An unsupervised sentiment classifier on summarized or full reviews
WISE'10 Proceedings of the 11th international conference on Web information systems engineering
| Hi-index | 0.00 |
Sentiment classification is an applied technology with great significance. It can help people find right reviews in a more efficient way. In this paper, we present a novel efficient method for BBS sentiment classification. Through extracting sentiment-bearing words from WordNet using the maximum entropy, a ranking criterion based on a function of the probability of having Polarity or not is introduced. The words with polarity are selected as features, which are processed with SVM classifier at the following step. The experimental results show that our method achieves high performance.