The University of Southampton
University of Southampton Institutional Repository

Cross-domain depression detection via harvesting social media

Cross-domain depression detection via harvesting social media
Cross-domain depression detection via harvesting social media

Depression detection is a significant issue for human well-being. In previous studies, online detection has proven effective in Twitter, enabling proactive care for depressed users. Owing to cultural differences, replicating the method to other social media platforms, such as Chinese Weibo, however, might lead to poor performance because of insufficient available labeled (self-reported depression) data for model training. In this paper, we study an interesting but challenging problem of enhancing detection in a certain target domain (e.g. Weibo) with ample Twitter data as the source domain. We first systematically analyze the depression-related feature patterns across domains and summarize two major detection challenges, namely isomerism and divergency. We further propose a cross-domain Deep Neural Network model with Feature Adaptive Transformation & Combination strategy (DNN-FATC) that transfers the relevant information across heterogeneous domains. Experiments demonstrate improved performance compared to existing heterogeneous transfer methods or training directly in the target domain (over 3.4% improvement in F1), indicating the potential of our model to enable depression detection via social media for more countries with different cultural settings.

Humans and AI, Personalization and User Modeling, Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications Machine Learning Applications, Machine Learning Applications, Humanities
1045-0823
1611-1617
International Joint Conferences on Artificial Intelligence
Shen, Tiancheng
c5ab6f9e-4c08-46fc-ad78-886263986178
Jia, Jia
c2078bda-2e64-47ca-9a63-2b40f1e1e52d
Shen, Guangyao
45904a2b-0909-4096-81ad-8696cb201b78
Feng, Fuli
1eab8a64-7541-4dc8-a52d-185520cd090b
He, Xiangnan
795ca97d-406e-4f73-96b9-c8713cb070cb
Luan, Huanbo
18395e2d-63bf-4d4a-b055-fc1c759202ca
Tang, Jie
69c44bae-b1fa-45eb-a01d-3ac5b00fa749
Tiropanis, Thanassis
d06654bd-5513-407b-9acd-6f9b9c5009d8
Chua, Tat Seng
4803e955-b3b1-4fc6-803d-192cbb1c127a
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Shen, Tiancheng
c5ab6f9e-4c08-46fc-ad78-886263986178
Jia, Jia
c2078bda-2e64-47ca-9a63-2b40f1e1e52d
Shen, Guangyao
45904a2b-0909-4096-81ad-8696cb201b78
Feng, Fuli
1eab8a64-7541-4dc8-a52d-185520cd090b
He, Xiangnan
795ca97d-406e-4f73-96b9-c8713cb070cb
Luan, Huanbo
18395e2d-63bf-4d4a-b055-fc1c759202ca
Tang, Jie
69c44bae-b1fa-45eb-a01d-3ac5b00fa749
Tiropanis, Thanassis
d06654bd-5513-407b-9acd-6f9b9c5009d8
Chua, Tat Seng
4803e955-b3b1-4fc6-803d-192cbb1c127a
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c

Shen, Tiancheng, Jia, Jia, Shen, Guangyao, Feng, Fuli, He, Xiangnan, Luan, Huanbo, Tang, Jie, Tiropanis, Thanassis, Chua, Tat Seng and Hall, Wendy (2018) Cross-domain depression detection via harvesting social media. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. vol. 2018-July, International Joint Conferences on Artificial Intelligence. pp. 1611-1617 . (doi:10.24963/ijcai.2018/223).

Record type: Conference or Workshop Item (Paper)

Abstract

Depression detection is a significant issue for human well-being. In previous studies, online detection has proven effective in Twitter, enabling proactive care for depressed users. Owing to cultural differences, replicating the method to other social media platforms, such as Chinese Weibo, however, might lead to poor performance because of insufficient available labeled (self-reported depression) data for model training. In this paper, we study an interesting but challenging problem of enhancing detection in a certain target domain (e.g. Weibo) with ample Twitter data as the source domain. We first systematically analyze the depression-related feature patterns across domains and summarize two major detection challenges, namely isomerism and divergency. We further propose a cross-domain Deep Neural Network model with Feature Adaptive Transformation & Combination strategy (DNN-FATC) that transfers the relevant information across heterogeneous domains. Experiments demonstrate improved performance compared to existing heterogeneous transfer methods or training directly in the target domain (over 3.4% improvement in F1), indicating the potential of our model to enable depression detection via social media for more countries with different cultural settings.

Text
IJCAI18 Shen et al depression detection - Accepted Manuscript
Download (816kB)

More information

Accepted/In Press date: 13 July 2018
e-pub ahead of print date: July 2018
Published date: July 2018
Venue - Dates: International Joint Conference on Artificial Intelligence, , Stockholm, Sweden, 2018-07-13 - 2018-07-19
Keywords: Humans and AI, Personalization and User Modeling, Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications Machine Learning Applications, Machine Learning Applications, Humanities

Identifiers

Local EPrints ID: 423226
URI: http://eprints.soton.ac.uk/id/eprint/423226
ISSN: 1045-0823
PURE UUID: e46f1ccb-f525-40f3-ae1d-1458d1e19550
ORCID for Thanassis Tiropanis: ORCID iD orcid.org/0000-0002-6195-2852
ORCID for Wendy Hall: ORCID iD orcid.org/0000-0003-4327-7811

Catalogue record

Date deposited: 19 Sep 2018 16:30
Last modified: 18 Mar 2024 03:09

Export record

Altmetrics

Contributors

Author: Tiancheng Shen
Author: Jia Jia
Author: Guangyao Shen
Author: Fuli Feng
Author: Xiangnan He
Author: Huanbo Luan
Author: Jie Tang
Author: Thanassis Tiropanis ORCID iD
Author: Tat Seng Chua
Author: Wendy Hall ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×