BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Almost-unsupervised multilingual sentiment analysis - John Carroll
  - University of Sussex
DTSTART:20090130T120000Z
DTEND:20090130T130000Z
UID:TALK16444@talks.cam.ac.uk
CONTACT:Johanna Geiss
DESCRIPTION:I will describe a new\, unsupervised method for classification
  of documents with respect to sentiment\, applied to product reviews in Ch
 inese. The method does not require any annotated training data\; it only r
 equires information about commonly occurring negations and adverbials. The
  results obtained are comparable to those of supervised classifiers\, up t
 o an F1 of 92%. I will also talk about a variant of this system entered in
  the NTCIR-7 Multilingual Opinion Analysis Task (MOAT). This system was th
 e only one applied to all four of the MOAT languages\, Japanese\, English\
 , and Simplified and Traditional Chinese. The system uses an almost-unsupe
 rvised approach\, tackling two of the sub-tasks: opinionated sentence dete
 ction and topic relevance detection. [Joint work with Taras Zagibalov (mai
 n contributor)]
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR