How we did it

The Oscar Senti-meter is a tool developed by the L.A. Times, IBM and the University of Southern California Annenberg Innovation Lab to analyze opinions about the Academy Awards race shared in millions of public messages on Twitter. Focused on the best actor, actress and picture categories, the Senti-meter combs through a high volume of tweets daily and uses language-recognition technology, developed in collaboration with USC’s Signal Analysis and Interpretation Lab, to gauge positive, negative and neutral opinions shared in the messages. It also tracks the number of tweets.

Cataloguing these tweets over time gives insight into the vox pop surrounding Hollywood’s awards season and gives a voice to average fans who may endorse – or abhor – the selections made by Tinseltown’s elite. While the Senti-meter has some ability to capture tweets in languages other than English, such as Spanish, it is not equipped to rate such tweets on a positive/negative scale. Such tweets are included in the total volume of tweets but are not scored for sentiment. The search terms and key words are also being continuously updated so as to capture the most relevant tweets about movies, actors and actresses and their Oscar buzz.

*Data missing for Jan. 29-31.