计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220300018-6.doi: 10.11896/jsjkx.220300018
付月1, 史伟2
FU Yue1, SHI We2
摘要： 讽刺检测是观点挖掘的一个子任务,主要目的是识别用户在书面文本中表达的观点或情感。文本中讽刺句往往具有混合的情感极性,正确识别讽刺句和非讽刺句在情感分析中起着至关重要的作用。讽刺检测方法一般都采用机器学习分类器,其中分类器的训练主要基于简单的词汇或基于词典的特征。本研究的目的是建立一个无监督的概率关系模型,根据微博中词语的情感分布来识别讽刺主题。模型基于主题级分布估计相关情感,评估出现在短文本中的情感相关词,给出情感相关标签。实验结果表明,该模型在讽刺检测方面优于其他最新的基线模型,非常适合于短文本的讽刺预测。
中图分类号:
| [1]BOUAZIZI M,OHTSUKI T.Sarcasm Detection in Twitter:“All products are Incredibly amazing !!!”-Are they really?[C]//IEEE Global Communications Conference.Keio University,Japan,2014. [2]CHUN-CHE P,MOHAMMAD L,JAN W P.Detecting sarcasm in text:an obvious solution to a trivial problem[R].Stanford CS 229 Machine Learning,2015. [3]ASHRAF K,MUHAMMAD A.CATBiGRU:Convolution andAttention with BiDirectional Gated Recurrent Unit for SelfDeprecating Sarcasm Detection[J].Cognitive Computation,2021,1:78-97. [4]RAJADESINGAN R,ZAFARANI H L.Sarcasm detection onTwitter:a behavioural modelling approach[C]//Proceedings of 18th ACM International Conference on Web Search Data Mining.2015:9-106. [5]YOGESH K,NIKITA G.AI-Based Learning Techniques forSarcasm Detection of Social Media Tweets:State-of-the-Art Survey[J].SN Computer Science,2020,1(318):20-34. [6]ZHANG Q L,DU J C,XU R F.Sarcasm Detection Based on Adversarial Learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2019,55(1):29-36. [7]HAN H,ZHAO Q T,SUN T Y,et al.Contextual Sarcasm Detection Model for Social Media Comments[J].Computer Engineering,2021,47(1):66-71. [8]VALDIVIA A,MARTÍNEZ-CÁMARA E,CHATURVEDI I,et al.What do people think about this monument? Understanding negative reviews via deep learning,clustering and descriptive rules[J].J Ambient Intell Human Comput,2020,11:39-52. [9]JOSHI A,VAIBHAV T,PUSHPAK B,et al.Harnessing se-quence labeling for sarcasm detection in dialogue from tv series friends[C]//CoNLL.Berlin,Germany:ACL’s Special Interest Group on Natural Language Learning,2016:146-155. [10]SILVIO A B C,WALLACE H L,PAULA CARVALHO M J S.Modelling context with user embeddings for sarcasm detection in social media[C]//CoNLL.Berlin,Germany:ACL’s Special Interest Group on Natural Language Learning,2016:167-179. [11]WANG Z L,WU Z J,REN Y F,et al.Twitter sarcasm detection exploiting a context based model[C]//Web Information Systems Engineering-WISE.Springer,Miami,FL,USA,2015:77-91. [12]HERNANDEZ-FARIAS,BENED J,ROSSO P.Applying basic features from sentiment analysis for automatic irony detection[C]//Pattern Recognition and Image Analysis.Springer,USA,2015:337-344. [13]NIMALA K,JEBAKUMAR A.A robust user sentiment biterm topic mixture model based on user aggregation strategy to avoid data sparsity for short text[J].J Med Syst,2019,43(93):32-48. [14]RAJADESINGAN A,ZAFARANI R,LIU H.Sarcasm detection on twitter:a behavioral modeling approach[C]//Proceedings of the 8th ACM International Conference on Web Search and Data Mining.ACM Press,2015:97-106. [15]WEITZEL L,PRATI R C,AGUIAR R F.The comprehension of figurative language:what is the influence of irony and sarcasm on NLP techniques?[M]//Sentiment Analysis and Ontdogy Engineering.New York:Springer,2016:49-74. [16]XIONG T,ZHANG P,ZHU H,et al.Sarcasm Detection withSelf-matching Networks and Low-rank Bilinear Pooling[C]//Proceeding of WWW ’19.Raleigh North Carolina,USA:ACM,2019:2115-2124. [17]SHI W,WANG H W,HE S Y.Study on construction of fuzzy Emotion ontology Based on HowNet[J]. Journal of the China Society for Scientific and Technical Information,2012(6):595-602. [18]HowNet[OL].http://www.keenage.com. |
|
||
首页