Emotions and Activity Profiles of Influential Users in Product Reviews Communities

Viral marketing seeks to maximize the spread of a campaignthrough an online social network, often targeting influential nodes with highcentrality. In this article, we analyze behavioral aspects of influentialusers in trust-based product reviews communities, quantifying emotionalexpression, helpfulness, and user activity level. We focus on two independentproduct review communities, Dooyoo and Epinions, in whichusers can write product reviews and define trust links to filter productrecommendations. Following the patterns of social contagion processes, wemeasure user social influence by means of the k-shell decomposition of trustnetworks. For each of these users, we apply sentiment analysis to extracttheir extent of positive, negative, and neutral emotional expression. Inaddition, we quantify the level of feedback they received in their reviews,the length of their contributions, and their level of activity over theirlifetime in the community. We find that users of both communities exhibit alarge heterogeneity of social influence, and that helpfulness votes and ageare significantly better predictors of the influence of an individual thansentiment. The most active of the analyzed communities shows a particularstructure, in which the inner core of users is qualitatively different fromits periphery in terms of a stronger positive and negative emotionalexpression. These results suggest that both objective and subjective aspectsof reviews are relevant to the communication of subjective experience.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.