Early fusion of low level features for emotion mining

Fabon Dzogang, Marie-Jeanne Lesot, Maria Rifqi, Bernadette Bouchon-Meunier

Research output: Contribution to journalArticle (Academic Journal)

Abstract

WE STUDY THE DISCRIMINATION OF EMOTIONS ANNOTATED IN FREE TEXTS AT THE SENTENCE LEVEL: a sentence can either be associated with no emotion (neutral) or multiple labels of emotion. The proposed system relies on three characteristics. We implement an early fusion of grams of increasing orders transposing an approach successfully employed in the related task of opinion mining. We apply a filtering process that consists in extracting frequent n-grams and making use of the Shannon's entropy measure to respectively maintain dictionaries at balanced sizes and keep emotion specific features. Finally the overall system is implemented as a 2-step decision process: a first classifier discriminates between neutral and emotion bearing sentences, then one classifier per emotion is applied on emotion bearing sentences. The final decision is given by the classifier holding the maximum confidence. Results obtained on the testing set are promising.

Original languageEnglish
Pages (from-to)129-36
Number of pages8
JournalBiomedical Informatics Insights
Volume5
Issue numberSuppl. 1
DOIs
Publication statusPublished - 2012

Fingerprint Dive into the research topics of 'Early fusion of low level features for emotion mining'. Together they form a unique fingerprint.

  • Cite this

    Dzogang, F., Lesot, M-J., Rifqi, M., & Bouchon-Meunier, B. (2012). Early fusion of low level features for emotion mining. Biomedical Informatics Insights, 5(Suppl. 1), 129-36. https://doi.org/10.4137/BII.S8973