Ghent University Academic Bibliography

Advanced

Combining lexico-semantic features for emotion classification in suicide notes

Bart Desmet UGent and Veronique Hoste UGent (2012) BIOMEDICAL INFORMATICS INSIGHTS. 5(suppl. 1). p.125-128
abstract
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.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
emotion detection, suicidology, topic detection
journal title
BIOMEDICAL INFORMATICS INSIGHTS
Biomed. Inform. Insights
volume
5
issue
suppl. 1
pages
125 - 128
ISSN
1178-2226
DOI
10.4137/BII.S8960
language
English
UGent publication?
yes
classification
A2
copyright statement
I have retained and own the full copyright for this publication
VABB id
c:vabb:339641
VABB type
VABB-1
id
3029640
handle
http://hdl.handle.net/1854/LU-3029640
date created
2012-10-16 13:57:49
date last changed
2014-02-05 11:58:04
@article{3029640,
  abstract     = {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.},
  author       = {Desmet, Bart and Hoste, Veronique},
  issn         = {1178-2226},
  journal      = {BIOMEDICAL INFORMATICS INSIGHTS},
  keyword      = {emotion detection,suicidology,topic detection},
  language     = {eng},
  number       = {suppl. 1},
  pages        = {125--128},
  title        = {Combining lexico-semantic features for emotion classification in suicide notes},
  url          = {http://dx.doi.org/10.4137/BII.S8960},
  volume       = {5},
  year         = {2012},
}

Chicago
Desmet, Bart, and Veronique Hoste. 2012. “Combining Lexico-semantic Features for Emotion Classification in Suicide Notes.” Biomedical Informatics Insights 5 (suppl. 1): 125–128.
APA
Desmet, Bart, & Hoste, V. (2012). Combining lexico-semantic features for emotion classification in suicide notes. BIOMEDICAL INFORMATICS INSIGHTS, 5(suppl. 1), 125–128.
Vancouver
1.
Desmet B, Hoste V. Combining lexico-semantic features for emotion classification in suicide notes. BIOMEDICAL INFORMATICS INSIGHTS. 2012;5(suppl. 1):125–8.
MLA
Desmet, Bart, and Veronique Hoste. “Combining Lexico-semantic Features for Emotion Classification in Suicide Notes.” BIOMEDICAL INFORMATICS INSIGHTS 5.suppl. 1 (2012): 125–128. Print.