Unsupervised sentiment classification of English movie reviews using automatic selection of positive and negative sentiment items
Strategy (2010)
Abstract
We consider the problem of classifying documents not by topic, but by overall sen- timent. Previous approaches to sentiment classification have favored domain-specific, supervised machine learning (Naive Bayes, maximum entropy classification, and support vector machines). Inherent in these method- ologies is the need for annotated training data. Building on previous work, we ex- amine an unsupervised system of iteratively extracting positive and negative sentiment items which can be used to classify docu- ments. Our method is completely unsuper- vised and only requires linguistic insight into the semantic orientation of sentiment.
Sign up today - FREE
Mendeley saves you time finding and organizing research. Learn more
- All your research in one place
- Add and import papers easily
- Access it anywhere, anytime
Start using Mendeley in seconds!
Readership Statistics
6 Readers on Mendeley
by Discipline
17% Linguistics
by Academic Status
50% Student (Master)
33% Researcher (at a non-Academic Institution)
17% Ph.D. Student
by Country
33% Germany
17% United Kingdom
17% Portugal
