course changes are also welcome. Quantitative as well as case studies on specific normative or non-normative life events are also of interest to this session.

Organised Session 05: Methodological and Software Advancements in Social Network Analysis

 

Stefano Ghinoi, University of Greenwich (s.ghinoi@greenwich.ac.uk)
Guido Conaldi, University of Greenwich

 

This session will be dedicated to the exploration and discussion of novel methodological approaches and software applications for the analysis of social networks. The session aims to bring together theoretical contributions, empirical applications, and software illustrations using novel analytical tools - especially in cases where a more specialised organised session is not also offered. Topics for this session include, but are not limited to:

 

• Advancements in agent-based modeling;
• Advancements in blockmodeling;
• Community detection and graph partitioning;
• Developments in – or entirely new - descriptive network measures
• Software developments for the visualisation and analysis of networks

 

This list is not exhaustive, and the topics are provided as examples. We encourage submissions of a wide range of topics related to the general aim of the session.

Organised Session 06: Modeling Network Dynamics

 

Nynke Niezink, Carnegie Mellon University (nniezink@andrew.cmu.edu)
Robert W Krause, Free University Berlin

 

Important insights into social networks can be obtained with the help of longitudinal observation designs. Such designs can be of a varied nature. Panel data is the structure used traditionally for self-reported networks; regular time series and time-stamped data can be obtained from official or automatic records; but this does not exhaust the types of longitudinal network designs. Corresponding to these differences in data collection, a variety of longitudinal methods of analysis have been developed, such as continuous-time actor-oriented and tie-oriented models for panel and time series data, network autoregressive models for time series at regular intervals, and network event models for data with a fine-grained time resolution. Some of these methods are based on actor-oriented models, others on tie-oriented models.

 

This session will be open to methodological as well as applied presentations about models for network dynamics. Papers can have a mathematical, statistical, theoretical, or empirical subject-matter focus, as long as they are relevant for empirical social science.

 

Keywords: network dynamics, longitudinal networks, actor-oriented models, network event models, Dynam, LERGM, TERGM, Siena, relevent, goldfish.

Organised Session 07: Multiplex Networks and Individual Outcomes in School

 

Andras Voros, University of Manchester (andras.voros@manchester.ac.uk)
Zsófia Boda, University of Essex
Elisa Bellotti, University of Manchester

 

The importance of multiplexity is increasingly recognised in (educational) network research. While research into the effects of peer networks has traditionally focused on a single network dimension at a time, most commonly on friendship, this approach has been shifting lately.

 

A wave of studies in recent years has showed how multiple forms of social ties emerge between students and affect a variety of their outcomes. Relevant networks include personal relations such as liking or “friendly” ties, spending free-time together, studying together, dislike, conflict, victimisation, and romantic ties. Besides these, interpersonal perceptions appear to have an impact on student behaviour and outcomes as well: such as perceptions about the status, social roles, or personality of peers.

 

Longitudinal studies have demonstrated that the emergence and change of the various network dimensions is interconnected. Multiplex social networks jointly influence individual outcomes, such as academic achievement, school attitudes, mental and physical health, political attitudes, and so on.

 

This section invites presentations which explore the importance of multiplex networks for individual outcomes in educational settings.

 

Particularly (but not exclusively), we would be happy to hear about work that focuses on:

 

• Data collection techniques for multiplex networks in school;
• Statistical methods that are specific to multiplex networks in school;
• Empirical data analyses and results involving the evolution of multiplex networks in school;
• Empirical data analyses and results involving the relationship of multiplex networks and individual outcomes in school.

 

The list is not exhaustive: we are very much open to a wide range of studies on the topic of multiplexity in schools. We hope to bring together a diverse set of research projects and facilitate discussion and collaboration between scholars interested in educational network research.

Organised Session 08: Network Analysis and Bibliometrics

 

Stefano Ghinoi, University of Greenwich (s.ghinoi@greenwich.ac.uk)
Guido Conaldi, University of Greenwich

 

The use of network analysis in bibliometrics has a long tradition, which dates back to the 1960s. However, while the analysis of bibliometric networks has become extremely popular in the last decades, there are still some areas that have received less attention; in particular, the construction of bibliometric networks, the use of different data sources, and the impact of bibliometric methods. Moreover, novel research topics constantly emerge in different scientific disciplines, and their evolution requires a robust mapping process.

 

This session is dedicated to methodological advancements, empirical applications, and proposals on the use of novel software and tools for applying network analysis in bibliometric studies. We welcome contributions exploiting the role of network analysis in bibliometric studies, including (but not limited to):

 

• Network structures in bibliometric studies;
• Authors’ and papers’ centrality;
• Co-authorship, co-occurrence, and network metrics;
• Modularity, sub-groups, and clusters;
• Cross-country collaborations;
• Bibliographic database journal coverage;
• Editorial board networks;
• Actors’ attributes in scientometrics;
• Network visualization.

Organised Session 09: Network Analysis and Sports

 

Lucio Palazzo, University of Naples Federico II (lucio.palazzo@unina.it)
Roberto Rondinelli, University of Naples Federico II
Filipe Manuel Clemente, Viana do Castelo Polytechnic Institute
Kristijan Breznik, International School for Social and Business Studies
Riccardo Ievoli, University of Ferrara

 

The analysis of sport data is becoming truly helpful for recognizing the strengths and weaknesses of individual players and collective behaviors of teams. Using such information is possible to make better decisions and organize the strategy to achieve greater success both in terms of sport results and economic aspects. Therefore, the rise of sport analytics tools mixed with the availability of data allow the spread of innovative methodologies in a broad range of sports. In this context, relational data are also arising.

 

The proposed session focuses on contributions regarding network analysis in sport data. Between the possible topics, network analysis may help to unveil the key elements regarding tactics and/or team strategies in team sports. Furthermore, connections between teams (e.g. trading and exchanges) and/or federations cover an important role and may contribute to sport results. The search of appropriate methodologies to deal with those data remains an open issue.

 

The audience of interest may include experts in statistics, operations research, machine learning, scientific computing, economics, sports management, and sport science interested in expanding these topics in a network perspective. Audience members will become aware of the most current thinking on common problems of interest in network modeling or analysis of sports data.

 

The session welcomes empirical, methodological and/or theoretical contributions exploiting the role of Network Analysis in sports, including (but not limited to):

 

• Local network structures;
• Temporal networks;
• Network indicators and sport outcomes;
• Signed networks;
• Multimodal networks;
• Multilayer networks;
• Complex networks.

Innovative approaches of network analysis for popular team sports (e.g., football, basketball, and volleyball) as well as original applications based on less known sports are also welcome.

