微博情感分析综述

摘要/Abstract

摘要： 随着微博用户数量的快速增长，微博中所携带的一些情感和观点对社会的影响越来越大，尤其是一些涉及到公众人身安全的负面情绪，可能会影响到社会的稳定，因此进行微博情感分析意义重大。微博情感分析的内容包括微博语料的获取、微博语料的预处理和情感分析方法等，常用的情感分析方法有基于情感词典的方法、基于机器学习的方法和基于深度学习的方法。随着注意力机制在NLP领域的广泛使用，很多研究者开始将注意力机制融合到深度学习模型中进行情感分析，这使得情感分析的准确率得到了很大的提升。谷歌提出的BERT模型本质上也是基于注意力机制实现的，BERT模型在情感分析领域取得了突破性的进展。

关键词: 微博舆论, 情感分析, 深度学习, 注意力机制, BERT

Abstract: With the rapid growth of the number of microblog users, some emotions and opinions carried in microblog have a growing impact on the society, especially some negative emotions related to the personal safety of the public, which may affect the stability of the society. Therefore, it is of great significance to analyze the sentiment of microblog. The content of microblog sentiment analysis includes the acquisition of microblog corpus, the preprocessing of microblog corpus and the methods of sentiment analysis. The commonly used sentiment analysis methods include the method based on emotion dictionary, the method based on machine learning, and the method based on depth learning. With the widespread use of attention mechanism in NLP field, many researchers began to integrate attention mechanism into deep learning model for sentiment analysis, which greatly improves the accuracy of sentiment analysis. The BERT model proposed by Google is also based on attention mechanism essentially, which has made a breakthrough in the field of sentiment analysis.

Key words: public opinion on microblog, sentiment analysis, deep learning, attention mechanism, BERT

王春东, 张卉, 莫秀良, 杨文军. 微博情感分析综述[J]. 计算机工程与科学, 2022, 44(01): 165-175.

WANG Chun-dong, ZHANG Hui, MO Xiu-liang, YANG Wen-jun. Overview on sentiment analysis of microblog[J]. Computer Engineering & Science, 2022, 44(01): 165-175.

