Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour

Xingyi Song; Johnny Downs; Sumithra Velupillai; Rachel Holden; Maxim  Kikoler; Kalina Bontcheva; Rina Dutta; Angus Roberts

Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour

Xingyi Song
, Johnny Downs
, Sumithra Velupillai
, Rachel Holden
, Maxim Kikoler
, Kalina Bontcheva
, Rina Dutta
, Angus Roberts

University of Sheffield
University of Canterbury, Southborough, UK.

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

128 Downloads (Pure)

Abstract

Identifying statements related to suicidal behaviour in psychiatric electronic health records (EHRs) is an important step when modeling that behaviour, and when assessing suicide risk. We apply a deep neural network based classification model with a lightweight context encoder, to classify sentence level suicidal behaviour in EHRs. We show that incorporating information from sentences to left and right of the target sentence significantly improves classification accuracy. Our approach achieved the best performance when classifying suicidal behaviour in Autism Spectrum Disorder patient records. The results could have implications for suicidality research and clinical surveillance.

Original language	English
Pages (from-to)	1303-1310
Number of pages	8
Journal	Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020)
Volume	1296–1303
Early online date	15 May 2020
Publication status	Published - 15 May 2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

Song X, Downs J, Velupillai S...Roberts A_LREC_2020Licence: CC BY

http://www.lrec-conf.org/proceedings/lrec2020/LREC-2020.pdfLicence: CC BY

Cite this

Song, X., Downs, J., Velupillai, S., Holden, R., Kikoler, M., Bontcheva, K., Dutta, R., & Roberts, A. (2020). Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour. Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020) , 1296–1303, 1303-1310. http://www.lrec-conf.org/proceedings/lrec2020/LREC-2020.pdf

@article{76bb24e9a0a24dc99799134bf6adaf0a,

title = "Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour",

abstract = "Identifying statements related to suicidal behaviour in psychiatric electronic health records (EHRs) is an important step when modeling that behaviour, and when assessing suicide risk. We apply a deep neural network based classification model with a lightweight context encoder, to classify sentence level suicidal behaviour in EHRs. We show that incorporating information from sentences to left and right of the target sentence significantly improves classification accuracy. Our approach achieved the best performance when classifying suicidal behaviour in Autism Spectrum Disorder patient records. The results could have implications for suicidality research and clinical surveillance.",

author = "Xingyi Song and Johnny Downs and Sumithra Velupillai and Rachel Holden and Maxim Kikoler and Kalina Bontcheva and Rina Dutta and Angus Roberts",

year = "2020",

month = may,

day = "15",

language = "English",

volume = "1296–1303",

pages = "1303--1310",

journal = "Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020) ",

publisher = "Unknown Publisher",

}

Song, X, Downs, J , Velupillai, S, Holden, R, Kikoler, M, Bontcheva, K, Dutta, R & Roberts, A 2020, 'Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour', Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020) , vol. 1296–1303, pp. 1303-1310. <http://www.lrec-conf.org/proceedings/lrec2020/LREC-2020.pdf>

Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour. / Song, Xingyi; Downs, Johnny ; Velupillai, Sumithra et al.
In: Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020) , Vol. 1296–1303, 15.05.2020, p. 1303-1310.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour

AU - Song, Xingyi

AU - Downs, Johnny

AU - Velupillai, Sumithra

AU - Holden, Rachel

AU - Kikoler, Maxim

AU - Bontcheva, Kalina

AU - Dutta, Rina

AU - Roberts, Angus

PY - 2020/5/15

Y1 - 2020/5/15

N2 - Identifying statements related to suicidal behaviour in psychiatric electronic health records (EHRs) is an important step when modeling that behaviour, and when assessing suicide risk. We apply a deep neural network based classification model with a lightweight context encoder, to classify sentence level suicidal behaviour in EHRs. We show that incorporating information from sentences to left and right of the target sentence significantly improves classification accuracy. Our approach achieved the best performance when classifying suicidal behaviour in Autism Spectrum Disorder patient records. The results could have implications for suicidality research and clinical surveillance.

AB - Identifying statements related to suicidal behaviour in psychiatric electronic health records (EHRs) is an important step when modeling that behaviour, and when assessing suicide risk. We apply a deep neural network based classification model with a lightweight context encoder, to classify sentence level suicidal behaviour in EHRs. We show that incorporating information from sentences to left and right of the target sentence significantly improves classification accuracy. Our approach achieved the best performance when classifying suicidal behaviour in Autism Spectrum Disorder patient records. The results could have implications for suicidality research and clinical surveillance.

UR - https://www.scopus.com/pages/publications/85096584439

M3 - Article

VL - 1296–1303

SP - 1303

EP - 1310

JO - Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020)

JF - Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020)

ER -

Using Deep Neural Networks with Intra- and Inter-Sentence Context to Classify Suicidal Behaviour

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this