Sunbelt 2017

Workshop Proposals

 

#1. Workshop Title: Introduction to Social Network Analysis Using Stata

Instructor: Dr. Thomas Grund

Contact information:

Dr. Thomas Grund / University College Dublin / thomas.grund@ucd.ie

Description: Stata is a widely used statistical software. This workshop introduces the new commands—a software suite of over 100 Stata commands—for social network analyses. The software includes programs for importing and exporting, loading and saving, handling, manipulating and replacing, generating, and visualizing and animating networks. It also includes commands for measuring the importance of network nodes, the detection of network patterns and features, the similarity of multiple networks, node attributes, and the advanced statistical analysis of networks including. This workshop gives several examples using these programs, provides instructions for the installation, use, and support of the software (http://www.nwcommands.org). A book published by StataPress (written by the course provider) is forthcoming and will be the basis of this workshop.

Pre-requisites: None.

Length: 6 hours.

Participant limit: 30 people

Link: www.nwcommands.org


#2. Workshop Title: Introduction to Social Network Analysis and UCINET: Application and Theory

Instructor: Dr. Sakin Erin

Contact information:

Sakin ERIN / Sociology Department, University of California-Riverside / sakinerin@ucr.edu

Description: This is a 6-hour introduction to social network analysis which will focus on both theory and the application of social network analysis. The theory aspect covers the dynamics of an interaction between individuals and social structures. Examining this dynamic from a sociological perspective, it shows how social actors affect social structures while at the same they are influenced by them. It particularly analyzes an individual’s position in social structure and the consequences of occupying certain positions in the structure such as behavior restrictions or opportunities for resources.

The application part covers basic methods of collecting social network data, managing data, and running some of the most essential network procedures using UCINET. These procedures include but not limited to basic measures of centrality concepts, structural equivalence, structural holes, change in egocentric networks and network visualization.

This workshop does not require any prior knowledge of social network analysis or UCINET software. It is also open to participants from any social science discipline.

Prerequisites: None.

Length: 6 hours

Participant limit: 25


#3. Workshop Title: Social Network Approaches for Behavior Change (Cancelled)

Instructor: Dr. Thomas W. Valente

Contact information:

Thomas W. Valente, PhD / University of Southern California / tvalente@usc.edu

Description: This workshop introduces the many ways that social networks influence individual and network-level behaviors.  It also provides a brief introduction to analytic approaches for understanding network influences on behaviors; and reviews existing evidence for the utility of using social network data for behavior change in a variety of settings including health behaviors and organizational performance.  The workshop presents a typology of network interventions and reviews existing evidence on the effectiveness of network interventions.  (Students familiar with the R environment may follow an R script written to demonstrate the 24 or so tactical interventions presented.)  The workshop will be conducted by Tom Valente who has been developing and implementing network based interventions for over 15 years.

Prerequisites: None.

Length: 3 hours

Participant limit: No limit


#4. Workshop Title: Understanding Diffusion with netdiffuseR  (Cancelled)

Instructor: Dr. Thomas W. Valente

Contact information:

Thomas W. Valente, PhD | George Vega Yoon, MS / University of Southern California / tvalente@usc.edu

Description: The netdiffuseR package provides a set of tools for analyzing and simulating diffusion of innovations on networks. In this workshop we demonstrate the features of the package through the analysis of both empirical and simulated data on the diffusion of innovations. The session will include examples on how to use netdiffuseR jointly with other network analysis packages such as RSiena, statnet, and igraph.  netdiffuseR’s main features are computing network exposure models based on various weight matrices (direct ties, structural equivalence, attribute-weighted, etc.), thresholds, infectiousness and susceptibility, among others.  The package works with both static and dynamic networks. Some other capabilities include handling relative large graphs, simulating networks and diffusion of innovation processes, and visualizing the diffusion of innovations.

Prerequisites: While there are no pre-requisites, it is suggested to have a working knowledge of the R programming language.