 

Organised Session 10: Networking Historical Past

 

Paolo Cimadomo, University of Haifa (cimadomopaolo@gmail.com)
Anna Collar, University of Southampton
Maria Carmela Schisani, University of Naples Federico II

 

The network perspective has currently reached a paradigmatic position in some fields, like sociology. Moreover, during recent years we have seen a steady increase of publications and works on a number of economic, social, cultural and religious aspects that have attempted to apply network analysis to the past world, in particular to explain their interconnections. Network analysis attracted scholars of human past for their potential in investigating human relationships, visualising and exploring their structures among different archaeological and historical sources. Archaeological and historical data sources pose challenging opportunities to network analysts and network scientists. World-Systems Analysis has especially emphasized the importance of understanding interactions and interrelationships between different peoples or inside the same human group.

 

The aim of this session is twofold. Firstly, we want to work towards a specific historical and archaeological network analysis, drawing on the relational thinking of network theory and incorporating archaeological and historical sources critique and reasoning. Secondly, we want to present new findings and approaches within historical and archaeological network research, and promote contacts between the various disciplines that approach past phenomena using methods derived from network analysis or network science.

 

The session invites contributions from various disciplines applying the methods of formal network analysis and network science to the study of the historical research. The contributions will answer questions such as: how can we detect change in human networks change over a long timeframe? How can literary and historical sources and material culture help in answering this question?

 

We welcome submissions about any period, geographical area and topic, which might include but are not limited to: economics, politics, military issues, religion and science, interpersonal relations, kinship, cultural networks, artistic transmission, material and immaterial connections, migration, networks extracted from texts, geospatial or temporal networks, big data and data collection from fragmentated sources.

Organised Session 11: Networks and Crime

 

Tomáš Diviák, University of Manchester (tomas.diviak@manchester.ac.uk)
Paolo Campana, University of Cambridge

 

The importance of social networks for analyzing and explaining criminal behavior has been widely recognized. A wide range of illegal activities, such as drug trafficking, human smuggling, or terrorism requires coordination among offenders to be successfully performed. It is not surprising, therefore, that the network perspective on crime has recently gained popularity, both among academics and law enforcement practitioners, as it captures the essence of such activities.

 

However, the study of criminal networks is challenging. Data collection is difficult in situations where subjects themselves aim not to be detected. Gathering first-hand evidence on such phenomena is therefore extremely difficult, and in some cases dangerous. Scholars have thus relied on police data, such as arrests, or investigative evidence, such as electronic surveillance or phone records, to build an empirical base for their analysis. A second challenge is methodological, i.e. matching/developing the right statistical models based on the specificities of criminal networks to adequately test criminological theories, allowing to move beyond descriptive network measures.

 

This session is dedicated to innovative research at the intersection of network analysis and criminology. We welcome a wide range of submissions focused on criminal networks, including methodological, theoretical, and empirical studies. Topics may include: collection of criminal network data, testing theories of co-offending, victimizations and violence using network data, case studies of specific criminal groups, and statistical modelling tailored to the complexities of criminal network data.

 

Keywords: covert networks, criminology, methodological innovation, co-offending, violence, organised crime, illegal markets, criminal networks, terrorist networks.

Organised Session 12: Organizational Networks

 

Spyros Angelopoulos, Durham University (spyros.angelopoulos@durham.ac.uk)
Emmanuel Lazega, SciencesPo
Francesca Pallotti, University of Greenwich
Paola Zappa, Maynooth University

 

The networked nature of organizations, and the organizational contexts of network dynamics create a complex ecosystem where individuals, groups, units, and other organizations are entangled and recursively active. Such entanglement shapes organizations in a dynamic way and affects their outcomes at multiple levels.

 

This session aims to bring together studies on organizational networks addressing antecedents, dynamics, and implications of the cross-level processes leading to the emergence of relations and outcomes at various levels. Submissions can refer, but are not limited, to the following areas of research:

 

• Micro-foundations of organizational networks: how individual characteristics and cognition affect the emergence of network structures and how these network structures affect individuals;
• Dynamics of organizational networks: how network structures at various levels co-evolve and affect one another, as well as organizational processes and outcomes;
• Time-dependence in organizational networks: how organizational networks at various levels change at different paces over time;
• Overlap and interplay between social and other kinds of networks within and across organizational settings: how organizational networks are affected by the affiliation of individuals, or organizations to events or contexts.

 

We welcome both theoretical and empirical contributions addressing various aspects and implications of organizational networks research.

Organised Session 13: Political Networks

 

Dimitris Christopoulos, Modul University Vienna
Manuel Fischer, University of Bern
Christina Prell, University of Groeningen
James Hollway, Graduate Institute, Geneva)
Petr Ocelik, Masaryk University (petr.ocelik@gmail.com)

 

We propose an Organized Session on Political Networks. The Session should provide a multidisciplinary space of convergence for scholars that, while holding diverse research interests in the study of politics, policy-making and political behaviour share an analytic approach to network processes in political life, coupled with strong attention to the integration of theory and empirical data. Political networks are conceived of in a broad sense - as defined around political actors, events that are relevant to the political biographies of individuals as well as around the use of digital communication technologies within political dynamics, among others. Thus, ties can consist of exchanges of resources, information, and symbols, as well as of collaborations and communications that may occur both on- and offline. Substantive issues that researchers in political networks have been dealing with are policy networks around climate change on the local, national and international levels, networks of social movement organizations, comparisons of networks across different institutional contexts, or political interactions within new social media, among others.

 

Organized Sessions on Political Networks have been well frequented at past Sunbelt / EUSN conferences, the session is endorsed by the Standing Group on Political Networks of ECPR (European Consortium on Political Research).

Organised Session 14: Population-scale Social Network Analysis

 

Eszter Bokanyi, UvA (e.bokanyi@uva.nl)
Laszlo Lorincz, Corvinus Universtiy
Guilherme K. Chihaya, Umeå University
Frank Takes, Leiden University
Eelke Heemskerk, University of Amsterdam

 

Multiple countries set up digital infrastructures to utilize citizen registers for academic research purposes. Recent technological advances make it possible to use these registers as rich resources for population-scale social network analysis by deriving formal ties of people based on, e.g., family, education or employment data. It enables new exciting research of relations at an unprecedented, representative scale, leading to actionable insights into key issues such as segregation, social change, or inequality. This fits in well with EUSN’s goal of providing a platform for the exchange of ideas on social network research. Discussing this novel branch of large-scale social networks, their potentials and limitations with respect to existing methods will likely be beneficial for participants of EUSN.

