The Use of Sound Symbolism in Sentiment Classification
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.
Unable to display preview. Download preview PDF.
- 2.David, C.: A Dictionary of Linguistics and Phonetics. Wiley-Blackwell (2008)Google Scholar
- 3.Fellbaum, C.: WordNet: An Electronic Lexical Database. MIT Press (1998)Google Scholar
- 4.Hamano, S.: The Sound-Symbolic System of Japanese. CSLI Publications (1998)Google Scholar
- 5.Hida, Y., Asada, H.: Gendai Giongo Gitaigo Yoho Jiten. Tokyo-do (2002) (in Japanese) ISBN: 9784490106107Google Scholar
- 6.Kamps, J., Marx, M., Mokken, R.J., de Rijke, M.: Using Wordnet to Measure Semantic Orientations of Adjectives. In: Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC 2004), pp. 1115–1118 (2004)Google Scholar
- 7.Köhler, W.: Gestalt Psychology. Liveright, New York (1929)Google Scholar
- 8.Ramachandran, V.S., Hubbard, E.M.: Synaesthesia: A window into perception, thought and language. Journal of Consciousness Studies, 3–34 (2001)Google Scholar
- 9.Takamura, H., Inui, T., Okumura, M.: Extracting semantic orientations of words using spin model. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics (ACL 2005), pp. 133–140 (2005)Google Scholar