参考文献［60］

［1］	Raviv R.A survey on opinion mining and sentiment analysis［J］.Knowledge-Based Systems,2015,89(C):14-46.
［2］	Chen Juan,Liu Yan-ping,Deng Sheng-li.An analysis on factors influencing the dissemination effect of rumor-refuting information［J］.Information Science,2018,36(1):91-95.(in Chinese)
［3］	Peng Xi-xian,Zhu Qing-hua,Liu Xuan.Research on behavior characteristics and classification of micro-blog users — Taking “Sina Micro-blog” as an example ［J］.Information Science,2015,33(1):69-75.(in Chinese)
［4］	Rao Hao,Chen Hai-mei.Application of Micro-blog public opinion prediction based on combination of principal component analysis and BP neural network ［J］.Journal of Modern Information,2016,36(7):58-62.(in Chinese)
［5］	Nasukawa T,Yi J.Sentiment analysis:Capturing favorability using natural language processing［C］∥Proc of the 2nd International Conference on Knowledge Capture,2003:70-77.
［6］	Lin L,Li J,Zhang R,et al.Opinion mining and sentiment analysis in social networks:A retweeting structure-aware approach［C］∥Proc of 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing,2014:890-895.
［7］	Pang B,Lee L,Vaithyanthan S.Thumbs up?:Sentiment classification using machine learning techniques ［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing,2002:79-86.
［8］	Ni X,Xue G R,Ling X,et al.Exploring in the weblog space by detecting informative and affective articles［C］∥Proc of International World Wide Web Conference,2007:281-290.
［9］	Ye Q,Zhang Z,Law R.Sentiment classification of online reviews to travel distinations by spervised machine learning approaches［J］.Expert Systems with Applications,2009,36(3):6527-6535.
［10］	Yang C,Lin K H,Chen H H.Emotion classification using web blog corpora［C］∥Proc of IEEE/WIC/ACM International Conference on Web Intelligence,2007:275-278.
［11］	Hofmann T.Probabilistic latent semantic analysis［C］∥Proc of the 15th Conference on Uncertainty in Artificial Intelligence,1999:289-296.
［12］	Blei D M,Ng A Y,Jordan M I.Latent Dirichlet allocation［J］.Journal of Machine Learning Research,2003,3:993-1022.
［13］	Tul Q,Ali M,Riaz A,et al.Sentiment analysis using deep learning techniques:A review［J］.International Journal of Advanced Computer Science and Applications,2017,8(6):1011-1026.
［14］	Wang P,Ji L,Yan J,et al.Concept and attention-based CNN for question retrieval in multi-view learning［J］.ACM Transactions on Intelligent Systems & Technology,2018,9(4):1-24.
［15］	Kim Y.Convolutional neural networks for sentence classification［C］∥Proc of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),2014:1746-1751.
［16］	Liu Long-fei,Yang Liang,Zhang Shao-wu,et al.Convolutional neural networks for Chinese Micro-blog sentiment analysis［J］.Journal of Chinese Information Processing,2015,29(6):159-165.(in Chinese)
［17］	Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need［C］∥Proc of the 31st International Conference on Neural Information Processing Systems,2017:6000-6010.
［18］	Devlin J,Chang M W,Lee K,et al.BERT:Pre-training of deep bidirectional transformers for language understanding［C］∥Proc of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2019:4171-4186.
［19］	Bevilacqua M,Navigl R. Quasi bidirectional encoder representations from transformers for word sense disambiguation［C］∥Proc of Recent Advances in Natural Language Processing,2019:122-131.
［20］	Aizawa A.An information-theoretic perspective of TF-IDF measures［J］.Information Processing & Management,2003,39(1):45-65.
［21］	Mikolov T,Chen K,Corrado G,et al.Efficient estimation of word representations in vector space ［J］.arXiv:1301.3781,2014.
［22］	Le Q,Mikolov T.Distributed representations of sentences and documents［C］∥Proc of the 31st International Confe- rence on Machine Learning, 2014:1188-1196.
［23］	Li Rui, Zhang Qian, Liu Jia-yong. Microblog sentiment analysis based on weighted word2vec［J］.Communications Technology,2017,50(3):502-506.(in Chinese)
［24］	Mnih V,Heess N,Graves A,et al.Recurrent models of visual attention［C］∥Proc of the 27th International Conference on Neural Information Processing Systems,2014:2204-2212.
［25］	Bahdanau D,Cho K,Bengio Y.Neural machine translation by jointly learning to align and translate［J］.arXiv:1409.0473,2014.
［26］	Luong M T,Pham H,Manning C D.Effective approaches to attention-based neural machine translation［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing,2015:1412-1421.
［27］	Xu K,Ba J,Kiros R,et al.Show,attend and tell:Neural image caption generation with visual attention［C］∥Proc of the International Conference on Machine Learning,2015:2048-2057.
［28］	Martins A F T,Astudillo R F.From softmax to sparsemax:A sparse model of attention and multi-label classification［C］∥Proc of the International Conference on Machine Learning,2016:1614-1623.
