Sentiment Classification of Online Mobile Reviews Using Combination of Word2vec and Bag-of-Centroids

  • Poonam ChoudhariEmail author
  • S. Veenadhari
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1101)


Sentiment classification is a technique to understand the feeling/attitude/sentiment toward a written piece of text by analyzing and then classifying the text as positive, negative, or neutral. One of the important aspects of classification is data that should be handled and represented carefully in the classification process, which affects the performance of the classifier. In the sentiment classification process, feature vector is used as the representation of data to work on. In the paper, we have experimented with the combination of Word2vec and Bag-of-Centroids’ feature vector in the sentiment classification process of online consumer reviews about different mobile brands. The feature vector is tested on different well-known machine learning classifiers used for sentiment analysis and compared with Word2vec feature vector. We also investigated the performance of a feature vector as the size of the dataset is increased. We found that the proposed feature vector performed well in comparison with Word2vec feature vector.


Sentiment classification Word2vec Bag-of-Centroids K-means clustering 


  1. 1.
    Alshari, E.M., A. Azman, S. Doraisamy, N. Mustapha, and M. Alkeshr. 2017. Improvement of sentiment analysis based on clustering of word2vec features. In 28th International Workshop on Database and Expert Systems Applications.Google Scholar
  2. 2.
    Bansal, Barkha, and Sangeet Shrivastava. 2018. Sentiment classification of online consumer reviews using word vector representations. Procedia Computer Science 132: 1147–1153. In ICCIDS 2018. International Conference on Computational Intelligence and Data Science, Apr 2018, ed. V. Singh and V.K. Asari. Elsevier.Google Scholar
  3. 3.
    Cambria, E., B. Schuller, Y. Xia, and C. Havasi. 2013. New avenues in opinion mining and sentiment analysis. IEEE Intelligent Systems 28 (2): 15–21.CrossRefGoogle Scholar
  4. 4.
    Poonam, Choudhari, and S. Veenadhari. 2019. Sentiment analysis of online product reviews with word2vec n-grams. Journal of Emerging Technologies and Innovative Research 6 (4): 555–559.Google Scholar
  5. 5.
    Fang, Xing, and Justin Zhan. 2015. Sentiment analysis using product review data. Journal of Big Data.
  6. 6.
  7. 7.
    Liu, Bing. 2012. Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies.Google Scholar
  8. 8.
    Mikolov, T., K. Chen, G. Corrado, and J. Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arXiv: 1301.3781v3 [cs.CL].Google Scholar
  9. 9.
    Mikolov, T., I. Sutskever, K. Chen, G. Corrado, J. Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. arXiv:1310.4546v1 [cs.CL].
  10. 10.
    Narayanan, Vivek, Ishan Arora, and Arjun Bhatia. 2013. Fast and accurate sentiment classification using an enhanced naive bayes model. In Intelligent Data Engineering and Automated Learning, IDEAL 2013. Lecture Notes in Computer Science 8206, 194–201.Google Scholar
  11. 11.
    Pang, B., and L. Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval 2: 1–135.CrossRefGoogle Scholar
  12. 12.
    Pang, B, and L. Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. Association for Computational Linguistics.Google Scholar
  13. 13.
    Pang, B., L. Lee, and S. Vaithyanathan. 2002. Thumbs Up? sentiment classification using machine learning techniques. In Annual Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.Google Scholar
  14. 14.
    Rong, Xin. 2016. word2vec parameter learning explained. arXiv: 1411.2738v4 [cs.CL].Google Scholar
  15. 15.
    Van Looy, A. 2016. Sentiment analysis and opinion mining (business intelligence 1). In Social media management, Springer texts in business and economics. Cham: Springer International Publishing Switzerland.
  16. 16.
    Zalik, K.R. 2008. An efficient k-means clustering algorithm. Pattern Recognition Letters 29: 1385–1391.CrossRefGoogle Scholar
  17. 17.
    Zhang, Dongwen, Hua Xu, Zengcai Su, and Yunfeng Xu. 2015. Chinese comments sentiment classification based on word2vec and SVMperf. Expert Systems with Applications 42: 1857–1863.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringRabindranath Tagore UniversityBhopalIndia

Personalised recommendations