Implicit Negative Link Prediction With a Network Topology Perspective
- 18 October 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (6) , 3132-3142
Abstract
Sign prediction in signed social networks is a new research direction in the field of social relation mining, which reveals underlying links between users. Traditional sign prediction research focuses on the prediction of positive signs and neglects the mining of potential implicit links, and there is little research on negative sign prediction. To address these problems, we propose a two-stage model that uses implicit link detection and link sign prediction. First, we use the preference attachment closeness degree (PACD) to predict possible implicit links by adding a measure of relationship closeness to the traditional link prediction algorithm (PA). Next, we propose a negative link sign prediction (Ne-LP) method to predict relation types through multidimensional negative sign-related features, including those of nodes, user similarity, and structural balance, and merge them by a logistic regression model. Finally, we evaluate PACD and Ne-LP through extensive experiments on three real-world social network datasets, whose results demonstrate that the method can effectively mine implicit relations and accurately predict negative links.Keywords
Funding Information
- National Natural Science Foundation of China (61802258, 61572326, 61702333)
- Natural Science Foundation of Shanghai Municipality (18ZR1428300, 20ZR1455600)
This publication has 29 references indexed in Scilit:
- Exploiting behaviors of communities of twitter users for link predictionSocial Network Analysis and Mining, 2013
- Recommendation as link prediction in bipartite graphs: A graph kernel-based machine learning approachDecision Support Systems, 2013
- Effects of user similarity in social media2012
- Exploiting longer cycles for link prediction in signed networks2011
- Influence Maximization in Social Networks When Negative Opinions May Emerge and Propagate2011
- Spectral Analysis of Signed Graphs for Clustering, Prediction and Visualization2010
- Trust and Distrust Prediction in Social Network with Combined Graphical and Review-Based Attributes2010
- Gradual trust and distrust in recommender systemsFuzzy Sets and Systems, 2009
- Propagation of trust and distrust2004
- A New Status Index Derived from Sociometric AnalysisPsychometrika, 1953