 

Organised Session 15: Public Policy and Discourse Networks

 

Philip Leifeld, University of Essex (philip.leifeld@essex.ac.uk)

 

Networks of political actors, such as legislators, interest groups, charities, NGOs, firms, political parties, and government agencies and branches, play a pivotal role in the policy process. They influence agenda setting, engender policy change or promote policy stability, act as backbones of polycentric or multi-level governance systems, and they can vary across institutional settings. In the literature, a variety of networks in public policy has been analysed, including discourse networks/policy debates, information exchange or collaboration among political actors, social media interactions, staff exchange, reputational networks, issue networks, lobbying relationships, and membership in organisations or forums. Policy and discourse networks can produce consequential structures, such as polarised advocacy coalitions, central brokers or opinion leaders, or polycentric clusters.

 

This panel invites submissions about applications of network analysis to the study of public policy, applications of discourse network analysis, the intersection between discourse and policy networks, the study of lobbying and interest groups, methodological contributions to the study of policy or discourse networks, and comparisons of networks across institutions, topics, data sources, or relations.

 

Organised Session 16: Social Cybersecurity: Convergence of Social Network Analysis in Cyber

 

Srinidhi Vasudevan, University of Greenwich (srinidhi.vasudevan@greenwich.ac.uk)
Anna Piazza, University College London
Madeline Carr, University College London

 

Building on cyber security that specifically focuses on machines and technology, social cyber security is an emerging and interdisciplinary field with perspectives from sociology, communication science, forensics, economics, linguistics, social psychology, and political science to name a few. Social cyber security looks at people, processes and technologies and the interactions between them to identify the influences impacting security behaviours of actors. Social Network Analysis provides a relational approach to provide a context for the creation and maintenance of social relations. Networks are embedded in cyber norms, cultures, values, and behaviours which for instance can vary according to contexts. For instance, cyber information sharing networks can differ across industries and countries, cyber behaviour can be influenced not only by organisational culture and norms but also by the patterns of social interactions among individuals within the organisations, criminal gangs on the Dark Web manipulated by ringleaders and the network topologies, cyber investments determined by interactions between the organisation’s risk appetite and its environment etc. This organized session brings together research that addresses these and related questions through a broad, cyber-network perspective.

 

To develop ‘social cybersecurity’ as a framework, we solicit methodological, conceptual, and empirical contributions that model, predict, and/or explain how social ties that are created and maintained by actors in a digital environment.

 

Topics of interest include but are not limited to the following lines of enquiry:

 

• Organised crimes, forensics, criminal behaviour;
• Cyber user behaviour and networks;
• Diffusion, misinformation, and disinformation;
• Mental health of cyber practitioners;
• Information sharing networks in cyber;
• Governance structure and cyber policy;
• Data science, machine learning, natural language processing and agent-based simulation in cyber space;
• Contexts of tie creation, maintenance, and dissolution in cyber space;
• Organisation and industry pertaining to cyber investment and policy.

Organised Session 17: Social Influence

 

Andras Voros, University of Manchester (andras.voros@manchester.ac.uk)
Zsófia Boda, University of Essex

 

The empirical study of social influence processes has become an increasingly popular topic in social network research in the past years. Advances in data collection and statistical modelling have made it possible to explore and distinguish various influence processes in longitudinal data on networks and individual behaviour. For instance, it is now possible to study which actors are likely to influence which other actors in a network. Further, we may also compare the influence from specific actors and from being in a certain network position, such as influence from and on popular individuals. Social influence is conceptually not even limited to network-and-behaviour studies. We can also investigate mechanisms of network-network influence, where one (one-mode) network defines what the reference group of social actors is that exerts influence, while another (one- or two-mode) network indicates what is being influenced. In this session, we welcome methodological, theoretical, and applied contributions to the study of social influence in networks, as long as they are relevant for empirical research.

 

Organised Session 18: Social Network Analysis and International Business

 

Kim Bui, University of Greenwich
Pi-Chi Chen, University of Greenwich
Bruce Cronin, University of Greenwich (c.b.cronin@gre.ac.uk)
Lena Langosch, University of Greenwich

 

Networks are a central concept in the study of International Business (IB) from supply and value chains to parent-subsidiary relationships and the embeddeness of multinational subsidiaries in host country environments. A core perspective in IB research is the use of a network lens through which firms are conceptualized as “embedded in social networks with other actors” (Andersson, Forsgren, & Holm, 2002; Granovetter, 1985). But while the theory of networks has attracted increasing attention in IB research, the systematic description, modelling and analysis of network relationships has still been scarce in IB research (Kurt & Kurt, 2020). Few studies of international business networks take the concept beyond metaphor.

 

Social network analysis (SNA) provides a rich set of mixed methods ability to provide contextual, longitudinal, multilevel, and processual explanations of International Business phenomena (Buchnea & Elsahn, 2022). As such, the incorporation of SNA and IB can be used to understand the path-dependent process of network development and change over time, and the implications of network embeddedness for firms’ behaviour and strategies. This conference track aims not only to incorporate theory of networks in IB research, but also recognise and highlight outstanding use of SNA to investigate pertinent IB phenomena.

 

The track therefore seeks to showcase rigorous and trustworthy use of SNA in IB research and question methodological conventions in SNA and IB and promote cutting-edge developments in SNA and IB methodological approaches. The EU Social Networks Conference Social Network Analysis and International Business track welcomes high quality submissions in the form of conceptual and empirical papers that develop new perspectives on SNA in IB that fit the 21st century global landscape. Studies employing a SNA perspective have enriched the understanding of international business, suggested areas of interest include (but not limited to) the following:

 

• Application of SNA in the speed and characteristics of internationalisation of multinational enterprises (MNEs) (Musteen et al., 2010).
• Knowledge exchange and transfer and learning within and outside of MNEs, including HQ- subsidiary relationships (Geppert & Dörrenbächer, 2014; Sandberg, 2014; Khan, Rao-Nicholson & Tarba, 2018).
• Types of cross-border relationships (Holm et al., 1996, Pedersen et al., 2019).
• Entrepreneurship (Coviello, 2006) and Internationalization of SMEs (Chetty & Holm, 2000).
• Exploration on how businesses interact with its environments (Welch & Wilkinson, 2004; Jansson, Johansson & Ramström, 2007).
• Corporate political activity and how firms manage the socio-political environment (Elsahn & Benson-Rea, 2018).

 

Further suggested questions and areas of interest include the following:

 

• What network theories can we develop to address new challenges in IB?
• How can we adapt SNA methods for today’s IB research challenges?
• How can SNA account for the dynamism and temporality of IB phenomena?

