TY - JOUR
T1 - Computational Modeling of Hierarchically Polarized Groups by Structured Matrix Factorization
AU - Sun, Dachun
AU - Yang, Chaoqi
AU - Li, Jinyang
AU - Wang, Ruijie
AU - Yao, Shuochao
AU - Shao, Huajie
AU - Liu, Dongxin
AU - Liu, Shengzhong
AU - Wang, Tianshi
AU - Abdelzaher, Tarek F.
N1 - Publisher Copyright:
Copyright © 2021 Sun, Yang, Li, Wang, Yao, Shao, Liu, Liu, Wang and Abdelzaher.
PY - 2021/12/22
Y1 - 2021/12/22
N2 - 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.
AB - 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.
KW - belief estimation
KW - hierarchical
KW - matrix factorization
KW - polarization
KW - unsupervised
UR - http://www.scopus.com/inward/record.url?scp=85122389764&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122389764&partnerID=8YFLogxK
U2 - 10.3389/fdata.2021.729881
DO - 10.3389/fdata.2021.729881
M3 - Article
C2 - 35005618
AN - SCOPUS:85122389764
SN - 2624-909X
VL - 4
JO - Frontiers in Big Data
JF - Frontiers in Big Data
M1 - 729881
ER -