Combining Lexico-semantic Features for Emotion Classification in Suicide Notes

This paper describes a system for automatic emotion classification, developed for the 2011 i2b2 Natural Language Processing Challenge, Track 2. The objective of the shared task was to label suicide notes with 15 relevant emotions on the sentence level. Our system uses 15 SVM models (one for each emo...

Descripción completa

Detalles Bibliográficos
Autores principales: Desmet, Bart, Hoste, Véronique
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Libertas Academica 2012
Materias:
Original Research
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3409478/
https://www.ncbi.nlm.nih.gov/pubmed/22879768
http://dx.doi.org/10.4137/BII.S8960
_version_ 1782239591716093952
author Desmet, Bart
Hoste, Véronique
author_facet Desmet, Bart
Hoste, Véronique
author_sort Desmet, Bart
collection PubMed
description This paper describes a system for automatic emotion classification, developed for the 2011 i2b2 Natural Language Processing Challenge, Track 2. The objective of the shared task was to label suicide notes with 15 relevant emotions on the sentence level. Our system uses 15 SVM models (one for each emotion) using the combination of features that was found to perform best on a given emotion. Features included lemmas and trigram bag of words, and information from semantic resources such as WordNet, SentiWordNet and subjectivity clues. The best-performing system labeled 7 of the 15 emotions and achieved an F-score of 53.31% on the test data.
format Online
Article
Text
id pubmed-3409478
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher Libertas Academica
record_format MEDLINE/PubMed
spelling pubmed-34094782012-08-09 Combining Lexico-semantic Features for Emotion Classification in Suicide Notes Desmet, Bart Hoste, Véronique Biomed Inform Insights Original Research This paper describes a system for automatic emotion classification, developed for the 2011 i2b2 Natural Language Processing Challenge, Track 2. The objective of the shared task was to label suicide notes with 15 relevant emotions on the sentence level. Our system uses 15 SVM models (one for each emotion) using the combination of features that was found to perform best on a given emotion. Features included lemmas and trigram bag of words, and information from semantic resources such as WordNet, SentiWordNet and subjectivity clues. The best-performing system labeled 7 of the 15 emotions and achieved an F-score of 53.31% on the test data. Libertas Academica 2012-01-30 /pmc/articles/PMC3409478/ /pubmed/22879768 http://dx.doi.org/10.4137/BII.S8960 Text en © the author(s), publisher and licensee Libertas Academica Ltd. This is an open access article. Unrestricted non-commercial use is permitted provided the original work is properly cited.
spellingShingle Original Research
Desmet, Bart
Hoste, Véronique
Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title_full Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title_fullStr Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title_full_unstemmed Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title_short Combining Lexico-semantic Features for Emotion Classification in Suicide Notes
title_sort combining lexico-semantic features for emotion classification in suicide notes
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3409478/
https://www.ncbi.nlm.nih.gov/pubmed/22879768
http://dx.doi.org/10.4137/BII.S8960
work_keys_str_mv AT desmetbart combininglexicosemanticfeaturesforemotionclassificationinsuicidenotes
AT hosteveronique combininglexicosemanticfeaturesforemotionclassificationinsuicidenotes

Ejemplares similares