Weakly supervised techniques for domain-independent sentiment classification

Read, Jonathon and Carroll, John (2009) Weakly supervised techniques for domain-independent sentiment classification. In: First International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion Measurement, Hong Kong, China.

Full text not available from this repository.


An important sub-task of sentiment analysis is polarity classification, in which text is classified as being positive or negative. Supervised machine learning techniques can perform this task very effectively. However, they require a large corpus of training data, and a number of studies have demonstrated that the good performance of supervised models is dependent on a good match between the training and testing data with respect to the domain, topic and time-period. Weakly-supervised techniques use a large collection of unlabelled text to determine sentiment, and so their performance may be less dependent on the domain, topic and time-period represented by the testing data. This paper presents experiments that investigate the effectiveness of word similarity techniques when performing weakly-supervised sentiment classification. It also considers the extent to which the performance of each method is independent from the domain, topic and time-period of the testing data. The results indicate that the word similarity techniques are suitable for applications that require sentiment classification across several domains.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: John Carroll
Date Deposited: 06 Feb 2012 18:54
Last Modified: 24 Apr 2012 09:39
URI: http://sro.sussex.ac.uk/id/eprint/18872
📧 Request an update