University of Cambridge > Talks.cam > NLIP Seminar Series > Almost-unsupervised multilingual sentiment analysis

Almost-unsupervised multilingual sentiment analysis

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Johanna Geiss.

I will describe a new, unsupervised method for classification of documents with respect to sentiment, applied to product reviews in Chinese. The method does not require any annotated training data; it only requires information about commonly occurring negations and adverbials. The results obtained are comparable to those of supervised classifiers, up to 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 the only one applied to all four of the MOAT languages, Japanese, English, and Simplified and Traditional Chinese. The system uses an almost-unsupervised approach, tackling two of the sub-tasks: opinionated sentence detection and topic relevance detection. [Joint work with Taras Zagibalov (main contributor)]

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity