CrystalFeel at SemEval-2018 Task 1: Understanding and Detecting Emotion Intensity using Affective Lexicons

While sentiment and emotion analysis has received a considerable amount of research attention, the notion of understanding and detecting the intensity of emotions is relatively less explored. This paper describes a system developed for predicting emotion intensity in tweets. Given a Twitter message, CrystalFeel uses features derived from parts-of-speech, n-grams, word embedding, and multiple affective lexicons including Opinion Lexicon, SentiStrength, AFFIN, NRC Emotion & Hash Emotion, and our in-house developed EI Lexicons to predict the degree of the intensity associated with fear, anger, sadness, and joy in the tweet. We found that including the affective lexicons-based features allowed the system to obtain strong prediction performance, while revealing interesting emotion word-level and message-level associations. On gold test data, CrystalFeel obtained Pearson correlations of 0.717 on average emotion intensity and of 0.816 on sentiment intensity.

[1]  Peter D. Turney,et al.  Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon , 2010, HLT-NAACL 2010.

[2]  A. Ortony,et al.  The psychological foundations of the affective lexicon. , 1987 .

[3]  Mike Thelwall,et al.  Sentiment strength detection for the social web , 2012, J. Assoc. Inf. Sci. Technol..

[4]  Brendan T. O'Connor,et al.  Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters , 2013, NAACL.

[5]  P. Shaver,et al.  Emotion knowledge: further exploration of a prototype approach. , 1987, Journal of personality and social psychology.

[6]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[7]  Cecilia Ovesdotter Alm,et al.  Emotions from Text: Machine Learning for Text-based Emotion Prediction , 2005, HLT.

[8]  J. M. Kittross.  The measurement of meaning , 1959 .

[9]  Saif Mohammad,et al.  Emotion Intensities in Tweets , 2017, *SEMEVAL.

[10]  Andrew Ortony,et al.  The complexity of intensity: Issues concerning the structure of emotion intensity , 1992 .

[11]  Saif Mohammad,et al.  Using Hashtags to Capture Fine Emotion Categories from Tweets , 2015, Comput. Intell..

[12]  Andrew Ortony,et al.  The Referential Structure of the Affective Lexicon , 1987, Cogn. Sci..

[13]  Saif Mohammad,et al.  SemEval-2018 Task 1: Affect in Tweets , 2018, *SEMEVAL.

[14]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[15]  Stan Szpakowicz,et al.  Identifying Expressions of Emotion in Text , 2007, TSD.

[16]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[17]  Xiaojun Wan,et al.  Emotion Classification in Microblog Texts Using Class Sequential Rules , 2014, AAAI.

[18]  M. Kreutzer,et al.  DARWIN and FACIAL EXPRESSION A CENTURY OF RESEARCH IN REVIEW , 2014 .

[19]  Raj Kumar Gupta,et al.  CrystalNest at SemEval-2017 Task 4: Using Sarcasm Detection for Enhancing Sentiment Classification and Quantification , 2017, *SEMEVAL.

[20]  Saif Mohammad,et al.  #Emotional Tweets , 2012, *SEMEVAL.

[21]  D. Robinson.  Brain function, emotional experience and personality , 2008 .

[22]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..