Predicting positive and negative links in online social networks

By Jure Leskovec, Dan Huttenlocher, Jon M. Kleinberg. 2010

1,708 citations recorded by the source corpus.

We study online social networks in which relationships can be either positive (indicating relations such as friendship) or negative (indicating relations such as opposition or antagonism). Such a mix of positive and negative links arise in a variety of online settings; we study datasets from Epinions, Slashdot and Wikipedia. We find that the signs of links in the underlying social networks can be predicted with high accuracy, using models that generalize across this diverse range of sites. These models provide insight into some of the fundamental principles that drive the formation of signed links in networks, shedding light on theories of balance and status from social psychology; they also suggest social computing applications by which the attitude of one user toward another can be estimated from evidence provided by their relationships with other members of the surrounding social network.

Subfields: Communication, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Statistical and Nonlinear Physics

Citations in the corpus

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, methodology): “Recently, several studies [12, 14, 31, 35] propose methods to solve the problem of predicting signed links.”
Vital nodes identification in complex networks (2016, background): “(iv) The WikiVote network [322] contains all the Wikipedia voting data from the inception of Wikipedia till January 2008.”
A classification for community discovery methods in complex networks (2011, background): “Multidimensionality in networks is an emerging topic [10, 11, 12].”
Echoes of power: language effects and power differences in social interaction (2011, background): “Recent work has also studied the inference of status from on-line social network features [20, 29].”
SoK: The Evolution of Sybil Defense via Social Networks (2013, positive): “Our experimental evaluation of several real life social networks shows (90% diameter column of Table I) that the 90%-effective diameter [15], which measures the maximum distance between 90% of the pair of nodes, is indeed barely affected under attack.”
Recommender Systems (2016, positive): “For such problems, signed link prediction methods [346, 591] can be used to predict both like and dislike ratings.”
Evolution of Cooperation in Multiplex Networks (2012, background): “These advances has been largely facilitated by the explosion of data about mobile communication [28, 29], web-based social platforms [26, 27] and even the monitoring of face-to-face human interactions [30, 31].”
Link Prediction in Complex Networks: A Survey (2010, background): “[163] proposed amethod to predict the signs of links (positive or negative), yet the prediction of both the existence of a link and its sign has not been well studied.”
mTrust: discerning multi-faceted trust in a connected world (2012, background): “study how trust and distrust relations among users in social networks can be predicted using various topological features of a social network [12].”
Robust Matrix Completion via Joint Schatten p-Norm and lp-Norm Minimization (2012, methodology): “We evaluate the performance of our method using the Wikipedia 2 [22] and Slashdot 3 [23] data set.”
Cross-domain collaboration recommendation (2012, background): “Researchers have studied various issues in social networks, such as network properties [6, 11] and generation processes [18], link predictions [19, 20, 21, 32] and recommendations [2, 7, 17].”
Community Interaction and Conflict on the Web (2018, background): “However, analyses of intercommunity interaction and conflict are largely absent in previous work on web communities, which tend to focus on community detection [18, 80], interactions within individual communities [38, 47, 49], or how users spread their time”
Inferring social ties across heterogenous networks (2012, methodology): “[19] employ a logistic regression model to predict positive and negative links in online social networks.”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “Social trust and distrust relationships are among the most studied of directed social relationships [Guha et al. 2004; Leskovec et al. 2010c; Ma et al. 2008, 2009a; Massa and Avesani 2007].”