Length: 3 hours

Participant limit: No limit


#5. Workshop Title: Analysis of temporal networks

Instructor: Dr. Vladimir Batagelj

Contact information:

Dr. Vladimir Batagelj / IMFM, Ljubljana and IAM UP, Koper, Slovenia / vladimir.batagelj@fmf.uni-lj.si

Description: To describe temporal networks we introduce the notion of temporal quantities. We define the addition and multiplication of temporal quantities in a way that can be used for the definition of addition and multiplication in temporal networks with zero latency. For details see the paper:

Batagelj, V., Praprotnik, S.: An algebraic approach to temporal network analysis based on temporal quantities. Social Network Analysis and Mining, 6(2016)1, 1-22.

To describe their temporal behavior we assign temporal quantities to nodes and links of a network. The proposed approach enables us to treat as temporal quantities also other network characteristics such as degrees, connectivity components, centrality measures, Pathfinder skeleton, cores, etc. It is an alternative to the usual approach to temporal network analysis based on time slices. We developed fast algorithms for the proposed operations. They are available as an open source Python library TQ:

http://vladowiki.fmf.uni-lj.si/doku.php?id=tq

and

https://github.com/bavla/TQ .

This workshop session will provide an introduction to the analysis of temporal networks based on temporal quantities. We will begin by learning how to describe temporal networks in the netJSON format. We will then review on examples the procedures provided by the library TQ. Finally we will present some results from the analysis of Franzosi’s violence network, Corman’s Reuters terror news network, (temporal) genealogies, collections of bibliographic networks, and others. A special attention will be given to the use of visualization for inspection of data and presentation of results.

Prerequisites: None.

Duration: half day (3 hours)

Maximum number of attendees: 30


#6. Workshop Title: Algebraic analysis and visualization of multiple, signed, and two-mode networks with ‘multiplex’ & ‘multigraph’

Instructor: Dr. Antonio Rivero Ostoic

Contact information:

Dr. Antonio Rivero Ostoic / AARHUS UNIVERSITY – School of Business and Social Sciences

M: multiplex@post.com; jaro@econ.au.dk

W: github.com/mplex

Description: This intensive workshop is about the analysis of complex networks by means of algebraic procedures and visualization with the computer programs “multiplex” & “multigraph”. These two R packages are especially designed for the analysis of multiple networks including signed and two-mode network structures, and the participants will have exclusive access to novel functions and features in the developing versions.

After this session, the participants will be able to create and manipulate multivariate network data, reduce multiple network structures with algebraic procedures, construct algebraic systems to represent relational and role structures, and analyze social influence processes in multiplex networks with actor attributes. Other topics include performing algebraic analyses of signed networks within the structural balance theory, and the application algebraic approaches for the study of affiliation or two-mode networks.

As complement to the different algebraic analyses, there is also an introduction to the visualization and manipulation of multigraphs (binary and weighted), bipartite graphs, and lattice structures within the R environment. The methodology of the workshop is learning by doing, and the different analyses are made by using real-life data sets.

Prerequisites: It is recommended that the participants have a basic knowledge of the R script language (https://www.R-project.org/), but a quick explanation of the essentials of R is given at the beginning of the workshop.

Length of the workshop: One session of 3 hrs.

Attendance Limit: 30 participants

Links:

https://CRAN.R-project.org/package=multiplex

https://CRAN.R-project.org/package=multigraph


#7. Workshop Title: Using Polinode: A Browser-Based Application for Collecting, Analyzing and Visualizing Network Data

Instructor: Andrew Pitts

Contact information: Andrew Pitts / Founder & CEO, Polinode / andrew.pitts@polinode.com | www.polinode.com

Description: Polinode is a web-application that allows users to upload arbitrary network data (called Polinode Networks) and to also collect network data via integrated relationship-based surveys (called Polinode Surveys). It’s designed to be relatively easy to use but also contains a number of advanced features such as advanced metrics and snowball relationship-based survey functionality.

In this 3 hour workshop the following will be covered:

  1. An introduction to Polinode
  2. Polinode Networks – attendees will learn how to:
    1. Upload a network
    2. Calculate a number of key metrics such as Eigenvector Centrality, Betweenness Centrality and Louvain Community Detection
    3. Capture and save multiple views per network
    4. Export data into a number of different formats
    5. Share views and networks with other users
  3. Polinode Surveys – attendees will learn how to:
    1. Create a relationship-based survey including using a Search and Select question type that scales to many thousands of respondents / nodes
    2. Use question piping to pipe selections to subsequent questions
    3. Measure relationship strength using slider question types
    4. An introduction to snowball survey methods using Polinode
    5. Produce interactive networks from relationship-based with a single click

Users will be provided (at no additional cost) with a Polinode account that will include (for the workshop and the following 3 months) the ability to run relationship-based surveys with up to 50 respondents for free and the ability to have 1 private network on the platform.

