A New LSTM Network Model Combining TextCNN
The development of computer communication technology has brought massive amounts of spam texts. Spammers use a variety of textual means to avoid detection of spam texts, which has brought challenges to spam text filtering technology. Deep neural network has superior performance in feature representation and feature extraction. TextCNN based on convolutional neural network can extract the local feature representation of sentences, but ignore the successive relationship between words. The LSTM based on the recurrent neural network takes into account the sequential relationship between words, but it is not as good as TextCNN in representation of local features. We propose an algorithm that combines the TextCNN and LSTM network called TC-LSTM to implement spam text filtering, and compare the Precision, Recall and F-measure indicators with the traditional TextCNN and LSTM on two datasets. Experiments show that our TC-LSTM algorithm is superior to the traditional TextCNN and LSTM networks in spam text filtering.
KeywordsDeep neural network Network fusion Spam text filtering Deep learning
This work is partially supported by the National Natural Science Foundation of China (61402310). Natural Science Foundation of Jiangsu Province of China (BK20141195).
- 5.Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)
- 6.Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
- 8.Liu, P., Qiu, X., Chen, J., Huang, X.: Deep fusion LSTMs for text semantic matching. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 1034–1043 (2016)Google Scholar
- 10.Marz, N., Warren, J.: Big Data: Principles and Best Practices of Scalable Real-time Data Systems. Manning Publications Co, New York (2015)Google Scholar
- 11.Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
- 12.Shen, Y., He, X., Gao, J., Deng, L., Mesnil, G.: Learning semantic representations using convolutional neural networks for web search. In: Proceedings of the 23rd International Conference on World Wide Web, pp. 373–374. ACM (2014)Google Scholar
- 13.Wang, X., Liu, Y., Chengjie, S., Wang, B., Wang, X.: Predicting polarities of tweets by composing word embeddings with long short-term memory. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), vol. 1, pp. 1343–1353 (2015)Google Scholar
- 14.Yih, W., He, X., Meek, C.: Semantic parsing for single-relation question answering. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), vol. 2, pp. 643–648 (2014)Google Scholar
- 15.Yu, K., Jia, L., Chen, Y., Xu, W.: Deep learning: yesterday, today, and tomorrow. J. Comput. Res. Dev. 20(6), 1349 (2013)Google Scholar
- 16.Zhou, X., Wan, X., Xiao, J.: Attention-based LSTM network for cross-lingual sentiment classification. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 247–256 (2016)Google Scholar