TY - JOUR
T1 - Implicit negative link detection on online political networks via matrix tri-factorizations
AU - Ozer, Mert
AU - Yildirim, Mehmet Yigit
AU - Davulcu, Hasan
N1 - Funding Information:
This work is supported by the Office of Naval Research Global under Grant N00014-16-1-2015; and Office of Naval Research under Grant N00014-15-1-2722.
Publisher Copyright:
© 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2018/4/3
Y1 - 2018/4/3
N2 - Political conversations have become a ubiquitous part of social media. When users interact and engage in discussions, there are usually two mediums available to them; textual conversations and platform-specific interactions such as like, share (Facebook) or retweet (Twitter). Major social media platforms do not facilitate users with negative interaction options. However, many political network analysis tasks rely on not only positive but also negative linkages. Thus, detecting implicit negative links is an important and a challenging task. In this work, we propose an unsupervised framework utilising positive interactions, sentiment cues, and socially balanced triads for detecting implicit negative links. We also present an online variant of it for streaming data tasks. We show the effectiveness of both frameworks with experiments on two annotated datasets of politician Twitter accounts. Our experiments show that the proposed frameworks outperform other well-known and proposed baselines. To illustrate the detected implicit negative links' contribution, we compare the community detection accuracies using unsigned and signed networks. Experimental results using detected negative links show superiority on the three datasets where the camps are known a priori. We also present qualitative evaluations of polarisation patterns between communities which are only possible in the presence of negative links.
AB - Political conversations have become a ubiquitous part of social media. When users interact and engage in discussions, there are usually two mediums available to them; textual conversations and platform-specific interactions such as like, share (Facebook) or retweet (Twitter). Major social media platforms do not facilitate users with negative interaction options. However, many political network analysis tasks rely on not only positive but also negative linkages. Thus, detecting implicit negative links is an important and a challenging task. In this work, we propose an unsupervised framework utilising positive interactions, sentiment cues, and socially balanced triads for detecting implicit negative links. We also present an online variant of it for streaming data tasks. We show the effectiveness of both frameworks with experiments on two annotated datasets of politician Twitter accounts. Our experiments show that the proposed frameworks outperform other well-known and proposed baselines. To illustrate the detected implicit negative links' contribution, we compare the community detection accuracies using unsigned and signed networks. Experimental results using detected negative links show superiority on the three datasets where the camps are known a priori. We also present qualitative evaluations of polarisation patterns between communities which are only possible in the presence of negative links.
KW - Negative link
KW - dynamic graph algorithms
KW - non-negative matrix tri-factorization
KW - online political networks
KW - online social networks
UR - http://www.scopus.com/inward/record.url?scp=85049020285&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85049020285&partnerID=8YFLogxK
U2 - 10.1080/13614568.2018.1482964
DO - 10.1080/13614568.2018.1482964
M3 - Article
AN - SCOPUS:85049020285
SN - 1361-4568
VL - 24
SP - 63
EP - 87
JO - New Review of Hypermedia and Multimedia
JF - New Review of Hypermedia and Multimedia
IS - 2
ER -