Computer Science

Computer Science ›› 2024, Vol. 51 ›› Issue (6A): 230800011-9.doi: 10.11896/jsjkx.230800011

• Artificial Intelligenc • Previous Articles     Next Articles

Construction Method of Domain Sentiment Lexicon Based on Improved TF-IDF and BERT

JIANG Haoda, ZHAO Chunlei, CHEN Han, WANG Chundong   

  1. 1 Key Laboratory of Computer Vision and System of Ministry of Education,Tianjin University of Technology,Tianjin 300384,China
    2 Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology,Tianjin 300384,China
  • Published:2024-06-06
  • About author:JIANG Haoda,born in 1997,master,is a member of CCF(No.I2375G).His main research interests include natural language processing and sentiment analysis.
    ZHAO Chunlei,born in 1979,Ph.D,is a member of CCF(No.18494M).Her main research interests include natural language processing and network information security.
  • Supported by:
    Key Special Project of “Science and Technology Helps Economy 2020” of National Key R&D Program of China(SQ2020YFF0413781,SQ2020YFF0401503).

PDF (PC)

317

Abstract: The construction of a domain sentiment lexicon is the foundation of domain text sentiment analysis.The existing me-thods for constructing domain sentiment lexicon have problems such as high redundancy of selected candidate sentiment words,inaccurate judgment of sentiment polarity,and high domain dependency.In order to improve the domain specificity of selected candidate sentiment words and the accuracy of judging the polarity of domain sentiment words,a domain sentiment lexicon construction method based on improved term frequency-inverse document frequency(TF-IDF) and BERT is proposed.This method improves the TF-IDF algorithm in the phase of selecting domain candidate sentiment words.The latent dirichlet allocation(LDA) algorithm is combined with the improved TF-IDF algorithm to perform domain corrections,improves the domain specificity of the selected candidate sentiment words.In the polarity judgment stage of candidate sentiment words,the semantic orientation pointwise mutual information(SO-PMI) algorithm is combined with BERT.By fine-tuning the BERT classification model using domain sentiment words,the accuracy of judging the sentiment polarity of domain candidate sentiment words is improved.Experiments are conducted on user comment datasets in different domains,and the experimental results show that this method can improve the quality of the constructed domain sentiment lexicon,and the F1 value of the domain sentiment lexicon constructed by this method for text sentiment analysis in the automotive field and mobile phone field reaches 78.02% and 88.35%,respectively.

Key words: Sentiment analysis, Domain sentiment lexicon, Term Frequency-Inverse Document Frequency(TF-IDF), Latent Dirichlet allocation(LDA), Semantic orientation pointwise mutual information(SO-PMI), BERT model

CLC Number: 

