Measuring user’s influence in the Yelp recommender system

Abstract

Purpose: Recommender systems collect information about users and businesses and how they are related. Such relation is given in terms of reviews and votes on reviews. User reviews gather opinions, rating scores and review influence. The latter component is crucial for determining which users are more relevant in a recommender system, that is, the users whose reviews are more popular than the average user’s reviews. Design/methodology/approach: A model of measure of user influence is proposed based on review and social attributes of the user. User influence is also used for determining how influenced has been a business being based on popular reviews. Findings: Results indicate there is a connection between social attributes and user influence. Such results are relevant for marketing, credibility estimation and Sybil detections, among others. Originality/value: The proposed model allows search parameterization based on the social attribute weights of users, reviews and businesses. Such weights defines the relevance on each attribute, which can be adjusted according to the search needs. Popularity results are then a function of weight preferences on user, reviews and businesses data join.