There is no need to bring data to upload as a sample file will be provided. Attendees should bring their own laptop computer with internet access. Chrome is the recommended browser. Since Polinode is web-based, no software installation is required. Further information can be found at www.polinode.com.

Prerequisites: None

Length: 3 hours

Attendance Limit: 25


#8. Workshop Title: Social Network Analysis using NetMiner

Instructors:

1)     Ghi-Hoon Ghim (ghghim@cyram.com, Cyram, Inc., South Korea)

2)     Dukjin Chang (dukjin@snu.ac.kr, Seoul National University, South Korea)

Contact information:

Woosik Choi, Senior R&D Division,

Cyram Inc. 11th, Taeseok Bldg., 5, Mabang-ro 10-gil Seocho-gu, Seoul, South Korea (06775)
E-mail: ws0213@cyram.com; Phone: +82-10-5024-9084

Description: The purpose of this session is to introduce variety of up-to-dated social network analytic features that are included in NetMiner, a general purpose SNA software specially designed for data analytic users and then to enable participants to have the chance of hands-on operation in it. Useful analytic methods in relation to SNA such as statistics, data mining, big data analysis and other analytic endeavors are also to be introduced.

In this workshop, we’ll deliver for beginners starting from a basic tutorial the most common measures of network analysis and furthermore advanced features and analytic methodology as for 2-mode network, keyword network and sentiments in a social network service (SNS) platform. High-level functions of SNA are also covered for experts to understand script environment and machine learning that are secondary step to utilize SNA outcome for further purpose. Topics to be covered are as follows.

– Social Network Analysis

– 1-mode networks and 2-mode networks

– Common measures of network analysis

– Advanced measures of network analysis: Centrality (PageRank, Katz, etc.), Cohesion (Community detection algorithms), Equivalence and Similarity

– Statistics for SNA

– Mining and machine learning

– Visualization using analyzed results

– Interpretation of analyzing results

– Script function based on Python language

Prerequisites: To make the workshop run smoothly, each participants are requested to bring a window laptop computer that is installed with a free trial version of NetMiner. It can be downloaded at http://www.netminer.com.

Workshop Length: 2 sessions (6 hours)

Participants limit: No limit.

Url to supporting information:

1) www.netminer.com (software homepage)

2) http://www.cyram.com (company (Cyram Inc.) homepage)


#9. Workshop Title: The Analysis of Longitudinal Social Network Data using RSIENA

Instructors: Per Block, Zsofia Boda, Timon Elmer, Andras Vörös (all ETH Zürich); James Hollway (Graduate Institute Geneva)

Contact information:

Per Block, ETH Zurich, Clausiusstr. 50, 8005 Zürich, Switzerland. / email: per.block@gess.ethz.ch; / Tel: +41446338921

Description: 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 30 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, structurally determined values, 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 length: 2 sessions (6 hours)

 Max Participants: 35


#10. Workshop Title: Advanced RSIENA and advanced actor-oriented network modelling workshop

Instructors: Per Block, Zsofia Boda, Timon Elmer, Andras Vörös (all ETH Zürich); James Hollway (Graduate Institute Geneva)

Contact information:

Per Block, ETH Zurich, Clausiusstr. 50, 8005 Zürich, Switzerland. / email: per.block@gess.ethz.ch; / Tel: +41446338921

Description: This workshop is intended for experienced users of RSiena, the package in the statistical software system R for analyzing longitudinal data of networks, and those interested in actor-oriented modelling of network dynamics.

A number of features of RSiena, and some possibilities that may be considered advanced options, will be discussed and demonstrated. Further, this workshop will situate actor-oriented models in the broader context of dynamic statistical networks models. Finally, options to analyse relational events in an actor-oriented framework are discussed.

Some of the following topics will receive attention:

–      Behavioural evolution for two-mode networks in which nodes in both modes have a behavioural variable and, thus, agency.