 

Organised Session 19: Social Network Analysis and System Science for Social Change

 

Emily Long, University of Glasgow
Claudia Zucca, Tilburg University (c.zucca@tilburguniversity.edu)
Mark McCann, University of Glasgow

 

Many of the problems that researchers and practitioners face every day addressing social, economic, political, and health issues are complex. A complex problem is characterized by the unpredictability of an outcome when we intervene in the system. For instance, promoting a policy to provide jobs for people who are unemployed, while not considering the many reasons they may be unemployed in the first place. In order to address complex problems, the field of system science employs a range of methodologies to intervene in complex systems and produce outcomes that are good for society. Social Network Analysis is one of the methods in the system science toolkit, alongside complementary methods such as agent-based modelling, System Dynamics, system thinking, etc.

 

This session will bring together scholars from social network analysis and system science to discuss research aimed at understanding complex systems where variables are intertwined, and outcomes are non-linear. We welcome studies that combine other system science approaches to network analysis, for instance, ABM simulations of social networks or semantic networks derived from causal loop diagrams. Both qualitative and quantitative research is welcome.

 

We are particularly interested in hearing from colleagues whose work is aimed at social change – researchers who collaborate with stakeholders in social, political, economic and health science. For instance, research that addresses problems such as adopting policies, the impact of new laws, effects of inflation, comorbidity of diseases, and the implication of loneliness for young people would be a good fit for this panel.

 

Organised Session 20: Social Networks and Personal Communities in Migration and Migrant Incorporation

 

Raffaele Vacca, University of Milan (raffaele.vacca@unimi.it)
Başak Bilecen, University of Groningen

 

Migration scholars have long called attention to the central role of social and personal networks in shaping migrants’ mobility patterns, migration decisions, incorporation trajectories, and transnational activities. However, while certain network metaphors and notions have always been popular in migration research, the actual collection and analysis of network data has been far less common in this field. A recent special issue of Social Networks showcased the potential of network data and methods, both egocentric and sociocentric, to answer different and fundamental questions in migration studies. This recurring EUSN/Sunbelt session aims to highlight the richness and variety of social network studies of migration and migrant incorporation, and their ability to open up new avenues in theoretical and empirical research in this area.

 

We are particularly interested in micro- and meso-level studies of sociocentric or egocentric networks, and their association with migration contexts, environments, and outcomes. Topics of interest include, but are not limited to:

 

• The role of social networks in different migration phases (initiation, transit, settlement, etc.);
• The composition, structure, size, spatial dispersion, dynamics etc. of migrants’ personal or egocentric networks;
• Networks, social support and migrant health;
• Networks and ethnic identity, ethnic segregation, or ethnic neighborhoods;
• Social relationships and migrant transnationalism;
• Social networks in specific migrant populations (e.g. elderly migrants, international students, return migrants);
• Network change among migrants and over the migration trajectory;
• Comparative studies of networks and migration (e.g., migrants vs. non-migrants, different migrant generations, forced vs. voluntary, documented vs. undocumented, female vs. male migrants, etc.);
• Mixed-methods studies of migrants’ social networks.

 

Organised Session 21: Social Support and Health

 

Guy Harling, University College London (g.harling@ucl.ac.uk)

 

A key aspect of social networks as they relate to health is the support and advice that flows through the network. This support is connected to, but distinct from, network position/structure itself. We invite abstracts that consider any aspect of social support and health on networks, focusing on what flows through ties as causal mechanisms for network or health status change in individuals. This might include how health-related support is generated within networks, or how it is patterned across networks (e.g. by age, gender, social status). It might also include longitudinal analysis of how support or advice predicts health knowledge, behaviour or outcome, or how health predicts receipt of support. Finally, we would be delighted to include work evaluating how interventions change social support and thus health in a network context.

 

In previous iterations, health topics have included substance use, sexual health, mental health and non-communicable health conditions – but other areas of research are welcome. While the sessions have primarily focused on quantitative analysis, qualitative and mixed-method approaches are welcome.

 

This session will be populated from submissions to the open call for abstracts for EUSN 2022.

 

Organised Session 22: Sustainability and Social Network Analysis

 

Stefano Ghinoi, University of Greenwich (s.ghinoi@greenwich.ac.uk)
Riccardo De Vita, University of Greenwich

 

In the last years, social network analysis (SNA) has been widely applied in business and economics studies, focusing on different levels of analysis and actors – small and medium enterprises, multinational companies, local and international institutions, and non-governmental organizations. One of the major focal points of the innovative efforts for such actors has been the definition, development, and implementation of sustainable practices, in order to change production paradigms and addressing emerging requests from local communities and policymakers, such as the achievement of the Sustainable Development Goals (SGDs) and the introduction of a circular economy system.

 

This session is looking for contributions that specifically concentrate on the application of network theories and methods for investigating the application of sustainable practices. We encourage scholars to submit proposals using both qualitative and quantitative approaches, and drawing on different datasets. Moreover, theoretical contributions and empirical analyses are all welcome, as well as case study papers representing all experiences that have emerged in different regions and countries. Possible topics for article submission include, but are not limited to:

 

• Inter- and intra-organizational networks and sustainable practices;
• Sustainability policies and networking;
• Sustainable Development Goals;
• Strategic partnerships for supporting sustainable business innovation;
• Circular economy and social network analysis;
• Sustainable practices at local level;
• Social relationships and social sustainability;
• Supply chain management, networks, and sustainability.

 

Organised Session 23: Teaching Social Network Analysis

 

Riccardo De Vita, University of Greenwich
Yasaman Sarabi, Edinburgh Business School, Heriot-Watt University (y.sarabi@hw.ac.uk)
Matthew Smith, Edinburgh Napier University
Guido Conaldi, University of Greenwich

 

More and more institutions across the world now include teaching of Social Network Analysis (SNA) as part of their offer. SNA is taught across different levels and either as a separate subject, often presented as a methodology, or embedded within specific disciplinary contexts. In some cases, SNA is the object of full programmes of study. The emphasis of teaching also varies across institutions, with some modules focusing on the theoretical concepts behind SNA, and others emphasising the use of software to perform SNA. Finally, universities, when introducing SNA concepts and ideas, need to be mindful of the expectations of students and employers, who are often interested in networking and successful networking behaviour in the workplace. Despite the growing popularity of teaching SNA, the SNA community lacks a formal forum to exchange ideas and practices about teaching SNA. This session seeks contributions on teaching SNA, focusing on best practices, challenges, and pedogeological reflections. We aim to create a platform to exchange views about the opportunities and challenges in teaching SNA and establish a first opportunity for teachers of SNA to share their experiences.

