Multi-Granularity Chinese Text Sentiment Analysis Driven by Knowledge and Data

doi:10.3778/j.issn.1002-8331.2204-0464

Abstract

Abstract: In recent years, researches on Chinese text sentiment analysis have made great progress, but few of which have explored the differences between languages, the effectiveness of domain knowledge, and downstream task requirement. In view of this, according to the particularity of Chinese texts and the actual needs of sentiment analysis, a Chinese text sentiment analysis method is proposed in this paper, which integrates multi-granularity semantic features such as characters, words, radicals, and parts of speech. This method deeply integrates the knowledge vectors obtained from the emotional knowledge triples through the TransE model, the feature vectors obtained by bidirectional gated recurrent unit（BiGRU） and attention mechanism, and introduces radical features and emotional part-of-speech features based on character and word features. The comparative experimental results on the Douban movie review dataset and the NLPECC dataset show that the method proposed in this paper can effectively use emotional knowledge and multi-granularity features to improve Chinese emotion recognition performance, and the F1 score of the method reaches 89.23% and 84.84% respectively, which completes the Chinese text sentiment analysis task well.

Key words: Chinese text, knowledge graph, multi-granularity semantic features, sentiment analysis

摘要： 近年来，中文文本情感分析研究取得了长足进步，但鲜有研究从语言间的差异性、领域知识的有效性和下游任务需求等方面进行探讨。鉴于此，针对中文文本的特殊性以及情感分析的实际需求，将情感知识三元组通过TransE模型得到的知识向量与双向门控循环单元、注意力机制等模型得到的特征向量进行深度融合，并在字、词特征的基础上，引入部首特征和情感词性特征，提出知识与数据协同驱动下融入字、词、部首、词性等多粒度语义特征的中文文本情感分析方法。豆瓣电影评论集和NLPECC数据集上的实验结果表明，所提方法能够有效利用情感知识与多粒度特征提升中文情感识别性能，其F1值分别达到了89.23%和84.84%，较好地完成了中文文本情感分析任务。

关键词: 中文文本, 知识图谱, 多粒度语义特征, 情感分析

LIU Zhongbao, WANG Yufei. Multi-Granularity Chinese Text Sentiment Analysis Driven by Knowledge and Data[J]. Computer Engineering and Applications, 2023, 59(15): 177-186.

刘忠宝, 王宇飞. 知识与数据驱动的多粒度中文文本情感分析[J]. 计算机工程与应用, 2023, 59(15): 177-186.

