From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series

TLDR

The study links public opinion polls with sentiment measures derived from text. The authors analyze 2008‑2009 consumer confidence and political opinion surveys, correlate them with Twitter sentiment word frequencies, and emphasize temporal smoothing to improve the model. Correlations between Twitter sentiment and polls reach up to 80%, showing that text streams can supplement or predict traditional polling and that temporal smoothing is essential for accurate modeling.

Abstract

We connect measures of public opinion measured from polls with sentiment measured from text. We analyze several surveys on consumer confidence and political opinion over the 2008 to 2009 period, and find they correlate to sentiment word frequencies in contempora- neous Twitter messages. While our results vary across datasets, in several cases the correlations are as high as 80%, and capture important large-scale trends. The re- sults highlight the potential of text streams as a substi- tute and supplement for traditional polling. consumer confidence and political opinion, and can also pre- dict future movements in the polls. We find that temporal smoothing is a critically important issue to support a suc- cessful model.