 

We welcome submissions discussing any issue associated with the teaching of SNA, including but not limited to:

 

• Teaching network theory;
• Teaching qualitative SNA;
• Teaching quantitative SNA;
• Teaching software for SNA;
• Teaching SNA across different levels (undergraduate, postgraduate, postgraduate research and executive education);
• Opportunities, best practices, and challenges of teaching SNA;
• Teaching SNA and networking behaviours;
• Experiments and SNA;
• Teaching SNA in different cultural contexts.

 

The contributions could be work in progress or completed studies. We welcome both theoretical and empirical studies, as well as those which are more focused on pedagogical reflections.

 

Workshops

Click anywhere on the workshop titles to see the instructors and details.

Monday 12th September, Full-day Sessions (6 hours)

Workshop 2: Handling Missing Network Data - Theory and Practice

 

Robert W Krause, Free University Berlin (robert.w.krause@fu-berlin.de)

 

Missing data are an all too common problem in network research. Due to the dependencies between the nodes, the very object of our studies, these missings constitute a far bigger problem in networks than they do for non-network data. Having given the workshop multiple times now, the empirical evidence suggests that a simple three hour workshop is not enough to properly dive into this complex problem. Therefore the workshop will be offered for six hours for the first time. In the first three hours of this workshop, we will discuss the theoretical and practical implications of missing data (What actually is missing data? What does it do to my data? How does it bias my results? Which treatments exist? What are their pros and cons?) and, crucially, relate these directly to your field(s) of study, your current missing data problems.

 

In the second part of the workshop we will make use of state of the art missing data treatments (multiple imputation with Bayesian ERGMs and/or SAOMs) to get hands on experience on how to handle missing data. This part will require some basic knowledge of ERGMs and SAOMs and thus includes a crash course in these model families - if scheduling allows, a visit to the introductory workshops on (B)ERGM or SAOM will of course be helpful. Where possible (given data and prior knowledge in R and the respective model families), participants will also have the opportunity to run models on their own data to obtain first imputations for their future analyses. Additionally, the workshop will also feature potential treatments for missing nodal attribute data.

 

The workshop is open to all, especially the first three hours. The second three hours, too, are open to all, but participants with prior experience in ERGMs and SAOMs will profit most from this part. However, introductory material will be provided before hand and a short introduction in the nature of these model families will be given.

 

 

Monday 12th September, Morning Half-day Sessions (3 hours)

Workshop 3: Discourse Network Analyzer 3.0

 

Philip Leifeld, University of Essex (philip.leifeld@essex.ac.uk)

 

Discourse Network Analyzer (DNA) is a desktop application with a graphical user interface for annotating text data with actor-based statements and exporting the data as networks. It was designed for the analysis of policy debates as temporal networks. The user loads source material, such as newspaper articles, speeches, or similar into the software, defines the variables a statement is comprised of, such as person, organisation, concept, and agreement, adds statements to the text while reading, and then exports a network of statements, such as an actor x actor congruence network, a bipartite graph of actors and concepts, or a series of temporal snapshots of how the actor network evolves over time. Discourse Network Analyzer can export to visone and Ucinet, and there is an associated R package called rDNA for direct interaction between DNA and R, which facilitates data transfer and adds techniques for analysing the resulting networks.

 

The new version 3.0 of Discourse Network Analyzer has been developed since 2021 and will be released this summer. The three-hour workshop introduces the software and gives an overview of what kinds of networks to export and how to analyse them in the separate network analysis software visone.

 

Participants are required to install Java (e.g., Adopt OpenJDK 11 from https://adoptopenjdk.net/) and download Discourse Network Analyzer along with its manual and sample database from https://github.com/leifeld/dna as well as visone from https://visone.ethz.ch before the workshop begins.

Workshop 4: Introduction to Network Analysis tools in R

 

Michal Bojanowski, Kozminski University (mbojanowski@kozminski.edu.pl)
Lorien Jasny, University of Exeter

 

Those wishing to use the R programming language for network analysis now have a plethora of choices when it comes to libraries. In this workshop, we survey the main packages used for network data management, analysis, and visualization. We will cover 1) importing network data (from actual files), 2) network objects and attributes, 3) computing basic descriptives (attribute distribution, mixing matrix, density, degrees, betweenness, closeness), and 4) visualization (layouts, node aesthetics). These will be done side by side for the different packages, as well as discussion of the strengths and weaknesses of each. We conclude with time for attendees to work either on toy datasets or with their own data with help from instructors. This workshop is a unification of workshops “Using R and ‘igraph’ for Social Network Analysis” and “Introduction to Social Network Analysis with R and statnet” that has been offered on Sunbelt and EUSN conferences since 2011. It will serve as an introduction for those wishing to take “Moving beyond descriptives”, “Using ‘igraph’ for SNA: advanced topics”, “An introduction to ERGM with Statnet”, or other Statnet-related workshops on the program.

Workshop 5: The Analysis of Longitudinal Social Network Data using RSIENA

 

Per Block, University of Oxford (per.block@sociology.ox.ac.uk)

 

This workshop is about analysing social networks panel data, understood here as two or more repeated observations of a directed graph on a given node set (usually between 20 and a few hundred nodes). The workshop teaches the statistical method to analyze such data, for which a tutorial is given in “Snijders, T.A.B., Steglich, C.E.G., and van de Bunt, G.G. (2010), Introduction to actor-based models for network dynamics (Social Networks, 32, 44-60)”. The method is implemented in RSiena, a package of the statistical system R. The workshop will demonstrate the basics of using RSiena. Attention will be paid to the underlying statistical methodology, to examples, and to the use of the software.

 

The statistical model is the actor-oriented model where the nodes are actors whose choices determine the network evolution. This allows to include various network effects (reciprocity, transitivity, popularity, etc.), effects of individual covariates (covariates connected to the sender, the receiver, or the similarity between sender and receiver), and of dyadic covariates.

 

An important extension is to have, in addition to the network, one or more actor variables that evolve in mutual dependence with the network; an example is a friendship network of adolescents where drinking behavior is a relevant actor variable which influences, and is influenced by, the friendship network. This leads to models for the simultaneous dynamics (‘co-evolution’) of networks and behavior, which are a special option in RSiena.

 

The first part of the workshop will focus on the intuitive understanding of the model and operation of the software. The second part will present models for the simultaneous dynamics of networks and behavior and other more advanced topics such as model specification, multivariate networks, and goodness of fit checking.

 

Further information about this method can be found at the SIENA website (http://www.stats.ox.ac.uk/~snijders/siena).