［29］	Kim Y,Denton C,Hoang L,et al.Structured attention networks［J］.arXiv:1702.00887,2017.
［30］	Seo M,Kembhavi A,Farhadi A,et al.Bi-directional attention flow for machine comprehension［J］.arXiv:1611.01603,2016.
［31］	Yang Z,Yang D,Dyer C,et al.Hierarchical attention networks for document classification［C］∥Proc of 2016 the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2016:1480-1489.
［32］	Cheng J, Dong L, Lapata M. Long short-term memory- networks for machine reading［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing,2016:551-561.
［33］	Song Y,Wang J,Jiang T,et al.Attentional encoder network for targeted sentiment classification［J］.arXiv:1902.09314,2019.
［34］	Li X,Bing L,Lam W,et al.Transformation networks for target-oriented sentiment classification［C］∥Proc of the 56th Annual Meeting of the Association for Computational Linguistics,2018:946-956.
［35］	Wang B, Lu W.Learning latent opinions for aspect-level sentiment classification［C］∥Proc of the 32nd AAAI Conference on Artificial Intelligence,2018:5537-5544.
［36］	Ma Ming.Research on rumor feature extraction and recognition algorithms on microblog［D］.Beijing:Beijing Jiaotong University,2019.(in Chinese)
［37］	Zheng H T,Kang B Y,Kim H G.An ontology-based approach to learnable focused crawling［J］.Information Sciences,2008,178(23):4512-4522.
［38］	Achsan H T Y,Wibowo W C.A fast distributed focused-web crawling［J］.Procedia Engineering,2014,41(8):1421-1429.
［39］	Sun Mao-song,Zuo Zheng-ping,Huang Chang-ning.An experimental study on dictionary mechanism for Chinese word segmentation［J］.Journal of Chinese Information Proces- sing,2000,14(1):1-6.(in Chinese)
［40］	Zhang Jing, Huang Dei-gen,Huang Kai-yu, et al.λ-active learning based microblog-oriented Chinese word segmentation［J］.Journal of Tsinghua University(Science and Technology),
20	18,58(3):260-265.(in Chinese)
［41］	Sproat R, Shih C. A statistical method for finding word boundaries in Chinese text［J］.Computer Processing of Chinese and Oriental Languages,1990,4(4):336-351.
［42］	Low J K,Ng H T,Guo W.A maximum entropy approach to Chinese word segmentation［C］∥Proc of the 4th SIGHAN Workshop on Chinese Language Processing,2005:161-164.
［43］	Berger A L,Pietra V J D,Pietra S A D.A maximum entropy approach to natural language processing［J］.Computational Linguistics,1996,22(1):39-71.
［44］	Rabiner L R.A tutorial on hidden Markov models and selected applications in speech recognition［J］.Proceedings of the IEEE,1989,77(2):257-286.
［45］	Peng F,Feng F,McCallum A.Chinese segmentation and new word detection using conditional random fields［C］∥Proc of the 20th International Conference on Computational Linguistics,2004:562-568.
［46］	Chen X,Qiu X,Zhu C,et al.Gated recursive neural network for Chinese word segmentation［C］∥Proc of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing,2015:1744-1753.
［47］	Cai D,Zhao H.Neural word segmentation learning for Chinese［C］∥Proc of the 54th Annual Meeting of the Association for Computational Linguistics,2016:409-420.
［48］	Turney P D,Littman M L.Measuring praise and criticism:Inference of semantic orientation from association［J］.ACM Transactions on Information Systems,2003,21(4):315-346.
［49］	Taboada M, Brooke J, Tofiloski M,et al.Lexicon-based methods for sentiment analysis［J］.Computational Lingustics,2011,37(2):267-307.
［50］	Dong Z D,Dong Q.HowNet—A hybrid language and know- ledge resource［C］∥Proc of International Conference on Natural Language Processing and Knowledge Engineering,2003:820-824.
［51］	Ku L W,Lo Y S,Chen H H.Using polarity scores of words for sentence-level opinion extraction［C］∥Proc of NTCIR-6 Workshop Meeting,2007:316-322.
［52］	Xu Lin-hong,Lin Hong-fei,Pan Yu,et al.Constructing the affective lexicon ontology［J］.Journal of the China Society for Scientific and Technical Information,2008,27(2):180-185.(in Chinese)
［53］	Yao Tian-fang,Lou De-cheng.Research on semantic orientation analysis for topics in Chinese sentences［J］.Journal of Chinese Information Processing,2007,27(5):73-79.(in Chinese)
［54］	Bravo-Marquez F,Frank E,Pfahringer B.Positive,negative,or neutral:Learning an expanded opinion lexicon from emoticon-annotated tweets［C］∥Proc of the 23rd International Joint Conference on Artificial Intelligence,2015:1229-1235.
［55］	Li M,Lu Q,Long Y,et al.Inferring affective meanings of words from word embedding［J］.IEEE Transactions on Affective Computing,2017,8(4):443-456.
［56］	Cambria E.Affective computing and sentiment analysis［J］.IEEE Intelligent Systems,2016,31(2):102-107.
［57］	Zhao J,Dong L,Wu J,et al.Moodlens:An emotion-based sentiment analysis system for Chinese tweets［C］∥Proc of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2012:1528-1531.
