07/06/2021

SIGNLENS: A Tool for Analyzing People's Polarization Social Relationship Based on Signed Graph Modeling

Junjie Huang, Huawei Shen, Xueqi Cheng

Keywords: Studies of digital humanities (culture, history, arts) using social media, Human computer interaction, social media tools, navigation and visualization, Subjectivity in textual data, sentiment analysis, polarity/opinion identification and extraction, lingu

Abstract: SIGNLENS is a tool that helps to analyze polarized social relationships based on signed graph modeling. It could be used by political analysts, historical researchers, and social media community organizations to analyze the social network with negative links (i.e., conflicts or disagreement). SIGNLENS can handle signed temporal graph by doing individual analysis and group analysis. Individual analysis gives a Web dashboard to users to explore the nodes who users focus on. Group analysis provides another perspective of analyzing the whole graph, which mainly analyzes the changes in the unbalance of the signed graph over time. We give two examples to demonstrate how our tool works, which consist of The China Biographical Database and the United States Congress Vote. More details about these two examples can be found in https://github.com/huangjunjie-cs/SIGNLENS.

 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at ICWSM 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd

Similar Papers