File(s) not publicly available
Weakly supervised techniques for domain-independent sentiment classification
presentation
posted on 2023-06-07, 21:43 authored by Jonathon Read, John CarrollAn 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.
History
Publication status
- Published
Publisher
Association for Computing Machinary, IncExternal DOI
Volume
p45-52Page range
45-52Pages
8.0Presentation Type
- paper
Event name
First International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion MeasurementEvent location
Hong Kong, ChinaEvent type
conferenceISBN
978-1-60558-805-6Department affiliated with
- Informatics Publications
Full text available
- No
Peer reviewed?
- Yes