Influence me! Predicting links to influential users

MONTESERIN, ARIEL J.; ARMENTANO, MARCELO G.

INFORMATION RETRIEVAL

SPRINGER

Año: 2019 vol. 22 p. 32 - 54

1386-4564

Abstract In addition to being in contact with friends, online social networks are commonly used as a source of information, suggestions and recommendations from members of the community. Whenever we accept a suggestion or perform any action because it was recommended by a ?friend?, we are being influenced by him/her. For this reason, it is useful for users seeking for interesting information to identify and connect to this kind of influential users. In this context, we propose an approach to predict links to influential users. Compared to approaches that identify general influential users in a network, our approach seeks to identify users who might have some kind of influence to individual (target) users. To carry out this goal, we adapted an influence maximization algorithm to find new influential users from the set of current influential users of the target user. Moreover, we compared the results obtained with different metrics for link prediction and analyzed in which context these metrics obtained better results.