Assessing the Effectiveness of Affective Lexicons for Depression Classification

Noor Fazilla Abd Yusof, Chenghua Lin, Frank Guerin

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

1 Citation (Scopus)
11 Downloads (Pure)

Abstract

Affective lexicons have been commonly used as lexical features for depression classification, but their effectiveness is relatively unexplored in the literature. In this paper, we investigate the effectiveness of three popular affective lexicons in the task of depression classification. We also develop two lexical feature engineering strategies for incorporating those lexicons into a supervised classifier. The effectiveness of different lexicons and feature engineering strategies are evaluated on a depression dataset collected from LiveJournal.
Original languageEnglish
Title of host publicationNatural Language Processing and Information Systems
Subtitle of host publicationNLDB 2018
EditorsM Silberztein, F Atigui , E Kornyshova , E Métais , F Meziane
PublisherSpringer
Pages65-69
Number of pages5
ISBN (Electronic)978-3-319-91947-8
ISBN (Print)978-3-319-91946-1
Publication statusPublished - 22 May 2018
Event23rd International Conference on Natural Language & Information Systems - Conservatoire National des Arts et Métiers., Paris, France
Duration: 13 Jun 201815 Jun 2018

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10859
ISSN (Print)0302-9743

Conference

Conference23rd International Conference on Natural Language & Information Systems
Abbreviated titleNLDB
CountryFrance
CityParis
Period13/06/1815/06/18

    Fingerprint

Keywords

  • depression analysis
  • affective lexicon
  • language analysis

Cite this

Abd Yusof, N. F., Lin, C., & Guerin, F. (2018). Assessing the Effectiveness of Affective Lexicons for Depression Classification. In M. Silberztein, F. Atigui , E. Kornyshova , E. Métais , & F. Meziane (Eds.), Natural Language Processing and Information Systems: NLDB 2018 (pp. 65-69). (Lecture Notes in Computer Science; Vol. 10859). Springer .