Multidimensional sentiment calculation method for Twitter based on emoticons

Purpose – The purpose of this paper is to propose a method of calculating the sentiment value of a tweet based on the emoticon role. Design/methodology/approach – Classification of emoticon roles as four types showing “emphasis”, “assuagement”, “conversion” and “addition”, with roles determined based on the respective relations to sentiment of sentences and emoticons. Findings – Clustering of users of four types based on emoticon sentiment. Originality/value – Formalization, using regression analysis, of the relation of sentiment between sentences and emoticons in all roles.

[1]  R. Plutchik.  The Multifactor-Analytic Theory of Emotion , 1960 .

[2]  T. Ikeda,et al.  Learning face marks for natural language dialogue systems , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[3]  David M. Pennock,et al.  Mining the peanut gallery: opinion extraction and semantic classification of product reviews , 2003, WWW '03.

[4]  Takashi Inui,et al.  Extracting Semantic Orientations of Words using Spin Model , 2005, ACL.

[5]  Toru Ishida,et al.  Semantics in Pictogram Communication , 2006 .

[6]  Yuji Matsumoto,et al.  Emotion Classification Using Massive Examples Extracted from the Web , 2008, COLING.

[7]  Jun Munemori,et al.  Analysis of Relationships between Smiley and Atmosphere during Chat with Emotional Characters , 2008, KES.

[8]  Tadahiko Kumamoto.  Design of Impression Scales for Assessing Impressions of News Articles , 2010, DASFAA Workshops.

[9]  Patrick Paroubek,et al.  Twitter as a Corpus for Sentiment Analysis and Opinion Mining , 2010, LREC.

[10]  Osamu Uchida,et al.  A method for automatically generating the emotional vectors of emoticons using weblog articles , 2011 .

[11]  Akiyo Nadamoto,et al.  Words-of-wisdom search based on multi-dimensional sentiment vector , 2011, iiWAS '11.

[12]  Katsumi Tanaka,et al.  Improving a Method for Quantifying Readers' Impressions of News Articles with a Regression Equation , 2011, WASSA@ACL.

[13]  P. Wilson,et al.  The Nature of Emotions , 2012 .

[14]  Ke Xu,et al.  MoodLens: an emoticon-based sentiment analysis system for chinese tweets , 2012, KDD.

[15]  Mitsunori Matsushita,et al.  Relationship between Emotional Words and Emoticons in Tweets , 2012, 2012 Conference on Technologies and Applications of Artificial Intelligence.

[16]  Kenji Araki,et al.  Emoticon recommendation system for effective communication , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[17]  Uzay Kaymak,et al.  Exploiting emoticons in sentiment analysis , 2013, SAC '13.

[18]  Aliza Sarlan,et al.  Twitter sentiment analysis , 2014, Proceedings of the 6th International Conference on Information Technology and Multimedia.