Finding Sentiment Dimension in Vector Space of Movie Reviews: An Unsupervised Approach
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
This study suggests an unsupervised method to find sentiment orienations of the words in Korean movie reviews. The orientations are represented as real values on a sentiment domain, which is derived from high-dimensional vector space for the movie reviews. To search for the dimension, the Pointwise Mutual Information is first used to select a set of words that are close to common modifiers; The phrases comprised of these words often form good/ bad associations (e.g., “good acting”, “terrible acting”). A neural language model (Word2Vec) is then used to calculate the point-wise similarity distances between the chosen words and, dimensionality reduction algorithms (e.g., PCA, MDS) are employed to find the axis of the sentiment orientations. Finally, the performance of our method is measured by unsupervised classification of the two movie reviews based on the orientation values. According to the results, the best accuracy achieves 66% and 76% for the two datasets.
Abstract
This study suggests an unsupervised method to find sentiment orienations of the words in Korean movie reviews. The orientations are represented as real values on a sentiment domain, which is derived from high-dimensional vector space for the movie reviews. To search for the dimension, the Pointwise Mutual Information is first used to select a set of words that are close to common modifiers; The phrases comprised of these words often form good/ bad associations (e.g., “good acting”, “terrible acting”). A neural language model (Word2Vec) is then used to calculate the point-wise similarity distances between the chosen words and, dimensionality reduction algorithms (e.g., PCA, MDS) are employed to find the axis of the sentiment orientations. Finally, the performance of our method is measured by unsupervised classification of the two movie reviews based on the orientation values. According to the results, the best accuracy achieves 66% and 76% for the two datasets.
참고문헌 (20)
- Baroni, M., "Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors", the ACL, (1) (2014)
- Bengio, Y., "A neural probabilistic language model", Journal of machine learning research, 3, pp.1137~1155 (2003)
- Bishop, C., "Pattern Recognition and Machine Learning (Information Science and Statistics)" (2007), Springer
- Collobert, R., "A unified architecture for natural language processing: Deep neural networks with multitask learning", the Proceedings of the 25th international conference on Machine learning (2008)
- Deerwester, S., "Indexing by latent semantic analysis", Journal of the American society for information science, 41(6), pp.391~ (1990)
- Freeman, L. C, "Centrality in social networks conceptual clarification", Social networks, 1(3), pp.215~239 (1978)
- Gärdenfors, P, "Conceptual spaces: The geometry of thought" (2004), MIT press
- Hatzivassiloglou, V., "Predicting the semantic orientation of adjectives", the Proceedings of the eighth conference on European chapter of the Association for Computational Linguistics (1997)
- Maaten, L. v. d., "Visualizing data using t-SNE", Journal of machine learning research, 9, pp.2579~2605 (2008)
- Mikolov, T., "Efficient estimation of word representations in vector space", arXiv preprint arXiv:1301.3781, ~ (2013)
- Murphy, M. L, "Semantic relations and the lexicon: Antonymy, synonymy and other paradigms" (2003), Cambridge University Press
- Padó, S., "Constructing semantic space models from parsed corpora", the Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, 1 (2003)
- Picard, J., "Finding content-bearing terms using term similarities", the Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics (1999)
- Rubenstein, H., "Contextual correlates of synonymy", Communications of the ACM, 8(10), pp.627~633 (1965)
- Ruge, G, "Experiments on linguistically-based term associations", Information Processing & Management, 28(3), pp.317~332 (1992)
- Sahlgren, M, "The distributional hypothesis", Italian Journal of Linguistics, 20(1), pp.33~54 (2008)
- Schütze, H., "Information retrieval based on word senses", the Proceedings of the 4th Annual Symposium on Document Analysis and Information Retrieval, pp.161~175 (1995)
- Turney, P. D, "Thumbs up or thumbs down? : semantic orientation applied to unsupervised classification of reviews", the Proceedings of the 40th annual meeting on association for computational linguistics (2002)
- Turney, P. D., "From frequency to meaning : Vector space models of semantics", Journal of artificial intelligence research, 37(1), pp.141~188 (2010)
- Zagibalov, T., "Automatic seed word selection for unsupervised sentiment classification of Chinese text", the Proceedings of the 22nd International Conference on Computational Linguistics, 1 (2008)