Computational Modeling of Hierarchically Polarized Groups by Structured Matrix Factorization
-
Published:2021-12-22
Issue:
Volume:4
Page:
-
ISSN:2624-909X
-
Container-title:Frontiers in Big Data
-
language:
-
Short-container-title:Front. Big Data
Author:
Sun Dachun,Yang Chaoqi,Li Jinyang,Wang Ruijie,Yao Shuochao,Shao Huajie,Liu Dongxin,Liu Shengzhong,Wang Tianshi,Abdelzaher Tarek F.
Abstract
The paper extends earlier work on modeling hierarchically polarized groups on social media. An algorithm is described that 1) detects points of agreement and disagreement between groups, and 2) divides them hierarchically to represent nested patterns of agreement and disagreement given a structural guide. For example, two opposing parties might disagree on core issues. Moreover, within a party, despite agreement on fundamentals, disagreement might occur on further details. We call such scenarios hierarchically polarized groups. An (enhanced) unsupervised Non-negative Matrix Factorization (NMF) algorithm is described for computational modeling of hierarchically polarized groups. It is enhanced with a language model, and with a proof of orthogonality of factorized components. We evaluate it on both synthetic and real-world datasets, demonstrating ability to hierarchically decompose overlapping beliefs. In the case where polarization is flat, we compare it to prior art and show that it outperforms state of the art approaches for polarization detection and stance separation. An ablation study further illustrates the value of individual components, including new enhancements.
Funder
Defense Advanced Research Projects Agency
Army Research Laboratory
United States Department of Defense
Publisher
Frontiers Media SA
Subject
Artificial Intelligence,Information Systems,Computer Science (miscellaneous)
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Influence Pathway Discovery on Social Media;2023 IEEE 9th International Conference on Collaboration and Internet Computing (CIC);2023-11-01