Step Out of Your Comfort Zone: More Inclusive Content Recommendation for Networked Systems

TL;DR

This paper proposes a new approach to content recommendation in social networks that aims to reduce bias towards closed communities by considering information dissemination as a metric, validated on academic and Yelp datasets.

Contribution

It introduces a novel metric based on information dissemination to improve inclusivity in social network content recommendations.

Findings

Enhanced recommendation diversity by reducing community bias

Validated approach on academic collaboration and Yelp datasets

Improved connection recommendations through dissemination metrics

Abstract

Networked systems are widely applicable in real-world scenarios such as social networks, infrastructure networks, and biological networks. Among those applications, we are interested in social networks due to their complexity and popularity. One crucial task on the social network is to recommend new content based on special characteristics of the graph structure. In this project, we aim to enhance the recommender systems by preventing the recommendations from leaning towards contents from closed communities. To counteract the bias, we will consider information dissemination across network as a metric to assess the recommendation for contents e.g. new connections and news feed. We use academic collaboration network and user-item interaction datasets from Yelp to simulate an environment for connection recommendations and to validate the proposed algorithm.