Postmortem Analysis of Decayed Online Social Communities: Cascade Pattern Analysis and Prediction

TL;DR

This study analyzes inactivity decay in online communities, identifying key cascade patterns and developing machine learning models to predict community collapse, with implications for understanding and preventing social network decay.

Contribution

It introduces a comprehensive analysis of decay patterns in online communities and proposes a predictive framework for cascade size and virality, validated on StackExchange data.

Findings

Decay patterns differ significantly between active and decayed communities.

Multiple network measures better explain decay than single measures.

Expert members influence community activity levels.

Abstract

Recently, many online social networks, such as MySpace, Orkut, and Friendster, have faced inactivity decay of their members, which contributed to the collapse of these networks. The reasons, mechanics, and prevention mechanisms of such inactivity decay are not fully understood. In this work, we analyze decayed and alive sub-websites from the StackExchange platform. The analysis mainly focuses on the inactivity cascades that occur among the members of these communities. We provide measures to understand the decay process and statistical analysis to extract the patterns that accompany the inactivity decay. Additionally, we predict cascade size and cascade virality using machine learning. The results of this work include a statistically significant difference of the decay patterns between the decayed and the alive sub-websites. These patterns are mainly: cascade size, cascade virality, cascade duration, and cascade similarity. Additionally, the contributed prediction framework showed satisfactory prediction results compared to a baseline predictor. Supported by empirical evidence, the main findings of this work are: (1) the decay process is not governed by only one network measure; it is better described using multiple measures; (2) the expert members of the StackExchange sub-websites were mainly responsible for the activity or inactivity of the StackExchange sub-websites; (3) the Statistics sub-website is going through decay dynamics that may lead to it becoming fully-decayed; and (4) decayed sub-websites were originally less resilient to inactivity decay, unlike the alive sub-websites.