BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Fine-grained sentiment analysis in text and multi-party conversati
 on - Theresa Wilson\, University of Edinburgh
DTSTART:20091113T120000Z
DTEND:20091113T130000Z
UID:TALK20471@talks.cam.ac.uk
CONTACT:Laura Rimell
DESCRIPTION:The past several years have seen a huge growth in research on 
 identifying and characterizing opinions and sentiments in text. While much
  of this work has focused on classifying the sentiment of documents\, a mo
 re fine-grained analysis at the sentence level and below is needed for any
  application that seeks detailed opinion information\, e.g.\, opinion ques
 tion answering. In this talk\, I will present work on fine-grained sentime
 nt analysis in both text and multi-party conversation. The approaches take
 n are quite different in terms of the features explored. For text\, a wide
  range of linguistically motivated features are employed for determining w
 hen instances of polarity terms are indeed being used to express positive 
 and negative sentiments in context. The results of this disambiguation are
  then used in determining sentence polarity. For sentiment analysis in spe
 ech\, the focus is on exploiting very shallow linguistic features\, such a
 s n-grams of characters and phonemes\, for classifying the subjectivity an
 d sentiment of utterances.\n
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR