Evaluation of sentiment polarity prediction using a dimensional and a categorical approach

I. Muresan, A. Stan, M. Giurgiu, R. Potolea

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In this paper we evaluate two approaches for predicting the sentiment polarity of an utterance. The first method is based on a 3-dimensional model which takes into account text expressiveness in terms of valence, arousal and dominance. The second one determines the word's semantic orientation according to Chi-square and Relevance factor statistic metrics. We describe the general flow of the methods and their extracted features, as well as their predictability potential using different machine learning algorithms, Naïve Bayes, SVM and C4.5. The evaluation is performed on four emotional datasets: Semeval 2007 “Affective Text”, ISEAR (International Survey on Emotional Antecedents and Reactions), children's fairy-tales and a movie review dataset. The results show a high correlation of the prediction performance with the database content, as well as to the average number of words within the classified text instances.
Original languageEnglish
Title of host publicationSpeech Technology and Human - Computer Dialogue (SpeD), 2013 7th Conference on
Number of pages6
Publication statusPublished - 1 Oct 2013

Keywords / Materials (for Non-textual outputs)

  • Bayes methods
  • emotion recognition
  • feature extraction
  • learning (artificial intelligence)
  • pattern classification
  • statistical analysis
  • text analysis
  • C4.5
  • International Survey on Emotional Antecedents and Reactions
  • SVM
  • Semeval Affective Text
  • arousal
  • categorical approach
  • chi-square statistic metrics
  • children fairy-tales
  • database content
  • dimensional approach
  • dominance
  • emotional dataset
  • machine learning algorithm
  • movie review dataset
  • naive Bayes
  • predictability potential
  • relevance factor statistic metrics
  • sentiment polarity prediction
  • text expressiveness
  • text instance classification
  • utterance sentiment polarity
  • valence
  • word semantic orientation
  • Databases
  • Feature extraction
  • Measurement
  • Motion pictures
  • Numerical models
  • Semantics
  • Support vector machines
  • VAD model
  • sentiment polarity
  • statistic metrics


Dive into the research topics of 'Evaluation of sentiment polarity prediction using a dimensional and a categorical approach'. Together they form a unique fingerprint.

Cite this