［58］	Yan X,Guo J,Lan Y,et al.A biterm topic model for short texts［C］∥Proc of the 22nd International Conference on World Wide Web,2013:1445-1456.
［59］	Zhao J, Liu K,Wang G.Adding redundant features for CRFs-based sentence sentiment classification［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing,2008:117-126.
［60］	Li Shou-shan,Huang Ju-ren.Chinese sentiment classification based on Stacking combination method［J］.Journal of Chinese Information Processing,2010,24(5):56-61.(in Chinese)
［61］	Bengio Y,Simard P,Frasconi P.Learning long-term depen- dencies with gradient descent is difficult［J］.IEEE Transactions on Neural Networks,1994,5(2):157-166.
［62］	Schuster M,Paliwal K K.Bidirectional recurrent neural networks［J］.IEEE Transactions on Signal Processing,1997,45(11):2673-2681.
［63］	Hochreiter S,Schmidhuber J.Long short-term memory［J］.Neural Computation,1997,9(8):1735-1780.
［64］	Tang D,Qin B,Liu T.Document modeling with gated recurrent neural network for sentiment classification［C］∥Proc of the 2015 Conference on Empirical Methods in Natural Language Processing,2015:1422-1432.
［65］	Eyben F,Bock S,Schuller B,et al.Universal onset detection with bidirectional long short-term memory neural networks［C］∥Proc of the 11th International Society for Music Information Retrieval Conference,2010:589-594.
［66］	Palanisamy P, Vineet Y,Harsha E.Serendio:Simple and practical lexicon based approach to sentiment analysis［C］∥Proc of Joint Conference on Lexical and Computational Semantics,2013:543-548.
［67］	Arras L,Montavon G,Müller K,et al.Explaining recurrent neural network predictions in sentiment analysis［C］∥Proc of the 8th Workshop on Computational Approaches to Subjectivity,Sentiment and Social Media Analysis,2017:159-168.
［68］	Lin Z, Feng M, Santos C N D, et al. A structured self- attentive sentence embedding［J］.arXiv:1703.03130,2017.
［69］	Biesialska K,Biesialska M,Rybinski H.Sentiment analysis with contextual embeddings and self-attention［EB/OL］.［2020-03-12］.https://arxiv.org/abs/2003.05574.
［70］	Long F,Zhou K,Ou W.Sentiment analysis of text based on bidirectional LSTM with multi-head attention［J］.IEEE Access,2019,7:141960-141969.
［71］	Liu W,Cao G,Yin J.Bi-level attention model for sentiment analysis of short texts［J］.IEEE Access,2019,7:119813-119822.
［72］	Meng W,Wei Y,Liu P,et al.Aspect based sentiment analysis with feature enhanced attention CNN-BiLSTM［J］.IEEE Access,2019,7:167240-167249.
［73］	Rida-E-Fatima S, Javed A, Banjar A, et al.A multi-layer dual attention deep learning model with refined word embeddings for aspect-based sentiment analysis［J］.IEEE Access,2019,7:114795-114807.
［74］	Wang X,Xu G,Zhang J,et al.Syntax-directed hybrid attention network for aspect-level sentiment analysis［J］.IEEE Access,2019,7:5014-5025.
［75］	Li D,Rzepka R,Ptaszynski M,et al.Emoji-aware attention-based bi-directional GRU network model for Chinese sentiment analysis［C］∥Proc of IJCAI Workshop on Linguistic
	and Cognitive Approaches to Dialog Agents Workshop(LACATODA 2019),2019:11-18.
［76］	Li L,Liu Y,Zhou A.Hierarchical attention based position- aware network for aspect-level sentiment analysis［C］∥Proc of the 22nd Conference on Computational Natural Language Learning,2018:181-189.
［77］	Li X,Bing L D,Zhang W X,et al.Exploiting BERT for end-to-end aspect-based sentiment analysis［J］.arXiv:1910.00883,2019.
［78］	Liu Y,Ott M,Goyal N,et al.RoBERTa:A robustly optimized BERT pretraining approach［J］.arXiv:1907.11692,2019.
［79］	Zhao L,Li L,Zheng X.A BERT based sentiment analysis and key entity detection approach for online financial texts［J］.arXiv:2001.05326,2020.
［80］	Alaparthi S,Mishra M.Bidirectional encoder representations from transformers (BERT):A sentiment analysis odyssey［J］.arXiv:2007.01127,2020.
［81］	Yu J, Jiang J. Adapting BERT for target-oriented multi- modal sentiment classification［C］∥Proc of the 28th International Joint Conference on Artificial Intelligence,2019:5408-5414,2020.
［82］	Hoang M,Bihorac O A,Rouces J.Aspect-based sentiment analysis using BERT［C］∥Proc of the 22nd Nordic Confe- rence on Computational Linguistics,2019:187-196.
	附中文参考文献：
［2］	陈娟,刘燕平,邓胜利.政务微博辟谣信息传播效果的影响因素研究［J］.情报科学,2018,36(1):91-95.
［3］	彭希羡,朱庆华,刘璇.微博客用户特征分析及分类研究——以“新浪微博”为例［J］.情报科学,2015,33(1):69-75.
［4］	饶浩,陈海媚.主成分分析与BP神经网络在微博舆情预判中的应用［J］.现代情报,2016,36(7):58-62.
［16］	刘龙飞,杨亮,张绍武，等.基于卷积神经网络的微博情感倾向性分析［J］.中文信息学报,2015,29(6):159-165.
［23］	李锐,张倩,刘佳勇.基于加权word2vec的微博情感分析［J］．通信技术,2017,50(3):502-506.
［36］	马鸣.微博上谣言的特征提取及识别算法的研究［D］.北京：北京交通大学，2019.
［39］	孙茂松,左正平,黄昌宁.汉语自动分词词典机制的实验研究［J］.中文信息学报,2000,14(1):1-6.
［40］	张婧,黄德根,黄锴宇,等.基于λ-主动学习方法的中文微博分词［J］.清华大学学报(自然科学版),2018,58(3):260-265.
［52］	徐林宏,林鸿飞,潘宇,等.情感词汇本体的构造［J］.情报学报,2008,27(2):180-185.
［53］	姚天昉,娄德成.汉语语句主题语义倾向分析方法的研究［J］.中文信息学报,2007,27(5):73-79.
［60］	李寿山,黄居仁.基于Stacking组合分离方法的中文情感分类研究［J］.中文信息学报,2010,24(5):56-61.

