TY - GEN
T1 - Detecting and explaining crisis
AU - Kshirsagar, Rohan
AU - Morris, Robert
AU - Bowman, Samuel R.
N1 - Funding Information:
We thank the anonymous reviewers and Ka-reem Kouddous for their feedback. Bowman acknowledges support from a Google Faculty Research Award and gifts from Tencent Holdings and NVIDIA Corporation. We thank Koko for contributing a unique dataset for this research.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - Individuals on social media may reveal themselves to be in various states of crisis (e.g. suicide, self-harm, abuse, or eating disorders). Detecting crisis from social media text automatically and accurately can have profound consequences. However, detecting a general state of crisis without explaining why has limited applications. An explanation in this context is a coherent, concise subset of the text that rationalizes the crisis detection. We explore several methods to detect and explain crisis using a combination of neural and non-neural techniques. We evaluate these techniques on a unique data set obtained from Koko, an anonymous emotional support network available through various messaging applications. We annotate a small subset of the samples labeled with crisis with corresponding explanations. Our best technique significantly outperforms the baseline for detection and explanation.
AB - Individuals on social media may reveal themselves to be in various states of crisis (e.g. suicide, self-harm, abuse, or eating disorders). Detecting crisis from social media text automatically and accurately can have profound consequences. However, detecting a general state of crisis without explaining why has limited applications. An explanation in this context is a coherent, concise subset of the text that rationalizes the crisis detection. We explore several methods to detect and explain crisis using a combination of neural and non-neural techniques. We evaluate these techniques on a unique data set obtained from Koko, an anonymous emotional support network available through various messaging applications. We annotate a small subset of the samples labeled with crisis with corresponding explanations. Our best technique significantly outperforms the baseline for detection and explanation.
UR - http://www.scopus.com/inward/record.url?scp=85121315113&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121315113&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85121315113
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 66
EP - 73
BT - Proceedings of the 4th Workshop on Computational Linguistics and Clinical Psychology - From Linguistic Signal to Clinical Reality, CLPsych 2017 at the Annual Meeting of the Association for Computational Linguistics, ACL 2017
A2 - Hollingshead, Kristy
A2 - Ireland, Molly E.
A2 - Loveys, Kate
PB - Association for Computational Linguistics (ACL)
T2 - 4th Workshop on Computational Linguistics and Clinical Psychology - From Linguistic Signal to Clinical Reality, CLPsych 2017 at the Annual Meeting of the Association for Computational Linguistics, ACL 2017
Y2 - 3 August 2017
ER -