How Twitter Identifies Public Sentiment

Rebecca Tuhus-Dubrow focuses on the research of Justin Hollander, an associate professor of urban and environmental policy and planning at Tufts and founder of the university’s Urban Attitudes Lab. Tuhus Dubrow explains that Hollander and his "and his colleagues have begun developing models to analyze Twitter posts for key words and sentiments, in an effort to harness 'the free-flowing ideas and thoughts that people express on social media…'"

Hollander and team's efforts have so far focused on developing a system for categorizing sentiments by comparing sentiments expressed in Twitter posts. "He collected 122,187 tweets geotagged to New Bedford, Mass., from February through April of this year, and analyzed them with an automated tool designed to classify sentiments as positive or negative," explains Tuhus Dubrow.

Tuhus Dubrow goes on to exemplify some of the many potential benefits of Twitter in identifying trends in public sentiment, as well as the limitations of social media in speaking for all of the public.