 

Prerequisites:

 

Course participants should have a basic understanding of model-based statistical inference (say, logistic regression), some prior knowledge of social networks, and should have had some basic exposure to the R statistical software environment. They are expected to bring their own laptop to the course (Windows, Mac or Linux), with the R statistical software environment and the RSiena package pre-installed. Participants for whom R is new are requested to learn the basics of R before the workshop: how to run R and how to give basic R commands. This is to reduce the amount of new material to digest at the workshop itself. The Siena website (RSiena tab) has some links which can be helpful for this purpose. Further instructions will be given before the conference starts

Workshop 6: The goldfish package in R

 

Christoph Stadtfeld, ETH Zürich
James Hollway, Graduate Institute, Geneva
Marion Hoffman, IAST
Alvaro Uzaheta, ETH social networks lab (alvaro.uzaheta@gess.ethz.ch)

 

Goldfish is an R package for analyzing relational event data using a variety of models. In particular, it implements different types of Dynamic Network Actor Models (DyNAMs), a class of models tailored to the study of actor-oriented processes. Goldfish also implements different versions of tie-oriented relational event models.

 

The workshop participants will learn to describe relational event data in R, estimate different models with the goldfish package, inspect and interpret results.

 

Prerequisites:

 

Course participants should be familiar with R and model-based statistical inference (such as logistic regression). They are expected to bring their laptop to the course with the R statistical software environment, the goldfish package, and dependencies installed.

 

More information about the package and installation is available on Github: https://github.com/snlab-ch/goldfish

Workshop 7: In-person and remote social network interviewing with Network Canvas

 

Bernie Hogan, University of Oxford (bernie.hogan@oii.ox.ac.uk)
Joshua Melville, Northwestern University

 

This workshop shows how to use the free, cross-platform software Network Canvas (www.networkcanvas.com) to conduct structured or semi-structured social network interviews both in-person and via video conferencing software. Network Canvas is designed for creating personal networks with a respondent using a variety of highly visual and touch optimised controls. This includes features for doing work with name generators, rosters, free recall, dyad census, and drawing edges manually. The software is structured into a series of stages and is regularly reported by respondents as fun and engaging. Data can be exported for use in most major social network analysis packages and apps. This workshop will focus on the Interviewer app for deploying interviews and the Architect App for designing interviews.

 

Order of topics:

• Guided walkthrough of an interview using the Interviewer app.
• Guided walkthrough of how it was created in the Architect app.
• Activity showing how to modify the interview in Architect followed by doing a Network Canvas interview with a peer.
• Discussion of strategies and issues for doing remote interview sessions considering the limitations of Zoom, Google Meet, and Teams.
• Time permitting, a brief guide to selected advanced features including skip-flow logic, prompt-based labelling, R export, and how to produce basic descriptive statistics.

 

The convenor will provide example protocols and scripts for users to work with. These will be available via URL and shared shortly before the workshop. Prior materials are available via the Network Canvas documentation page: https://documentation.networkcanvas.com/

 

Pre-requisites:

Course participants should arrive with a working copy of Network Canvas Interviewer and Architect installed on a personal computer such as a Mac OSX or Windows machine. Network Canvas is available from https://www.networkcanvas.com/

 

 

Monday 12th September, Afternoon Half-day Sessions (3 hours)

Workshop 8: REM beyond dyads: relational hyperevent modeling with eventnet

 

Juergen Lerner, University of Konstanz (juergen.lerner@uni-konstanz.de)
Alessandro Lomi, Università della Svizzera italiana

 

Networks of social relations and communication networks frequently generate information on repeated interaction over time. This information typically takes the form of relational event sequences - streams of time-ordered events connecting social actors. Examples of relational events are common. Conversations, email communication, interaction among members of teams, participation in social gatherings or in peer-production projects, are all examples of interactive settings that may generate observable streams of relational events. In this workshop we will specifically discuss “polyadic” social interaction processes in which events can connect varying and potentially large numbers of actors simultaneously. Examples of such polyadic events (or “hyperevents”) include sequences of meeting events or social gatherings, connecting all of their participants simultaneously, or multicast (i.e., “one-to-many”) communication events such as emails in which one actor sends the same message to several receivers.

 

This half-day workshop provides a hands-on introduction to relational hyperevent models (RHEM). We start with an informal discussion of the research questions (or network effects) that can be addressed by a RHEM analysis of meeting events extracted from contact diaries and illustrate practical analysis of the famous Davis, Gardner, and Gardner “Deep South / Southern Women” data with the open-source software eventnet (https://github.com/juergenlerner/eventnet). In the second part of this workshop we will discuss directed relational hyperevents resulting from multicast communication and illustrated by an analysis of the Enron email data.

 

The workshop is targeted at participants interested in statistical modeling of networks based on relational event data - with a specific focus on polyadic, multicast, or one-to-many interaction events. Participation to the workshop does not assume any particular prior knowledge or experience with statistical models for social networks. Participants are invited to informally point us to their own research projects, which may possibly be addressed by a RHEM analysis, prior to the workshop.

 

References:

 

Lerner and Lomi (2020). Reliability of relational event model estimates under sampling: How to fit a relational event model to 360 million dyadic events. Network science, 8(1), 97-135.

 

Lerner, Lomi, Mowbray, Rollings, and Tranmer (2021). Dynamic network analysis of contact diaries. Social Networks, 66, 224-236.

 

Lerner and Lomi (2021). Relational hyperevent models for polyadic interaction networks. arXiv preprint arXiv:2112.10552.

 

Lerner and Lomi (2022). A dynamic model for the mutual constitution of individuals and events. Journal of Complex Networks (to appear).

Workshop 9: Using igraph for SNA: advanced topics

 

Michal Bojanowski, Kozminski University (mbojanowski@kozminski.edu.pl)

 

Package igraph (Csardi and Nepusz 2006) is one of the main packages for network data handling, visualization and (descriptive) analysis. We take a deeper dive into the capabilities and focus on: (1) Indexing/subscripting network objects: querying nodes/ties by their properties and properties of ties/nodes they are incident upon. (2) Advanced visualization techniques (3) Studying connectivity (paths, connected components, cliques) (4) Network homophily, segregation and community detection. The workshop is designed for users familiar with the basics of R and ‘igraph,’ such as covered in the workshop “Introduction to Network Analysis Tools in R.” Elements of this workshop have been previously available as a part of “Using R and ‘igraph’ for Social Network Analysis” workshop offered on Sunbelt and EUSN conferences since 2011. This document is also designed for self-study with code examples and data from publicly available sources.

