面向散文的低频情感词语抽取与情绪标签确定
|
摘要
文章提出了一种基于随机游走模型,用于抽取散文体裁情感词语的方法。首先利用一般词典确定种子集词语,然后通过词语之间的共现关系确定词语间的相关性,再利用Word2Vec计算词语间的语义相似度,在此基础上构建随机游走图,用于确定候选词语的情绪标签。通过实验表明,随机游走模型方法在散文体裁的低频情感词语抽取和情绪标签确定上取得了较好的效果。
This paper proposes a method based on random walk model to extract prose genres emotional words.First,the general dictionary is used to determine seed set words.Then the co-occurrence relationship between words is used to determine the relevance between words.Besides,Word2 Vec is used to calculate the semantic similarity between words.Therefore,a random walk map is constructed to determine the emotional label of the candidate words.The experimental results show that proposed method has achieved good results in extraction low-frequency emotional words and identification of emotion label in prose genre.
This paper proposes a method based on random walk model to extract prose genres emotional words.First,the general dictionary is used to determine seed set words.Then the co-occurrence relationship between words is used to determine the relevance between words.Besides,Word2 Vec is used to calculate the semantic similarity between words.Therefore,a random walk map is constructed to determine the emotional label of the candidate words.The experimental results show that proposed method has achieved good results in extraction low-frequency emotional words and identification of emotion label in prose genre.
引文
[1]Park S,Lee W,Moon I C.Efficient Extraction of Domain Specific Sentiment Lexicon with Active Learning[J].Pattern Recognition Letters,2015,56(C):38-44.DOI:10.1016/j.patrec.2015.01.004.
[2]乔霈,王素格,陈鑫,等.基于词语关联的散文阅读理解问题答案获取方法[J].中文信息学报,2018,32(3):135-142.DOI:10.3969/j.issn.1003-0077.2018.03.017.Qiao P,Wang S G,Chen X,et al.Word Association Based Answer Acquisition for Reading Comprehension Questions from Prose[J].Journal of Chinese Information Processing,2018,32(3):135-142.DOI:10.3969/j.issn.1003-0077.2018.03.017.
[3]Rao D,Ravichandran D.Semi-supervised Polarity Lexicon Induction[C]∥proceedings of the 12th,Conference of the European Chapter of the Association for Computational Linguistics,2009,Athens,Greece.DBLP,2009:675-682.DOI:10.3115/1609067.1609142.
[4]张璞,王俊霞,王英豪.基于标签传播的情感词典构建方法[J].计算机工程,2018,44(5):168-173.DOI:10.19678/j.issn.1000-3428.0046862.Zhang P,Wang J X,Wang Y H.Sentiment Lexicon Construction Method Based on Label Propagation[J].Computer Engineering,2018,44(5):168-173.DOI:10.19678/j.issn.1000-3428.0046862.
[5]杨小平,张中夏,王良,等.基于Word2Vec的情感词典自动构建与优化[J].计算机科学,2017,44(01):42-47+74.DOI:10.11896/j.issn.1002-137X.2017.01.008.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(01):42-47+74.DOI:10.11896/j.issn.1002-137X.2017.01.008.
[6]Choi Y,Wiebe J.+/-EffectWordNet:Sense-level Lexicon Acquisition for Opinion Inference[C]∥Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,2014:1181-1191.DOI:10.3115/v1/D14-1125.
[7]Xu J,Xu R,Zheng Y,et al.Chinese Emotion Lexicon Developing Via Multi-lingual Lexical Resources Integration[C]∥Proceedings of the 14th International Conference on Computational Linguistics and Intelligent Text Processing,2013:174-182.DOI:10.1007/978-3-642-37256-8-15.
[8]Yang G,Baek S,Lee J,et al.Analyzing Enotion Words to Predict Severity of Software Bugs:A Case Study of Open Source Projects[C]∥Proceedings of the 2017 ACM Symposium on Applied Computing,2017:1280-1287.DOI:10.1145/3019612.3019788.
[9]Hamilton W L,Clark K,Leskovec J,et al.Inducing Domain-specific Sentiment Lexicons from Unlabeled Corpora[C]∥Proceedings of the 2016 Comferemceon Empirical Methods in Natural Language Processing,2016:595-605.DOI:10.18653/v1/D16-1057.
[10]Yu L C,Wu J L,Chang P C,et al.Using a Contextual Entropy Model to Expand Emotion Words and Their Intensity for the Sentiment Classification of Stock Market News[J].Knowledge-Based Systems,2013,41(1):89-97.DOI:10.1016/j.knosys.2013.01.001.
[11]Zhao Y,Qin B,Liu T.Creating a Fine-grained Corpus for Chinese Sentiment Analysis[J].IEEE Intelligent Systems,2014,30(1):36-43.DOI:10.1109/MIS.2014.33.
[12]Zhang Z,Singh M P.ReNew:A Semi-supervised Framework for Generating Domain-specific Lexicons and Sentiment A-nalysis[C]∥Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014:542-551.DOI:10.3115/v1/P14-1051.
