A Generate-and-Test Method of Detecting Negative-Sentiment Sentences

Abstract

Sentiment analysis requires human efforts to construct clue lexicons and/or annotations for machine learning, which are considered domain-dependent. This paper presents a sentiment analysis method where clues are learned automatically with a minimum training data at a sentence level. The main strategy is to learn and weight sentiment-revealing clues by first generating a maximal set of candidates from the annotated sentences for maximum recall and learning a classifier using linguistically-motivated composite features at a later stage for higher precision. The proposed method is geared toward detecting negative sentiment sentences as they are not appropriate for suggesting contextual ads. We show how clue-based sentiment analysis can be done without having to assume availability of a separately constructed clue lexicon. Our experimental work with both Korean and English news corpora shows that the proposed method outperforms word-feature based SVM classifiers. The result is especially encouraging because this relatively simple method can be used for documents in new domains and time periods for which sentiment clues may vary.