Abstract
For the issues that the accurate and rapid sentiment analysis of comment texts in the network big data environment, a text sentiment analysis method combining Bag of Words (CBOW) language model and deep learning is proposed. First, a vector representation of text is constructed by a CBOW language model based on feedforward neural networks. Then, the Convolutional Neural Network (CNN) is trained through the labeled training set to capture the semantic features of the text. Finally, the Dropout strategy is introduced in the Softmax classifier of traditional CNN, which can effectively prevent the model from over-fitting and has better classification ability. Experimental results on COAE2014 and IMDB datasets show that this method can accurately determine the emotional category of the text and is robust, the accuracy on the two datasets reached 90.5% and 87.2%, respectively.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Akhand MAH, Ahmed M, Rahman MMH (2016) Convolutional neural network training with artificial pattern for Bangla handwritten numeral recognition[C]. In: International conference on informatics, electronics and vision. IEEE, pp 625–630
Bitvai Z, Cohn T (2015) Non-linear text regression with a deep convolutional neural network[C]. In: Meeting of the association for computational linguistics and the, international joint conference on natural language processing, pp 180–185
He T, Huang W, Qiao Y et al (2016) Text-attentional convolutional neural network for scene text detection[J]. IEEE Trans Image Process 25(6):2529
Hu F, Xu X, Wang J et al (2017) Memory-enhanced latent semantic model: short text understanding for sentiment analysis[C]. In: International conference on database systems for advanced applications. Springer, Cham, pp 393–407
Huang Z, Zhao Z, Liu Q et al (2015) An unsupervised method for short-text sentiment analysis based on analysis of massive data[J], vol 50, no (3), pp 169–176
Kiritchenko S, Zhu X, Mohammad SM (2014) Sentiment analysis of short informal text[J]. J Artif Intell Res 50:723–762
Liu JM, Yang MH (2017) The signal processing and recognition of street view images by CNNs and softmax[C]. In: IEEE, international conference on communication software and networks. IEEE, pp 875–879
Luo Q, Xu W, Guo J (2014) A study on the CBOW model’s overfitting and stability[C]. In: International workshop on web-scale knowledge representation retrieval & reasoning. ACM, pp 9–12
Luo F, Li C, Cao Z (2016) Affective-feature-based sentiment analysis using SVM classifier[C]. In: IEEE, international conference on computer supported cooperative work in design. IEEE, pp 276–281
Menon A, Mehrotra K, Mohan CK et al (1996) Characterization of a class of sigmoid functions with applications to neural networks[J]. Neural Netw Off J Int Neural Netw Soc 9(5):819–835
Nguyen TH, Shirai K, Phrase RNN (2015) Phrase recursive neural network for aspect-based sentiment analysis[C]. In: Conference on empirical methods in natural language processing, pp 2509–2514
Poernomo A, Kang DK (2018) Biased dropout and crossmap dropout: learning towards effective dropout regularization in convolutional neural network [J]. Neural Netw 104:60–67
Ruan D, Pan H, Gao K (2015) Similar words analysis based on POS-CBOW language model[J]. J Hebei Univ Sci Technol 36(5):132–137
Sun X, He J (2018) A novel approach to generate a large scale of supervised data for short text sentiment analysis[J]. Multimed Tools Appl 21(1):1–21
Sun X, He J, Quan C (2017) A multi-granularity data augmentation based fusion neural network model for short text sentiment analysis[C]. In: Seventh international conference on affective computing and intelligent interaction workshops and demos. IEEE Computer Society, pp 12–17
Wang P, Xu J, Xu B et al (2015) Semantic clustering and convolutional neural network for short text categorization[C]. In: Meeting of the association for computational linguistics and the, international joint conference on natural language processing, pp 352–357
Wang J, Yu LC, Lai KR et al (2016) Dimensional sentiment analysis using a regional CNN-LSTM model[C]. In: Meeting of the association for computational linguistics, pp 225–230
Wang W, Zhao M, Wang J (2018) Effective android malware detection with a hybrid model based on deep autoencoder and convolutional neural network[J]. J Ambient Intell Humaniz Comput 30(1):1–9
Xiao K, Zhang Z, Wu J (2017) Chinese text sentiment analysis based on improved convolutional neural networks[C]. In: IEEE international conference on software engineering and service science. IEEE, pp 922–926
Yang J, Yang G (2018) Modified convolutional neural network based on dropout and the stochastic gradient descent optimizer[J]. Algorithms 11(3):28
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, B. Text sentiment analysis based on CBOW model and deep learning in big data environment. J Ambient Intell Human Comput 11, 451–458 (2020). https://doi.org/10.1007/s12652-018-1095-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-1095-6