[13]Yang M,Zhu D,Chow K P,et al.A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon[C]∥Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014:421-426.DOI:10.3115/v1/P14-2069.
[14]Wu F,Huang Y,Song Y,et al.Towards Building a High-quality Microblog-specific Chinese Sentiment Lexicon[J].Decision Support Systems,2016,87(C):39-49.DOI:10.1016/j.dss.2016.04.007.
[15]Song K,Feng S,Gao W,et al.Build Emotion Lexicon from Microblogs by Combining Effects of Seed Words and Emoticons in a Heterogeneous Graph[C]∥Proceedings of the 26th ACM Conference on Hypertext Social Media,2015:283-292.DOI:10.1145/2700171.2791035.
[16]Mohammad S M,Kiritchenko S.Using Hashtags to Capture Fine Emotion Categories from Tweets[J].Computational Intelligence,2015,31(2):301-326.DOI:10.1111/coin.12024.
[17]Abdaoui A,Aze J,Bringay S,et al.FEEL:a French Expanded Emotion Lexicon[J].Language Resources and Evaluation,2017,51(3):1-23.DOI:10.1007/s10579-016-9364-5.
[18]马秉楠,黄永峰,邓北星.基于表情符的社交网络情绪词典构造[J].计算机工程与设计,2016,37(5):1129-1133.DOI:10.16208/j.issn1000-7024.2016.05.003.Ma B N,Huang Y F,Deng B X.Generating Sentiment Lexicon of Online Social Network Based on Emotions[J].Computer Engineering and Design,2016,37(5):1129-1133.DOI:10.16208/j.issn1000-7024.2016.05.003.
[19]Lu Z,Ip H H S.Constrained Spectral Clustering Via Exhaustive and Efficient Constraint Propagation[C]∥Proceedings of the 11th European Conference on Computer Vision,2010:1-14.DOI:10.1007/978-3-642-15567-3-1.
[20]郑伟,王朝坤,刘璋,等.一种基于随机游走模型的多标签分类算法[J].计算机学报,2010,33(8):1418-1426.DOI:10.3724/SP.J.1016.2010.01418.Zheng W,Wang C K,Liu Z,et al.A Multi-label Classification Algorithm Based on Random Walk Model[J].Chinese Journal of Computers,2010,33(8):1418-1426.DOI:10.3724/SP.J.1016.2010.01418.
[21]徐琳宏,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.DOI:10.3969/j.issn.1000-0135.2008.02.004.Xu L H,Lin H F,P Y,et al.Constructing the Affective Lexicon Ontology[J].Journal of the China Society for Scientific and Technical Information,2008,27(2):180-185.DOI:10.3969/j.issn.1000-0135.2008.02.004.
[22]洪旭东,余正涛,严馨,等.基于标签传播算法的新词情感极性识别[J].计算机科学与探索,2015,9(12):1506-1512.DOI:10.3778/j.issn.1673-9418.1409023.Hong X D,Yu Z T,Yan X,et al.Emotional Polarity Recognition of New Words Based on Label Propagation Algorithm[J].Journal of Frontiers of Computer Science and Technology,2015,9(12):1506-1512.DOI:10.3778/j.issn.1673-9418.1409023.
[23]Kim Y.Convolutional Neural Networks for Sentence Classification[C]∥Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,2014:1746-1751.DOI:10.3115/v1/D14-1181.
[2]乔霈,王素格,陈鑫,等.基于词语关联的散文阅读理解问题答案获取方法[J].中文信息学报,2018,32(3):135-142.DOI:10.3969/j.issn.1003-0077.2018.03.017.Qiao P,Wang S G,Chen X,et al.Word Association Based Answer Acquisition for Reading Comprehension Questions from Prose[J].Journal of Chinese Information Processing,2018,32(3):135-142.DOI:10.3969/j.issn.1003-0077.2018.03.017.
[3]Rao D,Ravichandran D.Semi-supervised Polarity Lexicon Induction[C]∥proceedings of the 12th,Conference of the European Chapter of the Association for Computational Linguistics,2009,Athens,Greece.DBLP,2009:675-682.DOI:10.3115/1609067.1609142.
[4]张璞,王俊霞,王英豪.基于标签传播的情感词典构建方法[J].计算机工程,2018,44(5):168-173.DOI:10.19678/j.issn.1000-3428.0046862.Zhang P,Wang J X,Wang Y H.Sentiment Lexicon Construction Method Based on Label Propagation[J].Computer Engineering,2018,44(5):168-173.DOI:10.19678/j.issn.1000-3428.0046862.
[5]杨小平,张中夏,王良,等.基于Word2Vec的情感词典自动构建与优化[J].计算机科学,2017,44(01):42-47+74.DOI:10.11896/j.issn.1002-137X.2017.01.008.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(01):42-47+74.DOI:10.11896/j.issn.1002-137X.2017.01.008.
[6]Choi Y,Wiebe J.+/-EffectWordNet:Sense-level Lexicon Acquisition for Opinion Inference[C]∥Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,2014:1181-1191.DOI:10.3115/v1/D14-1125.
