Estimating Topic Exposure for Under-Represented Users on Social Media

TL;DR

This paper introduces a novel framework to estimate topic exposure for under-represented social media users, focusing on engagers, to reduce bias in behavioral analysis caused by participation inequality.

Contribution

The work presents a new method for identifying and estimating topic exposure for engagers, incorporating behavioral patterns and demographic data to improve analysis accuracy.

Findings

Effective identification of user groups based on engagement levels

Improved estimation of topic exposure for under-represented users

Reduction of bias in social media behavioral analysis

Abstract

Online Social Networks (OSNs) facilitate access to a variety of data allowing researchers to analyze users' behavior and develop user behavioral analysis models. These models rely heavily on the observed data which is usually biased due to the participation inequality. This inequality consists of three groups of online users: the lurkers - users that solely consume the content, the engagers - users that contribute little to the content creation, and the contributors - users that are responsible for creating the majority of the online content. Failing to consider the contribution of all the groups while interpreting population-level interests or sentiments may yield biased results. To reduce the bias induced by the contributors, in this work, we focus on highlighting the engagers' contributions in the observed data as they are more likely to contribute when compared to lurkers, and they comprise a bigger population as compared to the contributors. The first step in behavioral analysis of these users is to find the topics they are exposed to but did not engage with. To do so, we propose a novel framework that aids in identifying these users and estimates their topic exposure. The exposure estimation mechanism is modeled by incorporating behavioral patterns from similar contributors as well as users' demographic and profile information.