–      Advanced goodness of fit checking with sienaGOF().

–      Model Specification and new effects.

–      Multilevel analysis of network dynamics with sienaBayes().

–      Comparison of SAOMs with ERGMs, LERGMs, and TERGMs.

–      Analysing directed and undirected relational events in an actor-oriented framework.

–      Other recent developments

Participants are invited to email the organizer (per.block “at” gess.ethz.ch) 2-3 weeks before the start of the workshop to indicate preferences for other advanced topics that might be of interest.

Participants could consider bringing their own laptop with R and RSiena installed, such that some steps of the data analysis can be followed hands-on. Further instructions will be given before the conference starts.

Prerequisites: Experience with using RSiena and solid understanding of SAOMs.

Workshop length: 3 hours

Max Participants: 35


#11. Workshop Title: Research questions, competing explanations, and network configurations: A practical guide to theorizing about network processes

Instructor: Dr. András Vörös

Contact information:

András Vörös / Postdoctoral Research Fellow / ETH Zürich, Chair of Social Networks MTA TK “Lendület” Research Center for Educational and Network Studies (RECENS) / andras.voros@gess.ethz.ch

Description: Most workshops at network conferences focus on the application of basic or advanced statistical methods in the field. While this is undoubtedly useful, in the meantime relatively little attention is given to helping network scholars develop a solid conceptual background. Describing observed social patterns in network terms and hypothesizing about the (multiple, often competing) relational mechanisms behind these patterns are crucial skills for a social network researcher.

This course presents a systematic conceptual framework, one based on network configurations, for formulating network-related research questions, hypotheses, and alternative explanations. The approach has at least three major benefits for network scholars: it provides a systematic conceptual basis for developing substantive ideas, it facilitates the mature use of advanced network methods, and it aids the clear interpretation and communication of empirical findings. Despite these advantages of a systematic framework, often it seems that too many students and practicing researchers in the field of social networks rely on ad hoc conceptual approaches when formulating hypotheses.

  1. How can we formulate research questions in a clear and systematic way using the concept of network configurations?
  2. How can we formulate relevant hypotheses about the relational processes behind observed network patterns?
  3. How can we find the most important competing explanations of our hypothesis?

Based on experience in teaching advanced statistical network methods to various audiences over the past few years, it appears that many smart students of social network analysis, beginners and advanced users alike, lack a systematic conceptual framework that helps answering these questions in a rigorous way. In fact, when prompted to think about potential explanations of a network phenomenon people often revert to individual-level processes, forgetting about dyadic, triadic, or higher-order network mechanisms.

This workshop helps participants to develop and practice the use of an efficient conceptual framework for theorizing about network processes. The presented approach focuses on the fact that social networks are complex multi-level structures. This means that when developing our hypotheses and looking for competing explanations of a phenomenon, we need to be able to think systematically on the level of actors, network ties, dyads, triads, higher-order structures and whole communities.

The workshop consists of two parts:

  1. Conceptual introduction: Aregular lecture introducing basic and more advanced concepts of network research. The discussion starts from basic conceptual definitions related to ties and actors, and leads up to issues related to multiple embedded network configurations. We demonstrate a useful strategy for theoretical work based on the example of transitive closure. (Note: this is not a usual “introduction to networks” lecture.)
  1. Interactive group practice: After the lecture, participants are assigned to small groups (4-5 people per group). Each group receives an exercise describing a different imaginary social context and an observed social phenomenon (e.g. in a school, friends have similar smoking behavior). The groups discuss their example and develop a main hypothesis and a few competing explanations for the observed phenomenon. After the group-level discussions, groups present their solution to the all attendees.

The course does not require deep background knowledge in any specific area of social network analysis, only an interest in social network research questions and explanations. However, the lectures and exercises are structured in a way that even more advanced network scholars may find the workshop useful. The material and issues discussed help researchers in different stages of their career to theorize about and communicate their social network research in a clear and systematic fashion. In addition, the course prepares participants for a deeper understanding and a more conscious application of the cutting-edge statistical network methods in the field (such as Exponential Random Graph Models, Stochastic Actor-oriented Models/SIENA, Relational Event Models, and so on).