[7]Xu J,Xu R,Zheng Y,et al.Chinese Emotion Lexicon Developing Via Multi-lingual Lexical Resources Integration[C]∥Proceedings of the 14th International Conference on Computational Linguistics and Intelligent Text Processing,2013:174-182.DOI:10.1007/978-3-642-37256-8-15.
[8]Yang G,Baek S,Lee J,et al.Analyzing Enotion Words to Predict Severity of Software Bugs:A Case Study of Open Source Projects[C]∥Proceedings of the 2017 ACM Symposium on Applied Computing,2017:1280-1287.DOI:10.1145/3019612.3019788.
[9]Hamilton W L,Clark K,Leskovec J,et al.Inducing Domain-specific Sentiment Lexicons from Unlabeled Corpora[C]∥Proceedings of the 2016 Comferemceon Empirical Methods in Natural Language Processing,2016:595-605.DOI:10.18653/v1/D16-1057.
[10]Yu L C,Wu J L,Chang P C,et al.Using a Contextual Entropy Model to Expand Emotion Words and Their Intensity for the Sentiment Classification of Stock Market News[J].Knowledge-Based Systems,2013,41(1):89-97.DOI:10.1016/j.knosys.2013.01.001.
[11]Zhao Y,Qin B,Liu T.Creating a Fine-grained Corpus for Chinese Sentiment Analysis[J].IEEE Intelligent Systems,2014,30(1):36-43.DOI:10.1109/MIS.2014.33.
[12]Zhang Z,Singh M P.ReNew:A Semi-supervised Framework for Generating Domain-specific Lexicons and Sentiment A-nalysis[C]∥Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014:542-551.DOI:10.3115/v1/P14-1051.
[13]Yang M,Zhu D,Chow K P,et al.A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon[C]∥Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014:421-426.DOI:10.3115/v1/P14-2069.
[14]Wu F,Huang Y,Song Y,et al.Towards Building a High-quality Microblog-specific Chinese Sentiment Lexicon[J].Decision Support Systems,2016,87(C):39-49.DOI:10.1016/j.dss.2016.04.007.
[15]Song K,Feng S,Gao W,et al.Build Emotion Lexicon from Microblogs by Combining Effects of Seed Words and Emoticons in a Heterogeneous Graph[C]∥Proceedings of the 26th ACM Conference on Hypertext Social Media,2015:283-292.DOI:10.1145/2700171.2791035.
[16]Mohammad S M,Kiritchenko S.Using Hashtags to Capture Fine Emotion Categories from Tweets[J].Computational Intelligence,2015,31(2):301-326.DOI:10.1111/coin.12024.
[17]Abdaoui A,Aze J,Bringay S,et al.FEEL:a French Expanded Emotion Lexicon[J].Language Resources and Evaluation,2017,51(3):1-23.DOI:10.1007/s10579-016-9364-5.
[18]马秉楠,黄永峰,邓北星.基于表情符的社交网络情绪词典构造[J].计算机工程与设计,2016,37(5):1129-1133.DOI:10.16208/j.issn1000-7024.2016.05.003.Ma B N,Huang Y F,Deng B X.Generating Sentiment Lexicon of Online Social Network Based on Emotions[J].Computer Engineering and Design,2016,37(5):1129-1133.DOI:10.16208/j.issn1000-7024.2016.05.003.
[19]Lu Z,Ip H H S.Constrained Spectral Clustering Via Exhaustive and Efficient Constraint Propagation[C]∥Proceedings of the 11th European Conference on Computer Vision,2010:1-14.DOI:10.1007/978-3-642-15567-3-1.
[20]郑伟,王朝坤,刘璋,等.一种基于随机游走模型的多标签分类算法[J].计算机学报,2010,33(8):1418-1426.DOI:10.3724/SP.J.1016.2010.01418.Zheng W,Wang C K,Liu Z,et al.A Multi-label Classification Algorithm Based on Random Walk Model[J].Chinese Journal of Computers,2010,33(8):1418-1426.DOI:10.3724/SP.J.1016.2010.01418.
[21]徐琳宏,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.DOI:10.3969/j.issn.1000-0135.2008.02.004.Xu L H,Lin H F,P Y,et al.Constructing the Affective Lexicon Ontology[J].Journal of the China Society for Scientific and Technical Information,2008,27(2):180-185.DOI:10.3969/j.issn.1000-0135.2008.02.004.
[22]洪旭东,余正涛,严馨,等.基于标签传播算法的新词情感极性识别[J].计算机科学与探索,2015,9(12):1506-1512.DOI:10.3778/j.issn.1673-9418.1409023.Hong X D,Yu Z T,Yan X,et al.Emotional Polarity Recognition of New Words Based on Label Propagation Algorithm[J].Journal of Frontiers of Computer Science and Technology,2015,9(12):1506-1512.DOI:10.3778/j.issn.1673-9418.1409023.
[23]Kim Y.Convolutional Neural Networks for Sentence Classification[C]∥Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,2014:1746-1751.DOI:10.3115/v1/D14-1181.