Abstract
Disagreements, oppositions and negative opinions are indispensable parts of online political debates. In social media, people express their beliefs and attitudes not only on issues but also about each other through both their conversations and platform-specific interactions such as like, share in Facebook and retweet in Twitter. While there are explicit "like" features in these platforms, there is no explicit "dislike" feature. Many network analysis tasks, such as detecting communities and monitoring their dynamics (i.e. polarization patterns) require information about both positive and negative linkages. Hence, predicting negative links between users is an important task and a challenging problem. In this study, we propose an unsupervised framework to predict the negative links between users by utilizing explicit positive interactions and sentiment cues in conversations. We show the effectiveness of the proposed framework on a political Twitter dataset annotated through Amazon MTurk crowdsourcing platform. Our experimental results show that the proposed framework outperforms other well-known methods and proposed baselines. To illustrate the contribution of the predicted negative links, we compare the community detection accuracies using signed and unsigned user networks. Experimental results using predicted negative links show superiority on three political datasets where the camps are known a priori. We also present qualitative evaluations related to the polarization patterns (i.e. rivalries and coalitions) between the detected communities which is only possible in the presence of negative links.
| Original language | English (US) |
|---|---|
| Title of host publication | HT 2017 - Proceedings of the 28th ACM Conference on Hypertext and Social Media |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 125-134 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781450347082 |
| DOIs | |
| State | Published - Jul 4 2017 |
| Event | 28th ACM Conference on Hypertext and Social Media, HT 2017 - Prague, Czech Republic Duration: Jul 4 2017 → Jul 7 2017 |
Other
| Other | 28th ACM Conference on Hypertext and Social Media, HT 2017 |
|---|---|
| Country | Czech Republic |
| City | Prague |
| Period | 7/4/17 → 7/7/17 |
Fingerprint
Keywords
- Negative Link Prediction
- Online Political Networks
- Sentiment Analysis
- Social Media Mining
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Artificial Intelligence
- Human-Computer Interaction
- Software
Cite this
Negative link prediction and its applications in online political networks. / Ozer, Mert; Yildirim, Mehmet Yigit; Davulcu, Hasan.
HT 2017 - Proceedings of the 28th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2017. p. 125-134.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Negative link prediction and its applications in online political networks
AU - Ozer, Mert
AU - Yildirim, Mehmet Yigit
AU - Davulcu, Hasan
PY - 2017/7/4
Y1 - 2017/7/4
N2 - Disagreements, oppositions and negative opinions are indispensable parts of online political debates. In social media, people express their beliefs and attitudes not only on issues but also about each other through both their conversations and platform-specific interactions such as like, share in Facebook and retweet in Twitter. While there are explicit "like" features in these platforms, there is no explicit "dislike" feature. Many network analysis tasks, such as detecting communities and monitoring their dynamics (i.e. polarization patterns) require information about both positive and negative linkages. Hence, predicting negative links between users is an important task and a challenging problem. In this study, we propose an unsupervised framework to predict the negative links between users by utilizing explicit positive interactions and sentiment cues in conversations. We show the effectiveness of the proposed framework on a political Twitter dataset annotated through Amazon MTurk crowdsourcing platform. Our experimental results show that the proposed framework outperforms other well-known methods and proposed baselines. To illustrate the contribution of the predicted negative links, we compare the community detection accuracies using signed and unsigned user networks. Experimental results using predicted negative links show superiority on three political datasets where the camps are known a priori. We also present qualitative evaluations related to the polarization patterns (i.e. rivalries and coalitions) between the detected communities which is only possible in the presence of negative links.
AB - Disagreements, oppositions and negative opinions are indispensable parts of online political debates. In social media, people express their beliefs and attitudes not only on issues but also about each other through both their conversations and platform-specific interactions such as like, share in Facebook and retweet in Twitter. While there are explicit "like" features in these platforms, there is no explicit "dislike" feature. Many network analysis tasks, such as detecting communities and monitoring their dynamics (i.e. polarization patterns) require information about both positive and negative linkages. Hence, predicting negative links between users is an important task and a challenging problem. In this study, we propose an unsupervised framework to predict the negative links between users by utilizing explicit positive interactions and sentiment cues in conversations. We show the effectiveness of the proposed framework on a political Twitter dataset annotated through Amazon MTurk crowdsourcing platform. Our experimental results show that the proposed framework outperforms other well-known methods and proposed baselines. To illustrate the contribution of the predicted negative links, we compare the community detection accuracies using signed and unsigned user networks. Experimental results using predicted negative links show superiority on three political datasets where the camps are known a priori. We also present qualitative evaluations related to the polarization patterns (i.e. rivalries and coalitions) between the detected communities which is only possible in the presence of negative links.
KW - Negative Link Prediction
KW - Online Political Networks
KW - Sentiment Analysis
KW - Social Media Mining
UR - http://www.scopus.com/inward/record.url?scp=85026351593&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85026351593&partnerID=8YFLogxK
U2 - 10.1145/3078714.3078727
DO - 10.1145/3078714.3078727
M3 - Conference contribution
AN - SCOPUS:85026351593
SP - 125
EP - 134
BT - HT 2017 - Proceedings of the 28th ACM Conference on Hypertext and Social Media
PB - Association for Computing Machinery, Inc
ER -