DARE to Care: A Context-Aware Framework to Track Suicidal Ideation on Social Media

Bilel Moulahi 1 Jérôme Azé 1 Sandra Bringay 1, 2
1 ADVANSE - ADVanced Analytics for data SciencE
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
2 UM3 - Université Paul-Valéry - Montpellier 3
Abstract : The abundance and growing usage of social media has given an unprecedented access to users' social accounts for studying people's thoughts and sentiments. In this work, we are interested in tracking in-dividual's emotional states and more specifically suicidal ideation in mi-croblogging services. We propose a probabilistic framework that models user's online activities as a sequence of psychological states over time and predicts the emotional states by incorporating the context history. Based on Conditional Random Fields, our model is able to provide comprehensive interpretations of the relationship between the risk factors and psychological states. We evaluated our approach within real case studies of Twitter' users that have demonstrated a serious change in their emotional states and online behaviour. Our experiments show that the model is able to identify suicidal ideation with high precision and good recall with substantial improvements on state-of-the-art methods.
Keywords : Context CRFs Emotional states Suicide Social Media
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01633312
Contributor : Bilel Moulahi <>
Submitted on : Sunday, November 12, 2017 - 12:44:53 PM
Last modification on : Thursday, June 6, 2019 - 2:47:58 PM
Long-term archiving on : Tuesday, February 13, 2018 - 12:33:41 PM

File

wise2017-preprint.pdf
Files produced by the author(s)

Identifiers

Collections

LIRMM | MIPS | UNIV-MONTPELLIER | UNIV-PARIS-SACLAY | ADVANSE | UNIV-MONTP3

Citation

Bilel Moulahi, Jérôme Azé, Sandra Bringay. DARE to Care: A Context-Aware Framework to Track Suicidal Ideation on Social Media. WISE: Web Information Systems Engineering, Oct 2017, Moscow, Russia. pp.346-353, ⟨10.1007/978-3-319-68786-5_28⟩. ⟨lirmm-01633312⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

643

Files downloads

496

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD