Building Chinese Affective Resources in Valence-Arousal Dimensions

An increasing amount of research has recently focused on representing affective states as continuous numerical values on multiple dimensions, such as the valence-arousal (VA) space. Compared to the categorical approach that represents affective states as several classes (e.g., positive and negative), the dimensional approach can provide more finegrained sentiment analysis. However, affective resources with valence-arousal ratings are still very rare, especially for the Chinese language. Therefore, this study builds 1) an affective lexicon called Chinese valence-arousal words (CVAW) containing 1,653 words, and 2) an affective corpus called Chinese valencearousal text (CVAT) containing 2,009 sentences extracted from web texts. To improve the annotation quality, a corpus cleanup procedure is used to remove outlier ratings and improper texts. Experiments using CVAW words to predict the VA ratings of the CVAT corpus show results comparable to those obtained using English affective resources.

[1]  Shrikanth S. Narayanan,et al.  Distributional Semantic Models for Affective Text Analysis , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[2]  J. Russell.  A circumplex model of affect. , 1980 .

[3]  Preslav Nakov,et al.  SemEval-2015 Task 10: Sentiment Analysis in Twitter , 2015, *SEMEVAL.

[4]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[5]  Cindy K. Chung,et al.  The development of the Chinese linguistic inquiry and word count dictionary. , 2012 .

[6]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[7]  Hsin-Hsi Chen,et al.  Mining opinions from the Web: Beyond relevance retrieval , 2007, J. Assoc. Inf. Sci. Technol..

[8]  Rada Mihalcea,et al.  Porting Multilingual Subjectivity Resources across Languages , 2013, IEEE Transactions on Affective Computing.

[9]  D. Gokcay,et al.  Predicting the sentiment in sentences based on words: An exploratory study on ANEW and ANET , 2012, 2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom).

[10]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[11]  P. Lang.  Behavioral treatment and bio-behavioral assessment: computer applications , 1980 .

[12]  Kim Schouten,et al.  Survey on Aspect-Level Sentiment Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[13]  Haris Papageorgiou,et al.  SemEval-2016 Task 5: Aspect Based Sentiment Analysis , 2016, *SEMEVAL.

[14]  M. Bradley,et al.  Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings , 1999 .

[15]  Hanna Zijlstra,et al.  Validiteit van de Nederlandse versie van de Linguistic Inquiry and Word Count (liwc) , 2005 .

[16]  Chung-Hsien Wu,et al.  A Regression Approach to Affective Rating of Chinese Words from ANEW , 2011, ACII.

[17]  K. Robert Lai,et al.  Predicting Valence-Arousal Ratings of Words Using a Weighted Graph Method , 2015, ACL.

[18]  Harith Alani,et al.  Evaluation Datasets for Twitter Sentiment Analysis: A survey and a new dataset, the STS-Gold , 2013, ESSEM@AI*IA.

[19]  P. Ekman.  An argument for basic emotions , 1992 .

[20]  Claire Cardie,et al.  39. Opinion mining and sentiment analysis , 2014 .

[21]  Rafael A. Calvo,et al.  Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications , 2010, IEEE Transactions on Affective Computing.

[22]  Kam-Fai Wong,et al.  Cross lingual opinion holder extraction based on multi-kernel SVMs and transfer learning , 2013, World Wide Web.

[23]  Arvid Kappas,et al.  Predicting Emotional Responses to Long Informal Text , 2013, IEEE Transactions on Affective Computing.

[24]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[25]  Claire Cardie,et al.  Towards a General Rule for Identifying Deceptive Opinion Spam , 2014, ACL.

[26]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.