Utility-Based Link Recommendation for Online Social Networks

  title={Utility-Based Link Recommendation for Online Social Networks},
  author={Zhepeng Li and Xiao Fang and Xue Bai and Olivia R. Liu Sheng},
  journal={Economics of Networks eJournal},
Link recommendation, which suggests links to connect currently unlinked users, is a key functionality offered by major online social networks. Salient examples of link recommendation include "People You May Know" on Facebook and LinkedIn as well as "You May Know" on Google+. The main stakeholders of an online social network include users e.g., Facebook users who use the network to socialize with other users and an operator e.g., Facebook Inc. that establishes and operates the network for its… 

Diversity Preference-Aware Link Recommendation for Online Social Networks

This work operationalizes and operationalizes the concept of diversity preference for link recommendation and proposes a new link recommendation problem: the diversity preference-aware link recommendationProblem, and develops a novel link recommendation method to solve the problem.

A Survey of Link Recommendation for Social Networks

This article surveys state-of-the-art link recommendation methods and identifies social and economic theories, such as social interaction theory, that underlie these methods and explains from a theoretical perspective why a link recommendation method works.

Link Recommendation for Social Influence Maximization

This article measures the popularity of a user by means of her social influence, which is her capability to influence other users’ opinions, and proposes a link recommendation algorithm that evaluates the links to suggest according to their increment in social influence instead of their likelihood of being created.


A utility-based network building problem, with an aim to strike a balance between the gained social capital – in the form of closeness centrality – and the cost of establishing ties, and a suite of models of network formation that capture important structural properties are proposed.

An Experimental Evaluation of Link Prediction for Movie Suggestions Using Social Media Content

This chapter has explored a novel technique of recommendation for social media and used well known social network analysis mechanisms-link prediction, which exploits the prediction features to predict new links among users of IMDb.

Balancing the Pain and Gain of Hobnobbing: Utility-Based Network Building over Atributed Social Networks

A utility-based network building problem, with an aim to strike a balance between the gained social capital - in the form of closeness centrality - and the cost of establishing ties, and a suite of models of network formation that capture important structural properties are proposed.

What Will Be Popular Next? Predicting Hotspots in Two-mode Social Networks

A gradient learning method based on mutual reinforcement process (GLMR) that targets the optimal parameter configuration for pairwise ranking of social diffusions and demonstrates analytical properties of the proposed method such as guaranteed convergence and the convergence rate.

A Friend Like Me: Modeling Network Formation in a Location-Based Social Network

An empirical model of social link creation that incorporates individual characteristics and pairwise user similarities is built and finds the empirical results are robust: network formation decisions are significantly affected by the proximity measures.



Link Prediction and Recommendation across Heterogeneous Social Networks

This work gives a formal definition of link recommendation across heterogeneous networks, and proposes a ranking factor graph model (RFG) for predicting links in social networks, which effectively improves the predictive performance.

Exploiting place features in link prediction on location-based social networks

A supervised learning framework is described which exploits new prediction features based on the properties of the places visited by users which are able to discriminate potential future links among them and which exploits these prediction features to predict new links among friends-of-friends and place-friends.

Like like alike: joint friendship and interest propagation in social networks

This paper proposes a framework that exploits homophily to establish an integrated network linking a user to interested services and connecting different users with common interests, upon which both friendship and interests could be efficiently propagated.

Make new friends, but keep the old: recommending people on social networking sites

Algorithms based on social network information were able to produce better-received recommendations and find more known contacts for users, while algorithms using similarity of user-created content were stronger in discovering new friends.

Predicting Links and Inferring Attributes using a Social-Attribute Network (SAN)

The SAN framework is extended with several leading supervised and unsupervised link prediction algorithms and the novel observation that attribute inference can help inform link prediction, i.e., link prediction accuracy is further improved by rst inferring missing attributes.

Supervised random walks: predicting and recommending links in social networks

An algorithm based on Supervised Random Walks is developed that naturally combines the information from the network structure with node and edge level attributes and outperforms state-of-the-art unsupervised approaches as well as approaches that are based on feature extraction.

Using Friendship Ties and Family Circles for Link Prediction

It is shown that when there are tightly-knit family circles in a social network, the accuracy of link prediction models can be improved, by making use of the family circle features based on the likely structural equivalence of family members.

The link-prediction problem for social networks

Experiments on large coauthorship networks suggest that information about future interactions can be extracted from network topology alone, and that fairly subtle measures for detecting node proximity can outperform more direct measures.

Predicting Adoption Probabilities in Social Networks

This study identifies and operationalize key factors that affect adoption decisions: social influence, structural equivalence, entity similarity, and confounding factors and develops the locally weighted expectation-maximization method for Naive Bayesian learning to predict adoption probabilities.

Folks in Folksonomies: social link prediction from shared metadata

It is shown that a substantial level of local lexical and topical alignment is observable among users who lie close to each other in the social network, and suggests that users with similar topical interests are more likely to be friends, and semantic similarity measures among users based solely on their annotation metadata should be predictive of social links.