Prerequisites: Only a basic knowledge of social network concepts is required.

Length: 1 session (3 hours)

Attendance limit: 25


#12. Workshop Title: VIZUALISATION OF SOCIAL NETWORKS WITH NODEXL

Instructor: Verena Texier-Ast

Contact information:

Verena Texier-Ast / Universität Münster Geographisches Institut Heisenbergstraße 2 48149 Münster GSM: + 49 176 702 802 04 / Email: texierast@uni-muenster.de

https://www.uni-muenster.de/Geographie/mitarbeiter/texierast.html

Description: Over the past two decades, the term “social networks” has become a central way for describing the social contacts that a person or organisation, company, institution and so on (ego) has with another (alteri). Making their underlying social relations visible contributes to a better and deeper understanding of their network structure. It becomes tangible.

Besides commercial or partially commercial programs such as e.g. UCINET, NodeXL, a free Excel-Plug-In-Software can be seen as a useful alternative in this respect. It is easy to adopt for existing users of Excel, as it has just one further tab in the header within Excel and lends itself easily to “learning by doing”.

Aim of this three-hour workshop is to introduce the participants of the workshop to the mentioned freeware NodeXL. Particular attention will be paid to the individual application of the software in one owns research.

Course of the workshop:

  • Introduction to the software NodeXL
  • Discussion of the data to be visualized
  • Supporting individual visualization of social networks with NodeXL
  • Presentation of the social networks visualized by the participants
  • Final evaluation of the software NodeXL (advantages/ disadvantages)

 

Requirements for participants:

  • Participants must bring their own laptop with them to the course (Excel 2007 or higher must be installed)
  • Good knowledge in the work with Excel
  • Interest in the topic of vizualisation of social networks
  • Download and installation of the software NodeXL (https://nodexl.codeplex.com/)
  • Provision of a data set for vizualisation

Length: 1 session (3 hours)

Participant limit: 20


#13. Workshop Title: A Hands-on Introduction to Analyzing Social Networks with UCINET & Netdraw.

Instructors: James Coutinho (Manchester), Meredith Woehler (Kentucky) and Steve Borgatti (Kentucky)

Contact information:

Steve Borgatti / University of Kentucky / Email: sborgatti@uky.edu

Description: This interactive workshop gives all participants an opportunity for hands-on experience analyzing network data in the UCINET/Netdraw software package. We will provide a beginner’s tutorial on the concepts, methods, and data analysis techniques for a whole social network research project, from data entry through reporting results. Together, we will use sample datasets from public health and management settings to focus on the interpretation and calculation of some of the most common measures of network analysis. We will introduce ways to identify “important” nodes in a network based on different concepts of centrality and ego-network composition measures, as well as ways to identify sets of key players for particular applications (e.g., network-based interventions). We will also provide a hands-on tutorial for NetDraw, which creates network visualizations.

Requirements: In order to get the most practical benefit from the workshop, each participant should bring a Windows laptop computer (or Mac with a Windows emulator) in order to personally run the analyses as the instructors are demonstrating them.

We ask participants to download a free trial version of UCINET (which includes NetDraw as well as sample network data), available at http://www.analytictech.com/ucinet/, prior to the workshop, preferably in March since the free trial is good for 60 days.

Length: 2 sessions (6 hours)

Participant limit: None


#14. Workshop Title: Advanced Social Network Analysis Using UCINET and Netdraw.

Instructors: Steve Borgatti (Kentucky) Martin Everett (Manchester).

Contact information:

Steve Borgatti / University of Kentucky / Email: sborgatti@uky.edu

Description: This is a 1-day workshop for participants who already have some experience with UCINET and network analysis, but would like to learn more. We cover advanced aspects of centrality, finding subgroups, and measuring equivalence. We also cover advanced techniques for analyzing network change and handling multiple relations, missing data, non-symmetric data, valued data and 2-mode data. Throughout, we demonstrate powerful, sometimes undocumented, features of UCINET and NETDRAW, including newer routines that make it work much easier.

Note: what makes this workshop advanced is the selection of topics, not the speed or complexity of the exposition. In other words, wherever practical, all concepts are explained from first principles, making as few assumptions about prior knowledge as possible.