Workshop 10: migraph: multimodal network analysis

 

James Hollway, Graduate Institute, Geneva (james.hollway@graduateinstitute.ch)
Jael Tan, Graduate Institute, Geneva

 

The fields, arenas, or social spaces in which action takes place are never unidimensional but contain multiple types of actors and relations. Yet a common approach has been to ‘project’ any multimodal network data collected to one-mode networks to leverage existing network analytic packages. However, as outlined in Knoke, Diani, Hollway and Christopoulos’ (2021) Multimodal Political Networks, such an approach is no longer necessary as a host of techniques are readily available to those who wish to analyse multimodal networks.

 

This workshop introduces migraph, a new, complementary R package for the analysis of networks including multimodal and multilevel networks. It builds upon and works natively with igraph, sna/network, and tidygraph objects, as well as edgelists and adjacency and incidence matrices, and so works well with your existing workflows. Its functions work equally well with one-mode and two-mode (and sometimes three-mode or multilevel) network data, offering appropriate normalisations, procedures, and sensible defaults for different classes and types of networks. In addition to measures for e.g. centrality and cohesion, the package includes routines for CUG and QAP tests, blockmodelling, and MRQAP that work with two-mode networks.

 

The goal of this workshop is to provide an overview of multimodal network analysis and to teach participants how to conduct analyses on multimodal network data using the migraph package. The practical elements make use of R scripts, and so familiarity with R is recommended. Participants can bring their own research problems and data and, depending on the number of participants, remaining time can be used to discuss them.

Workshop 11: Generalized blockmodeling in R using blockmodeling package blockmodeling

 

Aleš Žiberna, University of Ljubljana (Ales.Ziberna@fdv.uni-lj.si)
Marjan Cugmas, University of Ljubljana

 

The workshop will cover generalized blockmodeling (Doreian et al., 2005; Žiberna, 2007) of mainly one-mode binary and valued networks in R using “blockmodeling” package (Žiberna, 2021). Only basic knowledge of R and networks/graphs is required. The workshop will cover matrix representation of the network, plotting of such matrices, and of course, clustering the units in the network, that is blockmodeling. Clustering units based on structural, regular and generalized equivalence will be covered. The later implies that also pre-specified blockmodeling will be covered. All aspects of blockmodeling with the blockmodeling package from preparing the data through calling the optimization function (including setting appropriate parameters) to plotting and interpreting the results will be covered. In case of sufficient time and expressed interest, blockmodeling two-mode, multilevel, and linked networks can also discussed.

Workshop 12: Introduction to UCINET

 

Srinidhi Vasudevan, University of Greenwich (Srinidhi.Vasudevan@greenwich.ac.uk)
Anna Piazza, University College London

 

This introductory workshop outlines the theoretical concepts of social network analysis and operationalisation of network measures through the use of the software Ucinet/Netdraw. The workshop covers the theoretical and empirical overview of the social network research field with an emphasis on the main concept of social network analysis, such as centrality, cohesion and social capital; and aspects of data collection and management for visualising and analysing networks through the software. The workshop will provide examples of applications of networks in various fields including education, management, health and bibliometric research and we will try to other examples that are relevant to the participants.

 

Ucinet/Netdraw can be downloaded from https://sites.google.com/site/ucinetsoftware/home and participants are strongly encouraged to download it prior to the workshop.

 

 

Friday 16th September, Full-day Sessions (6 hours)

Workshop 13: Advanced RSiena workshop

 

Tom A.B. Snijders, University of Groningen / University of Oxford (t.a.b.snijders@rug.nl)

 

This workshop is intended for participants who have experience in working with RSiena.

 

Topics treated will be the following – all in the framework of modelling network panel data using the RSiena package.

 

• Multivariate networks: cross-network effects; with attention to the associated hierarchy requirements.
• Two-mode networks.
• Co-evolution of two-mode and one-mode networks.
• Valued networks (two kinds: networks with weak and strong ties; signed networks).
• Multilevel estimation using sienaBayes.
• Parameter interpretation: semi-standardized parameters: entropy-based approach to explained variation.

 

SIENA website: http://www.stats.ox.ac.uk/~snijders/siena

Workshop 14: Using patent data for collaboration network analysis. An application with USTPO data in PatentsView

 

Pablo Galaso, Universidad de la Republica (pablogalaso@gmail.com)
Sergio Palomeque, Universidad de la Republica

 

This workshop aims to provide practical training in the use of patent data for the study of collaborative networks. Patent data is a source of information on invention developments at the level of regions, countries, cities, or other types of sub-national dimensions. One of the difficulties of this type of administrative records is that patent offices do not assign a unique identifier to inventors or owners and, for this reason, the analysis of linkages between agents is not always possible. In recent years, various efforts have been made to disambiguate patents. Among them, the PatentsView project stands out (https://patentsview.org/), which works with patents registered at the United States Patent and Trademark Office (USPTO) by applying an algorithm that analyses each registration and determines whether two agents can be the same. From this information, it is possible to construct incidence matrices linking inventors, owners (i.e. firms and organisations), cities, regions, countries or even technologies. These data may reflect either co-partnership or co-authorship between actors (e.g. two inventors involved in the same patent). However, this does not necessarily imply collaboration, which is why some scholars propose to apply Back Bone Extraction (BBE) techniques that allows to identify significant links to approach the phenomenon of collaboration.

 

The workshop will provide participants with information on how to access the raw data available in the PatentsView platform, different ways of systematising this information to build networks, some BBE techniques to define meaningful links and certain specificities of the study of the topological structure in this type of networks. An overview of the meaning and usefulness of an important part of the tables available on the platform will be given. Finally, examples of research works that have used them will be presented and some of the general limitations of this type of data, as well as those particular to PatentsView, will be discussed. Special emphasis will be placed on the technologies associated with patents and how to use them from a social network analysis perspective, allowing this methodology to be applied to units of analysis that are not people or organisations, but rather technological fields.

 

The specific objectives offered by the workshop to its participants are: (i) to become familiar with patent data and its usefulness for the study of network analysis, (ii) to become familiar with the main literature on the subject, (iii) to download USPTO data available through the PatentsView platform, (iv) to learn about and process the different tables included in the database, (v) to build different types of collaborative networks from this data, and (vi) to analyse these networks, emphasising some stylised facts common to this type of interactions.

 

Previous knowledge of the participants: it is recommended (although not exclusive) that attendees have a basic knowledge of R and RStudio, as well as a general knowledge of Social Network Analysis.