  • TP391.1
[1]ZHAO Y Y,QIN B,LIU T,et al.Sentiment Analysis[J].Journal of Software,2010,21(8):1834-1848.
[2]ZHAO Y Y,QIN B,SHI Q H,et al.Large-scale Sentiment Le-xicon Collection and Its Application in Sentiment Classification[J].Journal of Chinese Information Processing,2017,31(2):187-193.
[3]DAI L,LIU B,XIA Y,et al.Measuring Semantic Similarity between Words Using HowNet[C]//2008 International Confe-rence on Computer Science and Information Technology,Los Alamitos,USA:IEEE Computer Society,2008:601-605.
[4]LI J,SUN M.Experimental Study on Sentiment Classification ofChinese Review using Machine Learning Techniques[C]//2007 International Conference on Natural Language Processing and Knowledge Engineering.Piscataway,USA:IEEE,2007:393-400.
[5]KU L,CHEN H.Mining opinions from the Web:Beyond relevance retrieval[J].Journal of the American Society for Information Science and Technology,2007,58(12):1838-1850.
[6]ZHAI Y,WANG Z,ZENG H,et al.Social Media Opinion Lea-der Identification Based on Sentiment Analysis[C]//Proceedings of the 2021 International Conference on Bioinformatics and Intelligent Computing.New York,USA:Association for Computing Machinery,2021:436-440.
[7]PARK S,LEE W,MOON I.Efficient extraction of domain specific sentiment lexicon with active learning[J].Pattern Recognition Letters,2015,56(apr.15):38-44.
[8]WANG K,XIA R.A Survey on Automatical ConstructionMethods of Sentiment Lexicons[J].Acta Automatica Sinica,2016,42(4):495-511.
[9]NEVIAROUSKAYA A,PRENDINGER H,ISHIZUKA M.Senti-Ful:A Lexicon for Sentiment Analysis[J].IEEE Transactions on Affective Computing,2011,2(1):22-36.
[10]HASSAN A,ABUJBARA A,RADE V,et al.Identifying the Semantic Orientation of Foreign Words[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics.Stroudsburg,USA:Association for Computational Linguistics,2011:592-597.
[11]DRAGUT E C,WANG H,SISTLA P,et al.Polarity Consistency Checking for Domain Independent Sentiment Dictionaries[J].IEEE Transactions on Knowledge and Data Engineering,2015,27(3):838-851.
[12]ZHU Y L,MIN J,ZHOU Y Q,et al.Semantic Orientation Computing Based on HowNet[J].Journal of Chinese Information Processing,2006,20(1):14-20.
[13]BOLLEGALA D,WEIR D,CARROLL J.Using MultipleSources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classification[C]//Meeting of the Association for Computational Linguistics:Human Language Technologies.USA:Association for Computational Linguistics,2011:132-141.
[14]KRESTEL R,SIERSDORFER S.Generating contextualizedsentiment lexica based on latent topics and user ratings[C]//Proceedings of the 24th ACM Conference on Hypertext and Social Media.New York,USA:ACM,2013:129-138.
[15]DENG D,JING L,YU J,et al.Sentiment Lexicon Construction With Hierarchical Supervision Topic Model[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2019,27(4):704-718.
[16]WANG Y,YIN F,LIU J,et al.Automatic construction of domain sentiment lexicon for semantic disambiguation[J].Multimedia tools and applications,2020,79(31/32):22355-22373.
[17]ZHAO C,ZHANG P,LIU J,et al.Research on Domain Emotion Dictionary Construction Method based on Improved SO-PMI Algorithm[C]//2021 5th International Conference on Natural Language Processing and Information Retrieval(NLPIR).New York,USA:Association for Computing Machinery,2021:18-23.
[18]WANG Y,HUANG G,LI M,et al.Automatically Constructing a Fine-Grained Sentiment Lexicon for Sentiment Analysis[J].Cognitive Computation,2022,15(1):254-271.
[19]REN W,ZHANG H W,CHEN M.A Method of Domain Dictionary Construction for Electric Vehicles Disassembly[J].Entropy.2022,24(3):363.
[20]HUANG S,NIU Z,SHI C.Automatic construction of domain-specific sentiment lexicon based on constrained label propagation[J].Knowledge-Based Systems,2014,56(jan.):191-200.
[21]XI Y H.Construction of Domain-specific Sentiment Lexicon in Product Reviews[J].Journal of Chinese Information Proces-sing,2016,30(5):136-144.
