Abstract
Targeting at the great commercial and social values of sentiment analysis of online product reviews, this paper puts forward an emotion-semantics enhanced multi-channel convolutional neural network (EMCCNN) approach to dig automatically out the emotional position of the reviewer. This EMCCNN model is featured firstly with a completed construction of emotional symbols datasets which are composed of Chinese emotion words, degree adverbs, negative words, common Internet slang and emoticons, secondly with three input channels containing a relatively independent text sequence and emotional symbol sequence in each, thirdly with weighted pooling which summarizes different channel’s convolution result with various weight, then joins with max pooling to form the final emotion vectors, which are subsequently classified with softmax function. The experiment result shows that, after the adjustment of super parameters, the F1 value of EMCCNN has been improved by 3.2% compared with the traditional CNN one.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ravi, K., Ravi, V.: A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowl.-Based Syst. 89, 14–46 (2015)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168–177. ACM, New York (2004)
Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: Proceedings of International Conference on Web Search and Web Data Mining, pp. 231–240. ACM, New York (2008)
Turney, P.D.: Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 417–424. MIT Press, Cambridge (2002)
Kim, Y.: Convolutional neural network for sentence classification (2014). arXiv preprint. arXiv:1408.5882
Zhu, X., Sobihani, G.H.: Long short-term memory over recursive structure. IN: Proceedings of International Conference on Machine Learning, pp. 1604–1612. ACM, New York (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ren, X., Fu, Y., Yang, X. (2023). Sentiment Classification of Chinese Commodity-Comment Based on EMCCNN Model. In: Hong, W., Weng, Y. (eds) Computer Science and Education. ICCSE 2022. Communications in Computer and Information Science, vol 1811. Springer, Singapore. https://doi.org/10.1007/978-981-99-2443-1_27
Download citation
DOI: https://doi.org/10.1007/978-981-99-2443-1_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2442-4
Online ISBN: 978-981-99-2443-1
eBook Packages: Computer ScienceComputer Science (R0)