You are viewing a read-only archive of the Blogs.Harvard network. Learn more.

Ali Hashmi on Ideology and Text: Classifying and Analyzing Discourse using Machine Learning

June 30th, 2015

We can use technology to uncover patterns in data. But it’s much harder to uncover an “ideology” embedded in text.

In this talk, Ali Hashmi — a researcher at the MIT Center for Civic Media — discusses a tool he has created that uses data-driven approaches for classifying discourse in news media. Using an analysis of discourse on Islam in the mainstream media, the tool reveals how media coverage in several mainstream news sources tends to contextualize Muslims largely as a group embroiled in conflict at a disproportionately large level.

Also in ogg for download

More info on this event here.

Be Sociable, Share!

Entry Filed under: video

Leave a Comment

Required

Required, hidden

Some HTML allowed:
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>