Classification for Social Media Short Text Based on Word Distributed Representation

  • Dexin Zhao
  • Zhi ChangEmail author
  • Nana Du
  • Shutao Guo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)


According to the brief and meaningless features of the social media content, we propose a text classification algorithm based on word vectors, which can quickly and effectively realize the automatic classification of the short text in social media. In view of the lack of word order and position considerations in the Word2vec model, we combine the Word2vec trained word vector with the convolutional neural network (CNN) model to propose SW-CNN and WW-CNN classification algorithms. The methods are evaluated on the three different datasets. Compared with existing text classification methods based on convolutional neural network (CNN) or recurrent neural network (RNN), the experimental results show that our approach has superior performance in short text classification.


Text classification Word2vec Word vector Social media 


  1. 1.
    Silva, J., Coheur, L., Mendes, A.C.: From symbolic to sub-symbolic information in question classification. Artif. Intell. Rev. 35(2), 137–154 (2011)CrossRefGoogle Scholar
  2. 2.
    Huang, Z., Thint, M., Qin, Z.: Question classification using head words and their hypernyms. In: EMNLP, pp. 927–936 (2008)Google Scholar
  3. 3.
    Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Association for Computational Linguistics, pp. 90–94 (2012)Google Scholar
  4. 4.
    Delaye, A., Liu, C.L.: Text/Non-text classification in online handwritten documents with conditional random fields. Commun. Comput. Inf. Sci. 321(53), 514–521 (2012)Google Scholar
  5. 5.
    Kim, Y.: Convolutional neural networks for sentence classification. In: Conference on Empirical Methods on Natural Language Processing (2014)Google Scholar
  6. 6.
    Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A Convolutional neural network for modelling sentences. Eprint Arxiv. (2014)Google Scholar
  7. 7.
    Socher, R., Huval, B., Manning, C.D., et al.: Semantic compositionality through recursive matrix-vector spaces. In: Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1201–1211 (2012)Google Scholar
  8. 8.
    Johnson, R., Zhang, T.: Effective use of word order for text categorization with convolutional neural networks. Eprint Arxiv (2014)Google Scholar
  9. 9.
    Zhou, C., Sun, C., Liu, Z., et al.: A C-LSTM neural network for text classification. Comput. Sci. 1(4), 39–44 (2015)Google Scholar
  10. 10.
    Lee, J.Y., Dernoncourt, F.: Sequential short-text classification with recurrent and convolutional neural networks. 515–520 (2016)Google Scholar
  11. 11.
    Trask, A., Gilmore, D., Russell, M.: Modeling order in neural word embeddings at scale. Comput. Sci., 2266–2275 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Tianjin University of TechnologyTianjinChina

Personalised recommendations