[22]LI C,YAN X,XU G,et al.Khmer Sentiment Lexicon Based on PU Learning and Label Propagation Algorithm[J].ACM Tran-sactions on Asian and Low-Resource Language Information Processing,2023,22(3):1-18.
[23]YANG X P,ZHANG Z X,WANG L,et al.Automatic Construction and Optimization of Sentiment Lexicon Based on Word2Vec[J].Computer Science,2017,44(1):42-47.
[24]ZHANG P,WANG J X,WANG Y H.Sentiment Lexicon Construction Method Based on Label Propagation[J].Computer Engineering,2018,44(5):168-173.
[25]YANG S Q,XU C J.Research on Constructing Sentiment Dictionary of Online Course Reviews based on Multi-source Combination[C]//Proceedings of the 2019 2nd International Confe-rence on Data Science and Information Technology.New York,USA:ACM,2019:71-76.
[26]YE X,CAO J B,XU FEI X,et al.Sentiment dictionary adaptive learning method in Chinese domain[J].Computer Engineering and Design,2020,41(8):2231-2237.
[27]LIU H,CHEN X,LIU X.A Study of the Application of Weight Distributing Method Combining Sentiment Dictionary and TF-IDF for Text Sentiment Analysis[J].IEEE Access,2022,10:32280-32289.
[28]BLEI D M,NG A Y,JORDAN M I.Latent Dirichlet Allocation[J].Journal of Machine Learning Research,2003,3:993-1022.
[29]DEVLIN J,CHANG M,LEE K,et al.BERT:Pre-training ofDeep Bidirectional Transformers for Language Understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg,USA:Association for Computational Linguistics,2019:4171-4186.
[1] YANG Junzhe, SONG Ying, CHEN Yifei. Text Emotional Analysis Model Fusing Theme Characteristics [J]. Computer Science, 2024, 51(6A): 230600111-8.
[2] ZHANG Haoyan, DUAN Liguo, WANG Qinchen, GAO Hao. Long Text Multi-entity Sentiment Analysis Based on Multi-task Joint Training [J]. Computer Science, 2024, 51(6): 309-316.
[3] ZHANG Zebao, YU Hannan, WANG Yong, PAN Haiwei. Combining Syntactic Enhancement with Graph Attention Networks for Aspect-based Sentiment Classification [J]. Computer Science, 2024, 51(5): 200-207.
[4] ZHENG Cheng, SHI Jingwei, WEI Suhua, CHENG Jiaming. Dual Feature Adaptive Fusion Network Based on Dependency Type Pruning for Aspect-basedSentiment Analysis [J]. Computer Science, 2024, 51(3): 205-213.
[5] LIU Yingying, YANG Qiuhui, YAO Bangguo, LIU Qiaoyun. Study on REST API Test Case Generation Method Based on Dependency Model [J]. Computer Science, 2023, 50(9): 101-107.
[6] LI Yang, WANG Shi, ZHU Junwu, LIANG Mingxuan, GAO Xiang, JIAO Zhixiang. Summarization of Aspect-level Sentiment Analysis [J]. Computer Science, 2023, 50(6A): 220400077-7.
[7] LI Yang, TANG Jiqiang, ZHU Junwu, LIANG Mingxuan, GAO Xiang. Aspect-based Sentiment Analysis Based on Prompt and Knowledge Enhancement [J]. Computer Science, 2023, 50(6A): 220300279-7.
[8] FU Yue, SHI We. Study on Satire Detection Based on Sentiment-Topic-Satire Hybrid Model [J]. Computer Science, 2023, 50(6A): 220300018-6.
[9] YANG Ying, ZHANG Fan, LI Tianrui. Aspect-based Sentiment Analysis Based on Dual-channel Graph Convolutional Network with Sentiment Knowledge [J]. Computer Science, 2023, 50(5): 230-237.
[10] ZHANG Xue, ZHAO Hui. Sentiment Analysis Based on Multi-event Semantic Enhancement [J]. Computer Science, 2023, 50(5): 238-247.
[11] WANG Lin, MENG Zuqiang, YANG Lina. Chinese Sentiment Analysis Based on CNN-BiLSTM Model of Multi-level and Multi-scale Feature Extraction [J]. Computer Science, 2023, 50(5): 248-254.
[12] LUO Liang, CHENG Chunling, LIU Qian, GUI Yaocheng. Answer Selection Model Based on MLP and Semantic Matrix [J]. Computer Science, 2023, 50(5): 270-276.
[13] WANG Yali, ZHANG Fan, YU Zeng, LI Tianrui. Aspect-level Sentiment Classification Based on Interactive Attention and Graph Convolutional Network [J]. Computer Science, 2023, 50(4): 196-203.
[14] CHEN Zhen, PU Yuanyuan, ZHAO Zhengpeng, XU Dan, QIAN Wenhua. Multimodal Sentiment Analysis Based on Adaptive Gated Information Fusion [J]. Computer Science, 2023, 50(3): 298-306.
[15] LI Shuai, XU Bin, HAN Yike, LIAO Tongxin. SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement [J]. Computer Science, 2023, 50(3): 3-11.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.