NLG-based moderator response generator to support mental health

M. Sazzad Husain; Rafael A. Calvo; Louise Ellis; Juchen Li; Laura Ospina-Pinillos; Tracey Davenport; Ian Hickie

doi:10.1145/2702613.2732758

NLG-based moderator response generator to support mental health

M. Sazzad Husain, Rafael A. Calvo, Louise Ellis, Juchen Li, Laura Ospina-Pinillos, Tracey Davenport, Ian Hickie

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

3 Citations (Scopus)

Abstract

The global need to effectively address mental health problems and wellbeing is well recognised. Today, online systems are increasingly being viewed as an effective solution for their ability to reach broad populations. As online support groups become popular the workload for human moderators increases. Maintaining quality feedback becomes increasingly challenging as the community grows. Tools that can automatically detect mental health problems from social media posts and then generate smart feedback can greatly reduce human overload. In this paper, we present a system for the automation of interventions using Natural Language Generation (NLG) techniques. In particular, we focus on 'depression' and 'anxiety' related interventions. Psychologists evaluated the quality of the systems' interventions and results were compared against human (i.e. moderator) interventions. Results indicate our intervention system still has a long way to go, but is a step in the right direction as a tool to assist human moderators with their service. Copyright is held by the author/owner(s).

Original language	English
Title of host publication	CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings
Place of Publication	New York
Publisher	Association for Computing Machinery
Pages	1385-1390
Number of pages	6
Volume	18
ISBN (Electronic)	9781450331463
DOIs	https://doi.org/10.1145/2702613.2732758
Publication status	Published - 18 Apr 2015
Externally published	Yes
Event	33rd Annual CHI Conference on Human Factors in Computing Systems, CHI EA 2015 - Seoul, Korea, Republic of Duration: 18 Apr 2015 → 23 Apr 2015

Other

Other	33rd Annual CHI Conference on Human Factors in Computing Systems, CHI EA 2015
Country/Territory	Korea, Republic of
City	Seoul
Period	18/04/15 → 23/04/15

Access to Document

10.1145/2702613.2732758

Cite this

Husain, M. S., Calvo, R. A., Ellis, L., Li, J., Ospina-Pinillos, L., Davenport, T., & Hickie, I. (2015). NLG-based moderator response generator to support mental health. In CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings (Vol. 18, pp. 1385-1390). Association for Computing Machinery. https://doi.org/10.1145/2702613.2732758

@inproceedings{487aa0a74442405caab0bdbdc1e9ed23,

title = "NLG-based moderator response generator to support mental health",

abstract = "The global need to effectively address mental health problems and wellbeing is well recognised. Today, online systems are increasingly being viewed as an effective solution for their ability to reach broad populations. As online support groups become popular the workload for human moderators increases. Maintaining quality feedback becomes increasingly challenging as the community grows. Tools that can automatically detect mental health problems from social media posts and then generate smart feedback can greatly reduce human overload. In this paper, we present a system for the automation of interventions using Natural Language Generation (NLG) techniques. In particular, we focus on 'depression' and 'anxiety' related interventions. Psychologists evaluated the quality of the systems' interventions and results were compared against human (i.e. moderator) interventions. Results indicate our intervention system still has a long way to go, but is a step in the right direction as a tool to assist human moderators with their service. Copyright is held by the author/owner(s).",

author = "Husain, {M. Sazzad} and Calvo, {Rafael A.} and Louise Ellis and Juchen Li and Laura Ospina-Pinillos and Tracey Davenport and Ian Hickie",

year = "2015",

month = apr,

day = "18",

doi = "10.1145/2702613.2732758",

language = "English",

volume = "18",

pages = "1385--1390",

booktitle = "CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings",

publisher = "Association for Computing Machinery",

note = "33rd Annual CHI Conference on Human Factors in Computing Systems, CHI EA 2015 ; Conference date: 18-04-2015 Through 23-04-2015",

}

Husain, MS, Calvo, RA, Ellis, L, Li, J, Ospina-Pinillos, L, Davenport, T & Hickie, I 2015, NLG-based moderator response generator to support mental health. in CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings. vol. 18, Association for Computing Machinery, New York, pp. 1385-1390, 33rd Annual CHI Conference on Human Factors in Computing Systems, CHI EA 2015, Seoul, Korea, Republic of, 18/04/15. https://doi.org/10.1145/2702613.2732758

NLG-based moderator response generator to support mental health. / Husain, M. Sazzad; Calvo, Rafael A.; Ellis, Louise et al.
CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings. Vol. 18 New York: Association for Computing Machinery, 2015. p. 1385-1390.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - NLG-based moderator response generator to support mental health

AU - Husain, M. Sazzad

AU - Calvo, Rafael A.

AU - Ellis, Louise

AU - Li, Juchen

AU - Ospina-Pinillos, Laura

AU - Davenport, Tracey

AU - Hickie, Ian

PY - 2015/4/18

Y1 - 2015/4/18

N2 - The global need to effectively address mental health problems and wellbeing is well recognised. Today, online systems are increasingly being viewed as an effective solution for their ability to reach broad populations. As online support groups become popular the workload for human moderators increases. Maintaining quality feedback becomes increasingly challenging as the community grows. Tools that can automatically detect mental health problems from social media posts and then generate smart feedback can greatly reduce human overload. In this paper, we present a system for the automation of interventions using Natural Language Generation (NLG) techniques. In particular, we focus on 'depression' and 'anxiety' related interventions. Psychologists evaluated the quality of the systems' interventions and results were compared against human (i.e. moderator) interventions. Results indicate our intervention system still has a long way to go, but is a step in the right direction as a tool to assist human moderators with their service. Copyright is held by the author/owner(s).

AB - The global need to effectively address mental health problems and wellbeing is well recognised. Today, online systems are increasingly being viewed as an effective solution for their ability to reach broad populations. As online support groups become popular the workload for human moderators increases. Maintaining quality feedback becomes increasingly challenging as the community grows. Tools that can automatically detect mental health problems from social media posts and then generate smart feedback can greatly reduce human overload. In this paper, we present a system for the automation of interventions using Natural Language Generation (NLG) techniques. In particular, we focus on 'depression' and 'anxiety' related interventions. Psychologists evaluated the quality of the systems' interventions and results were compared against human (i.e. moderator) interventions. Results indicate our intervention system still has a long way to go, but is a step in the right direction as a tool to assist human moderators with their service. Copyright is held by the author/owner(s).

UR - http://www.scopus.com/inward/record.url?scp=84954232071&partnerID=8YFLogxK

U2 - 10.1145/2702613.2732758

DO - 10.1145/2702613.2732758

M3 - Conference proceeding contribution

AN - SCOPUS:84954232071

VL - 18

SP - 1385

EP - 1390

BT - CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings

PB - Association for Computing Machinery

CY - New York

T2 - 33rd Annual CHI Conference on Human Factors in Computing Systems, CHI EA 2015

Y2 - 18 April 2015 through 23 April 2015

ER -

Husain MS, Calvo RA, Ellis L, Li J, Ospina-Pinillos L, Davenport T et al. NLG-based moderator response generator to support mental health. In CHI 2015 - Extended Abstracts Publication of the 33rd Annual CHI Conference on Human Factors in Computing Systems: Crossings. Vol. 18. New York: Association for Computing Machinery. 2015. p. 1385-1390 doi: 10.1145/2702613.2732758

NLG-based moderator response generator to support mental health

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this