Provenance and social network analysis for recommender systems: a literature review

Abstract

Recommender systems (RS) and their scientific approach have become very important because they help scientists find suitable publications and approaches, customers find adequate items, tourists find their preferred points of interest, and many more recommendations on domains. This work will present a literature review of approaches and the influence that social network analysis (SNA) and data provenance has on RS. The aim is to analyze differences and similarities using several dimensions, public datasets for assessing their impacts and limitations, evaluations of methods and metrics along with their challenges by identifying the most efficient approaches, the most appropriate assessment data sets, and the most appropriate assessment methods and metrics. Hence, by correlating these three fields, the system will be able to improve the recommendation of certain items, by being able to choose the recommendations that are made from the most trusted nodes/resources within a social network. We have found that content-based filtering techniques, combined with term frequency-inverse document frequency (TF-IDF) features are the most feasible approaches when combined with provenance since our focus is to recommend the most trusted items, where trust, distrust, and ignorance are calculated as weight in terms of the relationship between nodes on a network.