[1]	马思远, 焦佳辉, 任晟岐, 宋伟. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(08): 1354-1364.
[2]	尹春勇, 冯梦雪. 基于注意力机制的半监督日志异常检测方法[J]. 计算机工程与科学, 2023, 45(08): 1405-1415.
[3]	余子丞, 凌捷. 基于Transformer和多特征融合的DGA域名检测方法[J]. 计算机工程与科学, 2023, 45(08): 1416-1423.
[4]	唐剑, 车文刚, 高盛祥. 融入注意力机制的多尺度卷积图像去雾方法[J]. 计算机工程与科学, 2023, 45(08): 1453-1462.
[5]	吴栋梁, 刘知贵, . 基于轻量化YOLOX的电子元器件缺陷检测方法研究[J]. 计算机工程与科学, 2023, 45(08): 1463-1471.
[6]	易啸, 马胜, 肖侬. 深度学习加速器在不同剪枝策略下的运行优化[J]. 计算机工程与科学, 2023, 45(07): 1141-1148.
[7]	康宇晗, 时洋, 陈照云, 文梅. 面向迈创+MatrixZone异构系统的深度学习编程框架[J]. 计算机工程与科学, 2023, 45(07): 1149-1158.
[8]	刘浩翰, 孙铖, 贺怀清, 惠康华. 基于改进YOLOv3的金属表面缺陷检测[J]. 计算机工程与科学, 2023, 45(07): 1226-1235.
[9]	白杉, 冯秀芳. 基于注意力增强的中心差分自适应图卷积的骨架行为识别[J]. 计算机工程与科学, 2023, 45(07): 1263-1273.
[10]	王剑, 姜林, 王琳钦, 余正涛, 张松, 高盛祥, . 基于BiLSTM的低资源老挝语文本正则化任务[J]. 计算机工程与科学, 2023, 45(07): 1292-1299.
[11]	田秀霞, 刘正, 刘秋旭, 李浩然. 一种改进Faster R-CNN的图像篡改检测模型[J]. 计算机工程与科学, 2023, 45(06): 1030-1039.
[12]	杨慧剑, 孟亮. 基于改进的YOLOv5的航拍图像中小目标检测算法[J]. 计算机工程与科学, 2023, 45(06): 1063-1070.
[13]	濮子俊, 张寿明. 基于特征融合与Transformer模型的声音事件定位与检测算法研究[J]. 计算机工程与科学, 2023, 45(06): 1097-1105.
[14]	许浪, 李代伟, 张海清, 唐聃, 何磊, 于曦. 基于神经网络的医疗文本分类研究[J]. 计算机工程与科学, 2023, 45(06): 1116-1122.
[15]	刘晓航, 姜晶菲, 许金伟. 基于脉动阵列的层融合注意力模型加速器结构[J]. 计算机工程与科学, 2023, 45(05): 802-809.