Determining Impact of Social Media Badges through Joint Clustering of Temporal Traces and User Features

TL;DR

This paper presents two innovative methods for assessing the influence of social media badges on user behavior by analyzing temporal activity traces and user features, validated through synthetic and real-world data.

Contribution

It introduces joint clustering and classification approaches that combine temporal traces and user features to determine badge impact, a novel integration in this context.

Findings

Methods effectively validate badge influence on users

Approaches can characterize affected user groups

Results generalize across different datasets

Abstract

Badges are a common, and sometimes the only, method of incentivizing users to perform certain actions on online sites. However, due to many competing factors influencing user temporal dynamics, it is difficult to determine whether the badge had (or will have) the intended effect or not. In this paper, we introduce two complementary approaches for determining badge influence on users. In the first one, we cluster users' temporal traces (represented with point processes) and apply covariates (user features) to regularize results. In the second approach, we first classify users' temporal traces with a novel statistical framework, and then we refine the classification results with a semi-supervised clustering of covariates. Outcomes obtained from an evaluation on synthetic datasets and experiments on two badges from a popular Q&A platform confirm that it is possible to validate, characterize and to some extent predict users affected by the badge.