References

[1] 许智宏，于子琪，董永峰，等.影评情感分析知识图谱构建研究[J].计算机仿真，2020，37（8）：424-430.
XU Z H，YU Z Q，DONG Y F，et al.Research on constructing the knowledge graph based on emotional analysis of film review[J].Computer Simulation，2020，37（8）：424-430.
[2] CAI Y，YANG K，HUANG D，et al.A hybrid model for opinion mining based on domain sentiment dictionary[J].International Journal of Machine Learning and Cybernetics，2019，10（8）：2131-2142.
[3] RUZ G A，HENRíQUEZ P A，MASCARE?O A.Sentiment analysis of Twitter data during critical events through Bayesian networks classifiers[J].Future Generation Computer Systems，2020，106：92-104.
[4] 张海涛，王丹，徐海玲，等.基于卷积神经网络的微博舆情情感分类研究[J].情报学报，2018，37（7）：695-702.
ZHANG H T，WANG D，XU H L，et al.Sentiment classification of micro-blog public opinion based on convolution neural network[J].Journal of the China Societific and Technical Information，2018，37（7）：695-702.
[5] 李平，戴月明，吴定会.双通道卷积神经网络在文本情感分析中的应用[J].计算机应用，2018，38（6）：1542-1546.
LI P，DAI Y M，WU D H.Application of dual-channel convolutional neural network in sentiment analysis[J].Journal of Computer Applications，2018，38（6）：1542-1546.
[6] 曹宇，李天瑞，贾真，等.BGRU：中文文本情感分析的新方法[J].计算机科学与探索，2019，13（6）：973-981.
CAO Y，LI T R，JIA Z，et al.BGRU：new method of Chinese text sentiment analysis[J].Journal of Frontiers of Computer Science and Technology，2019，13（6）：973-981.
[7] 张柳，王晰巍，黄博，等.基于字词向量的多尺度卷积神经网络微博评论的情感分类模型及实验研究[J].图书情报工作，2019，63（18）：99-108.
ZHANG L，WANG X W，HUANG B，et al.A sentiment classification model and experimental study of microblog commentary based on multivariate convolutional neural networks based on word vector[J].Library and Information Service，2019，63（18）：99-108.
[8] 吴鹏，李婷，仝冲，等.基于OCC模型和LSTM模型的财经微博文本情感分类研究[J].情报学报，2020，39（1）：81-89.
WU P，LI T，TONG C，et al.Sentiment classification of financial microblog text based on the model of OCC and LSTM[J].Journal of the China Society for Scientific and Technical Information，2020，39（1）：81-89.
[9] 王义，沈洋，戴月明.基于细粒度多通道卷积神经网络的文本情感分析[J].计算机工程，2020，46（5）：102-108.
WANG Y，SHEN Y，DAI Y M.Sentiment analysis of texts based on fine-grained multi-channel convolutional neural network[J].Computer Engineering，2020，46（5）：102-108.
[10]   刘文秀，李艳梅，罗建，等.基于BERT与BiLSTM的中文短文本情感分析[J].太原师范学院学报（自然科学版），2020，19（4）：52-58.
LIU W X，LI Y M，LUO J，et al.Sentiment analysis of Chinese short text based on BERT and BiLSTM[J].Journal of Taiyuan Normal University（Natural Science Edition），2020，19（4）：52-58.
[11]   DEVLIN J，CHANG M W，LEE K，et al.BERT：pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，Minneapolis，USA，2019：4171-4186.
[12]   缪亚林，姬怡纯，张顺，等.CNN-BiGRU模型在中文短文本情感分析的应用[J].情报科学，2021，39（4）：85-91.
MIAO Y L，JI Y C，ZHANG S，et al.Application of CNN-BiGRU model in Chinese short text sentiment analysis[J].Information Science，2021，39（4）：85-91.
[13] 胡任远，刘建华，卜冠南，等.融合BERT的多层次语义协同模型情感分析研究[J].计算机工程与应用，2021，57（13）：176-184.
HU R Y，LIU J H，BU G N，et al.Research on sentiment analysis of multi-level semantic collaboration model fused with BERT[J].Computer Engineering and Applications，2021，57（13）：176-184.
[14]   林世平，林松海，魏晶晶，等.融合知识图谱的文本情感分析[J].福州大学学报（自然科学版），2020，48（3）：269-275.
LIN S P，LIN S H，WEI J J，et al.Emotional classification of combining knowledge graph[J].Journal of Fuzhou University（Natural Science Edition），2020，48（3）：269-275.
[15] 邓立明，魏晶晶，吴运兵，等.基于知识图谱与循环注意力网络的视角级情感分析[J].模式识别与人工智能，2020，33（6）：479-487.
DENG L M，WEI J J，WU Y B，et al.Aspect level sentiment analysis based on knowledge graph and recurrent attention network[J].Pattern Recognition and Artificial Intelligence，2020，33（6）：479-487.
[16]   MIKOLOV T，SUTSKEVER I，CHEN K，et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference in Neural Information Processing Systems，New York，USA，2013：3111-3119.
[17]   BORDERS A，USUNIER N，GARCIA-DURAN A，et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 27th Annual Conference on Neural Information Processing Systems，Lake Tahoe，Nevada，USA，2013：2787-2795.
[18]   ZHOU H，HUANG M，ZHANG T，et al.Emotional chatting machine：emotional conversation generation with internal and external memory[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence，Louisiana，USA，2018：730-738.