Sunbelt XXXI International Network for Social Network ... - INSNA

Extraction And Validation Of Socio‐technical Network Data About The Sudan From Text CorporaDiesner, Jana; Carley, Kathleen M.Words and Networks ‐ Natural Language Processing, ConflictMethods, Text AnalysisWED.PM2In 2005, the Government of Sudan and the Sudan People's Liberation Movement (SPLM) signed a Comprehensive Peace Agreement. In 2011, Southern Sudanwill hold a referendum regarding its independence from Northern Sudan. Network data representing interactions in this socio‐technical system during this sixyear time period can help us to understand the development of culture and conflicts in this region. Since such data is hard to collect through classic methodssuch as surveys, we use Relation Extraction methods to approximate network data from publically available news coverage on Sudan. We will report on howwe utilize theoretically grounded, lexicalized features and feedback loops with subject matter experts to adjust our relation extraction technology to thisdomain. This technology uses a model that we trained via supervised machine learning, the classifier used for that are Conditional Random Fields. We willpresent our results from analyzing the retrieved socio‐technical network that comprises tribes, issues and resources.Eyetracking Of Network VisualizationsZenk, Lukas; Smuc, Michael; Windhager, FlorianVisualizationVisualization, Organizational Change, Intra‐organizational Networks, Visual Analytics, Network Visualization, EyetrackingWED.PM2A picture is worth a thousand words and visualizations are of utmost importance in social network analysis to better understand complex patterns ofrelationships. Visualizations are often used to gain an overview of collected data or to present results of empirical studies. In the context of organizationalnetwork studies, the visual exploration of data provides also insights for involved persons to reflect their communication behaviour. But how do people look atnetwork graphs? What are their eyes doing when they explore such visualizations and how do they achieve insights by visually working through the relationalwebs? In the course of the research project ViENA (Visual Enterprise Network Analysis), we studied various longitudinal networks in a university department.Accordingly, we visualized selected networks and how they changed over time. In front of an eyetracker, we presented the visualizations to involved persons ofthe department and analyzed how they observed their networks. In this presentation we will show the first results of this experiment.