计算机科学 ›› 2023, Vol. 50 ›› Issue (12): 255-261.doi: 10.11896/jsjkx.221000214
陆靓倩, 王中卿, 周国栋
LU Liangqian, WANG Zhongqing, ZHOU Guodong
摘要： 情感分析一直是自然语言处理中的热点研究方向,隐式情感分类指无显式情感词的情感分类任务,目前,隐式情感分析还处于起步阶段。隐式情感分析面临缺乏显式情感词、表达方式委婉、语义难以理解等问题,传统的情感分析方法如情感词典、词袋模型等难以生效,使得隐式情感分类任务更加艰巨。针对以上问题,提出了一种结合文本、词性与依存关系的图神经网络模型来进行隐式情感分类。具体来说,模型首先抽取文本的词性和依存特征,然后使用预训练语言模型BERT提取文本向量特征,从而构建了一个基于多种语言学特征的图注意力神经网络。该模型在SMP2021隐式情感识别公开数据集上进行了多次实验。实验结果表明,相较于多种基线模型,所提模型取得了较好的分类效果,证实了所提出的融合了多种语言学特征的隐式情感分类方法具有可行性和有效性。
中图分类号:
| [1]YGNG L G,ZHU J,TANG S P.Review of text emotion analysis[J].Computer Applications,2013,33(6):1574-1578. [2]LIU B.Sentiment analysis and opinion mining[M].Americal:Morgan & Claypool Publishers,2012. [3]LIAO J,WANG S G,LI D Y.Identification of fact-implied implicit sentiment based on multi-level semantic fused representation[J].Knowledge-Based Systems,2019,165(1):197-207. [4]JIAN L,YANG L,WANG S G.The constitution of a fine-grained opinion annotated corpus on weibo[C]//Lecture Notes in Artificial Intelligence Volume.2016:227-240. [5]YUAN J L,DING Y,PAN D X,et al.Chinese implicit emotion classification model based on temporal and contextual features[J].Computer Applications,2021,41(10):2820-2828. [6]ZHAO L G.Sentence level fine-grained affective computingbased on dependency syntax[D].Guangzhou:South China University of Technology,2015. [7]LIAO J.Research on fact-based implicit affective an-a lysisbased on representation learning[D].Taiyuan:Shanxi University,2018. [8]GUO F R,HUANG X X,WANG R B,et al.Metaphor recognition based on transformer and graph convolution neural network[J].Data Analysis and Knowledge Discovery,2022,6(4):120-129. [9]ZHANG W,WANG H,CHEN Y T,et al.Research on know-ledge recognition and relevance of Chinese idiom metaphor integrating transfer learning and text enhancement[J].Data Ana-lysis and Knowledge Discovery,2022,6(Z1):167-183. [10]HUANG H Y,LIU X,LIU Q.Text metaphor recognition graph coding method based on knowledge enhancement[J].Computer Research and Development,2023(1):140-152. [11]BHATTASALI S,CYTRYN J,FELDMAN E,et al.Automatic identification of rhetorical questions[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.2015:743-749. [12]WEN Z.Research on rhetorical question recognition and emotion discrimination based on depth learning[D].Shanxi:Shanxi University,2019. [13]LI Y,WU Z J,WANG S G,et al.A rhetorical question recognition method based on automatic acquisition of linguistic features[J].Journal of Chinese Information Science,2020,34(2):96-104. [14]SUN X,HE J J,REN F J.Satirical pragmatic discriminationbased on hybrid neural network model of multi feature fusion[J].Journal of Chinese Information,2016,30(6):215-223. [15]LU X.Research on Chinese Irony Recognition and EmotionalDiscrimination Based on Deep Learning[D].Shanxi:Shanxi University,2019. [16]LUO G Z,ZHAO Y Y,QIN B,et al.Irony Recognition for Social Media[J].Intelligent Computers and Applications,2020,10(2):301-307. [17]LI Z Y,ZOU Y C,ZHANG C,et al.Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:246-256. [18]ZHOU D Y,WANG J N,ZHANG L H,et al.Implicit Sentiment Analysis with Event-Centered Text Representation[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:6884-6893. [19]YANG S L,CHANG Z.Chinese implicit emotion analysis based on graph attention neural network[J].Computer Engineering and Application,2021,57(24):161-167. [20]HUANG S C,HAN D H,QIAO B Y,et al.An implicit emotion analysis method based on ERNIE2.0-BiLSTM-Attention[J].Small Microcomputer System,2021,42(12):2485-2489. [21]CHEN Q C,ZHAO H,ZUO E G,et al.Implicit emotion analysis based on context aware tree recurrent neural network[J].Computer Engineering and Application,2022,58(7):167-175. [22]YUAN J L,DING Y,PAN D X,et al.Chinese implicit emotion classification model based on temporal and contextual features[J].Computer Applications,2021,41(10):2820-2828. [23]CHEN M,UBUL K,XU X,et al.Connecting Text Classification with Image Classification:A New Preprocessing Method for Implicit Sentiment Text Classification[J].Sensors(Basel),2022,22(5):1899. [24]ZHUANG Y,LIU Z,LIU T T,et al.Implicit sentiment analysis based on multi-feature neural network model[J].Journal Information,2022,26(2):635-644. [25]SUN Y,WANG S,LI Y K,et al.Ernie2.0:understanding a continuous language pre training framework[C]//AAAI Artificial Intelligence Conference.2020:8968-8975. [26]DEVLIN J,CHANG M W,LEE K,et al.Bert:pre-training of deep bidirectional transformers for language understanding[C]//The 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Association for Computational Linguistics,2019:4171-4186. [27]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[C]//The 6th International Conference on Learning Representations.2018:1-12. [28]ARMAD J.Bag of Tricks for Efficient Text Classification[DB/OL].(2016-8-9).[2023-3-20].https://arxiv.org/abs/1607.01759. [29]RIE J,TONG Z.Deep Pyramid Convolutional Neural Networks for Text Categorization[C]//Annual Meeting of the Association for Computational Linguistics(ACL).2017. [30]YOON K.Convolutional neural networks for sentence classification[C]//Conference on Empirical Methods in Natural Language Processing.2014:1746-1751. [31]YANG L,WU Y G,WANG J L,et al.Review of research on cyclic neural networks[J].Computer Applications,2018,38(S2):1-6,26. [32]SUN Y,WANG S,LI Y,et al.ERNIE:Enhanced Representation through Knowledge Integration[J].arXiv:1904.09223,2019. [33]SONG Y,WANG J,TAO J,et al.Attentional Encoder Network for Targeted Seniment Classification[J].arXiv:1902.09314,2019. |
|
||
首页