Workshop 15: Egocentric network analysis with R

 

Raffaele Vacca, University of Milan (raffaele.vacca@unimi.it)

 

This workshop is an introduction to the R programming language and its tools to represent, manipulate and analyze egocentric or personal network data. No previous familiarity with R is required. To participate you only need a laptop with R and RStudio installed. Topics include: introduction to ego-network research and data; introduction to data structures and network objects in R; visualizing ego-networks; calculating measures on ego-network composition and structure; converting your ego-network measures to general R functions; applying your functions to many ego-networks. The workshop emphasizes R tidyverse packages for data science. We’ll show how tidyverse functions can be used to easily conduct common operations in egocentric network analysis and to scale them up to large collections of ego-networks. We’ll cover both base R functions and specific packages for network analysis (igraph, network, egor), data management (dplyr) and programming (purrr). We’ll also provide a brief introduction to the egor package for ego-network analysis, and pointers to further resources to learn more about it. This workshop has been taught for the past nine years at several international conferences, including INSNA’s Sunbelt and EUSN meetings. It draws on concepts and methods discussed in “Conducting personal network research: A practical guide” by Christopher McCarty, Miranda Lubbers, Raffaele Vacca and José Luis Molina (Guilford Press)

 

More details on the workshop’s materials, history and instructor are here: raffaelevacca.com/egonet-r.

 

 

Friday 16th September, Morning Half-day Sessions (3 hours)

Workshop 16: Analysis of multiplex social networks (hands on with R)

 

Matteo Magnani, Uppsala University (matteo.magnani@it.uu.se)

 

A multiplex network is a network where actors are connected through different types of ties, such as individuals “working together”, “being friend”, etc. These different types of connections are also known as layers.

 

The workshop covers several topics in multiplex network analysis, including a selection of: community detection, layer comparison methods, actor measures, data exploration and network generation, depending on time and interest of the participants. For each topic, a quick presentation of the relevant theory and methods is followed by a practical application on a real pedagogical dataset. Part of the presented theory is covered in the book “Multilayer Social Networks” and in recent survey articles, such as “Community detection in multiplex networks” (ACM Computing Surveys) and “Quantifying layer similarity in multiplex networks: a systematic study” (Royal Society Open Science), and in several research papers developed in different fields by different authors.

 

The short theoretical presentations are all meant to provide the necessary knowledge to perform practical exercises with network analysis software. This is an updated version of a workshop already given at previous conferences (including SunBelt and EUSN).

 

In this workshop we will use the multinet library, available on the CRAN archive since 2017. Only limited knowledge of R is needed, as we will mainly use library functions. However, knowledge of R and igraph can be useful to understand some topics in more detail.

 

The proposed duration is 3 hours (including breaks), and the target are researchers at any level of seniority interested in an introduction to multiplex networks.

 

The lecturer has authored several research and survey articles on multilayer networks during the last 11 years, is the main author of the software, and is a Distinguished University Teacher at Uppsala University.

Workshop 17: Moving beyond descriptives: basic hypothesis testing with R/Statnet

 

Lorien Jasny, University of Exeter (L.Jasny@exeter.ac.uk)

 

This workshop will cover basic statistical methods for network analysis within the R/statnet platform. The approach taken is practical rather than theoretical, with emphasis on simple, robust methods for hypothesis testing and exploratory data analysis of single and multi-network data sets. Topics include: permutation tests for marginal relationships between node or graph-level indices and covariates and when you can use standard regression methods; Monte Carlo tests for structural biases; Quadratic Assignment Procedure (QAP), network correlation, autocorrelation, and regression; baseline models and conditional uniform graph tests; and exploratory multivariate analysis of multi-network data sets. We will also cover interpreting R code in existing functions and writing your own functions. We discuss briefly how these methods relate to Exponential Random Graph models (ERGM), but the focus of this workshop is on non-ERGM statistical methods.

 

Prerequisites: Some prior exposure to R, but extensive experience is not assumed. Completion of the “Introduction to Network Analysis with R” workshop session is suggested for those new to R. Familiarity with the basic concepts of descriptive network analysis (e.g., centrality scores, network visualization) is strongly recommended. Participants are recommended to bring a laptop with R, RStudio, and statnet installed. Sample data and code will be provided.

Workshop 18: Tidy Networks: the tidyverse and tidygraph for social network analysis in R

 

Matthew Smith, Edinburgh Napier University (M.Smith3@napier.ac.uk)
Yasaman Sarabi, Edinburgh Business School, Heriot-Watt University

 

This 3-hour workshop provides an introduction to the R programming language for those without any previous or limited experience. It will introduce the tidyverse – a set of functions and packages for data processing, cleaning, and visualisation in R. In particular, we will focus on dplyr for data processing, ggplot2 for visualisation, and Rmarkdown for creating reports. We will go on to demonstrate how the tidyverse can be applied to social network analysis - more specifically through the use of the tidygraph package. The tidygraph permits you to utilise the underlying grammar structure of the tidyverse when dealing with graph objects in R. By using the tidygraph package you can manage edgelists and network attributes in a single object, along with implementing analysis on these objects. The tidyverse allows you to create tidy data frames, whilst the tidygraph allows you to create tidy graph objects – or tidy networks!

 

By the end of the session participants should be able to:

 

• Use R and RStudio.
• Make use of the tidyverse for data processing – more specifically preparing datasets for SNA.
• Visualising networks in R using ggplot2 (part of the tidyverse) and tidygraph.
• Create tidygraph objects and undertake some initial network analysis using the tidygraph package.

 

Target group: Individuals new to R, or those with limited R experience. These users will benefit from gaining an insight into how to use R for data processing and social network analysis following the tidy philosophy.

 

Requirements: No prior knowledge of R is required as an introduction will be provided.

 

Matthew Smith is a lecturer at Edinburgh Napier University. Yasaman Sarabi is an assistant professor at Edinburgh Business School, Heriot-Watt University. Both have experience delivering similar workshops at Sunbelt and EUSN conferences, including EUSN 2019 where this workshop was offered.

Workshop 19: Introduction to visone

 

Julian Müller, ETH Zürich / Università della Svizzera italiana (julian.mueller@gess.ethz.ch)

 

This workshop offers a hands-on introduction to visone (ital. mink), a free software tool that combines comprehensive means for analysis with unique visualization capabilities. The software features many standard and non-standard methods for analysis and visualization of networks, and offers a powerful graphical user interface.

 

After a brief overview of visone’s design and features, we will explore some of visone’s core functionality. Using example network analyses, we will produce presentations of findings step-by-step, starting from input data and arriving at publication-quality information visualizations.

 

Visone is written in Java and freely available at http://www.visone.info. It is advisable to bring a laptop running Windows, MacOS, or Linux, preferably with Java 8 or newer already installed.

© 2021 All rights reserved