Prerequisites: We do assume basic familiarity with UCINET as a pre-requisite for the workshop.

Length: 2 sessions (6 hours)

Participant limit: None


#15. Workshop Title: Fundamentals of Biased Net Models

Instructor: John Skvoretz

Contact information: 

John Skvoretz, Distinguished University Professor of Sociology, AAAS Fellow

Carolina Distinguished Professor Emeritus

Department of Sociology

University of South Florida

4202 E Fowler Ave, CPR 107

Tampa, FL USA 33620-5550

Email: jskvoretz@usf.edu

Description: This workshop introduces the biased net modeling framework first proposed by Anatol Rapoport and colleagues in the 1950s.  The workshop covers historical developments of the approach and contemporary uses of the framework to model aggregate tie data often gathered through ego network designs or other means (such as, marriage registers that tabulate demographic attributes of spouses) and to model complete networks including networks through time.  All estimation code is written in R and so previous experience with the R environment would be extremely useful.

Prerequisites: Familiarity with the R environment.

Length: 3 hours

Participant limit: 25


#16. Workshop Title: Network Exploration, Visualization and Interpretation by Pajek, with Pajek and around Pajek (taught in Chinese)

Instructor: Dr. Feng Lin

Contact information:

Dr. Feng Lin

Associate Professor, Mentor for Master’s Degree, Rehabilitation School of Nanjing Medical University.

Associate Senior Physician, Rehabilitation Medicine Center, the First Affiliated Hospital of Nanjing Medical University.

Email: peterduuslin@gmail.com

Tel: +86-13851446615

Description:

This workshop will be presented mainly in Chinese Mandarin, Q&A will be given in English.

Pajek is a classical and user-friendly GUI application. It is not only suitable for beginners, who want to establish an operational knowledge system of network philosophy, but also available for advanced scholars and professionals, who demand facilitated network analysis tools. Two years ago, the publish of the 2nd Chinese edition of the textbook “Exploratory Social Network Analysis with Pajek” made it possible for Chinese learners to access this software. We received a lot of suggestions, ideas and questions about this book and Pajek. Many advanced learners also required to use Pajek in combination with other tools such as Matlab, R or Python. By the opportunity of Sunbelt2017 in Beijing, we want offer a Mandarin workshop including but not limited to following aspects:

  1. Operational philosophy about Pajek.
  2. Elementary practice strategies of Pajek.
  3. Data preparation to network modeling.
  4. File generation for Pajek formats.
  5. Net visualization by Pajek.
  6. Parameter calculation in Pajek.
  7. *Using Matlab, R and Python with Pajek.

This workshop will help participants to design researches based on network theory and technique, and will provide several examples including:

□ Historical network analysis through text mining in ancient classics.

□ Disease network modeling of International Classification of Function.

□ Social representation research based on word association tests.

□ Semantic network analysis using patient generated semantic feature dataset.

□ Functional brain graph modeling with magnetoencephalogram data.

□ Author networks and citation networks.

Pre-requisites:

Attendees should be proficient in Mandarin Chinese. English is welcome in Q&A subsection.

In the first section, we will introduce the up-mentioned 1-5 aspects, participants need no prior SNA experiences and coding skills. We will release necessary resources through mail list, including a network file generator (Chines edition) and several sample network files with their original dataset. Since this is an interdisciplinary and interactive workshop, we will arrange a 30-minute subsection for attendees to discuss their own research questions and provide some explorations with their own sample data sets.

The second section will include coding tools, especially the up-mentioned 6th aspect, in order to generate Pajek-requiring data, or to process Pajek-generated results. Participants should prepare Matlab, R or Python for training, but no prior coding skills are necessary in this section. We will offer all codes and sample materials through mail list.

Participants can download Pajek and open-access resources from http://mrvar.fdv.uni-lj.si/pajek/be2.htm.

