Machine Learning
Extracting semantic orientations of words using spin model
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Hi-index | 0.00 |
In this paper, we present a method for estimating the sentiment polarity of Japanese sentences including onomatopoeic words. Onomatopoeic words imitate the sounds they represent and can help us understand the sentiment of the sentence. Although there are many onomatopoeic words in Japanese, conventional sentiment classification methods have not taken them into consideration. The sentiment polarity of onomatopoeic words can be estimated using the sound symbolism derived from their vocal sounds. Our experimental results show that the proposed method with sound symbolism can significantly outperform the baseline method that is not with sound symbolism.