Predicting risky behavior in social communities

TL;DR

This paper introduces a model that predicts individual risk profiles by combining local features with social community structures, improving accuracy over feature-only models in social network data.

Contribution

The paper proposes a novel approach that leverages social community detection to enhance risk prediction, addressing limitations of local features and sparse network influence modeling.

Findings

Model outperforms feature-only predictions in accuracy.

Effective in diverse social network datasets.

Better predictions with richer network information.

Abstract

Predicting risk profiles of individuals in networks (e.g.~susceptibility to a particular disease, or likelihood of smoking) is challenging for a variety of reasons. For one, `local' features (such as an individual's demographic information) may lack sufficient information to make informative predictions; this is especially problematic when predicting `risk,' as the relevant features may be precisely those that an individual is disinclined to reveal in a survey. Secondly, even if such features are available, they still may miss crucial information, as `risk' may be a function not just of an individual's features but also those of their friends and social communities. Here, we predict individual's risk profiles as a function of both their local features and those of their friends. Instead of modeling influence from the social network directly (which proved difficult as friendship links may be sparse and partially observed), we instead model influence by discovering social communities in the network that may be related to risky behavior. The result is a model that predicts risk as a function of local features, while making up for their deficiencies and accounting for social influence by uncovering community structure in the network. We test our model by predicting risky behavior among adolescents from the Add health data set, and hometowns among users in a Facebook ego net. Compared to prediction by features alone, our model demonstrates better predictive accuracy when measured as a whole, and in particular when measured as a function of network "richness."