Length: 6 hours

Participant limit: 30 people

Link: http://mrvar.fdv.uni-lj.si/pajek/be2.htm


#17. Dynamic Network Analysis (DNA) and *ORA

Instructor: Dr. Kathleen M. Carley and Dr. L. Richard Carley

Contact information:

Kathleen M. Carley (kathleen.carley@cs.cmu.edu)

L. Richard Carley (carley@ece.cmu.edu)

Carnegie Mellon University  – www.casos.cs.cmu.edu

Description:

A lecture and hands-on workshop in which attendees learn about Dynamic Network Analysis (DNA) and the DNA toolkit *ORA. Foundational concepts and techniques of Dynamic Network Analysis are presented including: assessing meta-network data, geo-spatial enabled network analysis, and change over time. Using *ORA the attendees will learn how to import, export, visualize, and assess data. Attention will be focused on spatio-temporal visualization, grouping technologies, key entity identification, dynamic networks, and network change. Participants will be presented with a thorough demonstration of software features used to create a sample network and analyze it using traditional and advanced DNA techniques. Participants will be provided with a CD for a windows PC or MAC with executable of the software (student version), a trial professional version), sample data, and a user’s guide. Basic social network and dynamic network representations, statistics, analysis and visualization techniques are covered, both in concept and practical operation. This workshop will be fast-paced and involves advanced material, however novices to network analysis should be able to follow along, as the material is presented in an affable, but comprehensive manner.

This full day session begins with an overview of ORA, and techniques for entering, visualizing, and analyzing social and meta-network data. Special features for handling node attributes are presented.  The early session provides an introduction to the basic network capabilities; whereas, the later session covers more advanced topics.  Key node identification, clustering, spatio-temporal analytics and visualization, twitter analytic, and semantic networks are covered.

*ORA is a powerful network analysis and visualization tool.  *ORA supports the assessment of standard social network data, organizational network data, high-dimensional network data, meta-network data, geo-spatial network data, and dynamic network data. Relatively unique features include trail and network visualization, fuzzy grouping algorithms, multi-mode network assessment, built in network simulators, JSON and CSV importers, specialized twitter analytics, two mode metrics, and powerful visualizer with data entry and mark-up capabilities. The professional version is capable of handling large 106 networks, and can run under the PC, Mac or linux operating system.  ORA visualizations support many languages including English and Chinese.

Topics Include:

  • Social Network Analysis
  • Comparing and contrasting networks
  • Multi-mode, multi-link, high dimensional network metrics
  • Networks with positive and negative ties
  • Weighted networks
  • Semantic networks
  • Placing networks on maps, geo-network analytics
  • Analyzing Twitter data
  • *ORA software
    • Data management, Visualization, General, temporal and geo-spatial, metrics, Grouping algorithms, Reporting

Pre-requisites:

Those who are interested in assessing social media data, networks derived from texts, groups, organizations or communities using sets of interconnected multi-mode or multi-link networks and/or sets of networks across time and/or space and who want to learn how to use existing software tools and techniques to analyze such meta-network data, should attend this full-day workshop. The material and its delivery is suitable for researchers and practitioners, alike. This is designed to be a non-technical workshop, however, by its very nature, the material will involve some mathematics, although this will be minimized as the delivery is driven towards forming an understanding of the concepts, not mastery of the details.

Length: 6 hours

Participant limit: None

Computer Equipment:

The software presented in this tutorial is Windows or Mac operating system based. Participants should bring their own laptops to workshop. The software will be screen-projected to the group as a live walk-through demonstration. Participants will be provided with a data CD containing the complete set of software and will be guided through its installation and subsequent hands-on usage.


#18. Guanxi Networks

Instructor: Dr. Yanjie Bian

Contact information:

  • Institute for Empirical Social Science Research, Xi’an Jiaotong University, China, email: yjbian@mail.xjtu.edu.cn.
  • Department of Sociology, University of Minnesota, USA, email: bianx001@umn.edu.

Description:

This workshop is designed to discuss the most typical characterizations of guanxi, the Chinese expression of social connections, and the theoretical and methodological issues emerging from the most recent studies of the topic in China and elsewhere. This workshop will be instrumental to students and young researchers who have an interest in using the network modules of several open data archives (CGSS2003, CGSS2008, CGSS2012, EASS2008, EASS2012) for conducting a social network analysis of China and East Asia. Access to these and other open data archives is described in the workshop. A 2017 International Social Survey Programme module of “social capital and social resources” will also be introduced.

Pre-requisites: None

Participant limit: 50

Length:  3 hours