Dynamic Domain Adapting Sentiment Classifiers
Speaker: Justin Martineau
Start: Tuesday, September 22, 2009, 10:15AM
End: Tuesday, September 22, 2009, 11:30AM
Location: ITE 325 B
Abstract: Justin Martineau will give us a
preview of his dissertation proposal.
Sentiment analysis is the automatic detection and measurement of sentiment
in text segments by machines. However, sentiment is highly domain dependent.
This is particularly troubling given the scale and variety of topics seen on
the web. Providing sentiment search on the web requires more than the
standard machine learning approach. In this talk I describe a plan to
overcome domain dependence by breaking down documents into three different
types of signals. The different processing requirements exhibited by each of
these signals necessitates a dynamic domain adapting approach.
Participate remotely via dimdim. After 10:15, click on JOIN MEETING and enter 'ebiquity' for the meeting name.
Host: Tim Finin