1.School of Computer Information Engineering, Jiangxi Normal University, Nanchang, Jiangxi 330022, China; 2.School of Journalism and Communication, Jiangxi Normal University, Nanchang, Jiangxi 330022, China; 3.Management Decision Evaluation Research Center, Jiangxi Normal University, Nanchang, Jiangxi 330022, China
Abstract：Text emotion classification is a well-addressed task in the field of natural language processing. To deal with the unbalanced data which hurt the classification performance, this paper proposes an emotion classification method combining CNN and EWC algorithms. First, the method uses the random under-sampling method to obtain multiple sets of balanced data for training. Then it feeds each balanced dataset to CNN training in sequence, introducing EWC algorithm in the training process to overcome the catastrophic forgetting issue in CNN. Finally, the CNN model trained by the last data set is treated as the final classification model. The experimental results show that the proposed method is superior to the ensemble learning framework based on under-sampling and multi-classification algorithms, and outperforms the multi-channel LSTM neural network with 1.9% and 2.1% improvements in accuracy and G-mean, respectively.
[1] 李然,林政,林海伦,等.文本情绪分析综述[J].计算机研究与发展,2018,55(01):30-52. [2] 王中卿,李寿山,朱巧明,等.基于不平衡数据的中文情感分类[J].中文信息学报,2012,26(03):33-37,64. [3] 殷昊,李寿山,贡正仙,等.基于多通道LSTM的不平衡情绪分类方法[J].中文信息学报,2018,32(01):139-145. [4] 赵楠,张小芳,张利军.不平衡数据分类研究综述[J].计算机科学,2018,45(S1):22-27,57. [5] Krizhevsky A,Sutskever I,Hinton G.ImageNet classification with deep convolutional neural networks[C]//Proceedings of Advances in Neural Information Processing Systems,2012:1097-1105. [6] Kim Y.Convolutional neural networks for sentence classification[J].arXiv preprint arXiv:1408.5882,2014. [7] Xi Ouyang,Pan Zhou,Cheng Hua Li,et al.Sentiment analysis using convolution neural network[C]//Proceedings of 2015 IEEE International Conference on Computer and Information Technology,Ubiquitous Computing and Communications,Dependable,Autonomic and Secure Computing.IEEE,2015:2539-2364. [8] 李德玉,罗锋,王素格.融合CNN和标签特征的中文文本情绪多标签分类[J].山西大学学报(自然科学版),2019:1-12. [9] 张璐,沈忱林,李寿山.基于情绪特定词向量的情绪分类算法[J].计算机科学,2019,46(S1):93-97. [10] 郝苗苗,徐秀娟,于红,等.基于中文微博的情绪分类与预测算法[J].计算机应用,2018,38(S2):89-96. [11] 黄磊,李寿山,周国栋.基于句法信息的微博情绪识别方法研究[J].计算机科学,2017,44(02):244-249. [12] 温雯,吴彪,蔡瑞初,等.基于多类别语义词簇的新闻读者情绪分类[J].计算机应用,2016,36(08):2076-2081. [13] 乌达巴拉,汪增福.一种基于组合语义的文本情绪分析模型[J].自动化学报,2015,41(12):2125-2137. [14] 林怀逸,刘箴,柴玉梅,等.基于词向量预训练的不平衡文本情绪分类[J].中文信息学报,2019,33(05):132-142. [15] Tripathi S,Acharya S,Sharma R D,et al.Using deep and convolutional neural networks for accurate emotion classification on DEAP dataset[C]//Proceedings of the 29th IAAI Conference,2017. [16] 周安众,罗可.一种卷积神经网络的稀疏性Dropout正则化方法[J].小型微型计算机系统,2018,39(08):1674-1679. [17] McCloskey M,Cohen N J.Catastrophic interference in connectionist networks:The sequential learning problem[M].Psychology of Learning and Motivation.Academic Press,1989,24:109-165. [18] T Xiao,J Zhang,K Yang,et al.Errordriven incremental learning in deep convolutional neural network for large-scale image classification[C]//Proceedings of the 22nd ACM International Conference on Multimedia.ACM,2014:177-186. [19] Rebuffi S,Kolesnikov A,Sperl G,et al.iCaRL:Incremental classifier and representation learning[C]//Proceddings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:2001-2010. [20] Kirkpatrick J,Pascanu R,Rabinowitz N,et al.Overcoming catastrophic forgetting in neural networks[J].Proceedings of the National Academy of Sciences,2017,114(13):3521-3526.
2020, Vol. 34 
