Residualized Factor Adaptation for Community Social Media Prediction Tasks
This addresses the challenge of accurately modeling community-level predictions in social media for researchers and practitioners, though it is incremental by building on prior work on socio-demographic contexts.
The paper tackles the problem of predicting community outcomes from social media language by integrating socio-demographic context, showing that residualized factor adaptation significantly improves predictions in 4 out of 5 tasks, such as heart disease mortality and life satisfaction.
Predictive models over social media language have shown promise in capturing community outcomes, but approaches thus far largely neglect the socio-demographic context (e.g. age, education rates, race) of the community from which the language originates. For example, it may be inaccurate to assume people in Mobile, Alabama, where the population is relatively older, will use words the same way as those from San Francisco, where the median age is younger with a higher rate of college education. In this paper, we present residualized factor adaptation, a novel approach to community prediction tasks which both (a) effectively integrates community attributes, as well as (b) adapts linguistic features to community attributes (factors). We use eleven demographic and socioeconomic attributes, and evaluate our approach over five different community-level predictive tasks, spanning health (heart disease mortality, percent fair/poor health), psychology (life satisfaction), and economics (percent housing price increase, foreclosure rate). Our evaluation shows that residualized factor adaptation significantly improves 4 out of 5 community-level outcome predictions over prior state-of-the-art for incorporating socio-demographic contexts.