Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk

Tianyu He; Yuyu Zheng; Jing Bai; Pan Chen; Yue Ma; Guanghui Fu; Shengxin Hu; Songhe Li; Zhisheng Huang; Qian Liu; Xiang Yang Bing

doi:10.1145/3500931.3501027

Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk

Tianyu He, Yuyu Zheng, Jing Bai, Pan Chen, Yue Ma, Guanghui Fu, Shengxin Hu, Songhe Li, Zhisheng Huang^*, Qian Liu, Xiang Yang Bing

^*Corresponding author for this work

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

Abstract

Background Suicide is a global public health and mental health problem. With the rapid development of internet technology, more and more people tend to express their suicidal tendencies and suicidal intentions online. The difference of emotional characteristics between high and low risk of suicide messages should be analyzed to help identify suicide risk and provide early intervention. Methods The "tree hole"intelligent robot captures message data, then randomly selects the same number of high and low suicide risk messages manually, and the high frequency keywords of high and low suicide risk messages are obtained by word segmentation and a TF-IDF algorithm. The keywords are analyzed by Gephi software, and the emotion dictionary provided by Boson is used to judge the emotional tendency of high and low suicide risk users. Results The emotional score of high suicide risk messages was -3.511 ∼ 2.514, averaging (-0.225±0.405), while the total score of low suicide risk messages was -4.547 ∼ 3.403, averaging (-0.121±0.628). Low suicide risk messages mainly focused on negative emotions, interpersonal relationships and social support, while high suicide risk messages mainly centered on invited suicide, means, locations and time of suicide. Conclusion There are differences in emotional characteristics between high and low suicide risk messages. The higher the suicide risk, the more obvious the negative tendency of the users' emotions. More attention is needed to the greater potential for suicide among this group of users and psychological support and interventions should be included.

Original language	English
Title of host publication	ISAIMS '21
Subtitle of host publication	Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences
Publisher	Association for Computing Machinery
Pages	562-567
Number of pages	6
ISBN (Electronic)	9781450395588
DOIs	https://doi.org/10.1145/3500931.3501027
Publication status	Published - Oct 2021
Event	2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021 - Virtual, Online, China Duration: 29 Oct 2021 → 31 Oct 2021

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021
Country/Territory	China
City	Virtual, Online
Period	29/10/21 → 31/10/21

Bibliographical note

Funding Information:
Sincere thanks are given to Sharon R. Redding (EdD, RN, CNE) for assistance in editing. Funding: This study is supported by the National Natural Science Foundation of China (No. 72174152), Wuhan university provincial college students' innovation and entrepreneurship training program (S2020305001, S202110486194, S202110486196) and Wuhan university 2019 school of medicine students' innovation and entrepreneurship training program (MS2019046).

Publisher Copyright:
© 2021 ACM.

Funding

Sincere thanks are given to Sharon R. Redding (EdD, RN, CNE) for assistance in editing. Funding: This study is supported by the National Natural Science Foundation of China (No. 72174152), Wuhan university provincial college students' innovation and entrepreneurship training program (S2020305001, S202110486194, S202110486196) and Wuhan university 2019 school of medicine students' innovation and entrepreneurship training program (MS2019046).

Funders	Funder number
Wuhan university provincial college students' innovation and entrepreneurship training program	MS2019046, S202110486196, S2020305001, S202110486194
National Natural Science Foundation of China	72174152
National Natural Science Foundation of China

Keywords

Artificial intelligence
Emotional characteristics analysis
Suicide risk
Weibo "tree hole"

UN SDGs

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

Access to Document

10.1145/3500931.3501027

Persistent URL (handle)

Persistent link

Cite this

He, T., Zheng, Y., Bai, J., Chen, P., Ma, Y., Fu, G., Hu, S., Li, S., Huang, Z., Liu, Q., & Bing, X. Y. (2021). Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk. In ISAIMS '21: Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences (pp. 562-567). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3500931.3501027

@inproceedings{45bfecd67b6948519baf055eb9a21d0a,

title = "Analysis of emotional characteristics of Weibo {"}tree hole{"} users with different suicide risk",

abstract = "Background Suicide is a global public health and mental health problem. With the rapid development of internet technology, more and more people tend to express their suicidal tendencies and suicidal intentions online. The difference of emotional characteristics between high and low risk of suicide messages should be analyzed to help identify suicide risk and provide early intervention. Methods The {"}tree hole{"}intelligent robot captures message data, then randomly selects the same number of high and low suicide risk messages manually, and the high frequency keywords of high and low suicide risk messages are obtained by word segmentation and a TF-IDF algorithm. The keywords are analyzed by Gephi software, and the emotion dictionary provided by Boson is used to judge the emotional tendency of high and low suicide risk users. Results The emotional score of high suicide risk messages was -3.511 ∼ 2.514, averaging (-0.225±0.405), while the total score of low suicide risk messages was -4.547 ∼ 3.403, averaging (-0.121±0.628). Low suicide risk messages mainly focused on negative emotions, interpersonal relationships and social support, while high suicide risk messages mainly centered on invited suicide, means, locations and time of suicide. Conclusion There are differences in emotional characteristics between high and low suicide risk messages. The higher the suicide risk, the more obvious the negative tendency of the users' emotions. More attention is needed to the greater potential for suicide among this group of users and psychological support and interventions should be included.",

keywords = "Artificial intelligence, Emotional characteristics analysis, Suicide risk, Weibo {"}tree hole{"}",

author = "Tianyu He and Yuyu Zheng and Jing Bai and Pan Chen and Yue Ma and Guanghui Fu and Shengxin Hu and Songhe Li and Zhisheng Huang and Qian Liu and Bing, {Xiang Yang}",

note = "Funding Information: Sincere thanks are given to Sharon R. Redding (EdD, RN, CNE) for assistance in editing. Funding: This study is supported by the National Natural Science Foundation of China (No. 72174152), Wuhan university provincial college students' innovation and entrepreneurship training program (S2020305001, S202110486194, S202110486196) and Wuhan university 2019 school of medicine students' innovation and entrepreneurship training program (MS2019046). Publisher Copyright: {\textcopyright} 2021 ACM.; 2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021 ; Conference date: 29-10-2021 Through 31-10-2021",

year = "2021",

month = oct,

doi = "10.1145/3500931.3501027",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "562--567",

booktitle = "ISAIMS '21",

}

He, T, Zheng, Y, Bai, J, Chen, P, Ma, Y, Fu, G, Hu, S, Li, S, Huang, Z, Liu, Q & Bing, XY 2021, Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk. in ISAIMS '21: Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 562-567, 2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021, Virtual, Online, China, 29/10/21. https://doi.org/10.1145/3500931.3501027

Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk. / He, Tianyu; Zheng, Yuyu; Bai, Jing et al.
ISAIMS '21: Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences. Association for Computing Machinery, 2021. p. 562-567 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk

AU - He, Tianyu

AU - Zheng, Yuyu

AU - Bai, Jing

AU - Chen, Pan

AU - Ma, Yue

AU - Fu, Guanghui

AU - Hu, Shengxin

AU - Li, Songhe

AU - Huang, Zhisheng

AU - Liu, Qian

AU - Bing, Xiang Yang

N1 - Funding Information: Sincere thanks are given to Sharon R. Redding (EdD, RN, CNE) for assistance in editing. Funding: This study is supported by the National Natural Science Foundation of China (No. 72174152), Wuhan university provincial college students' innovation and entrepreneurship training program (S2020305001, S202110486194, S202110486196) and Wuhan university 2019 school of medicine students' innovation and entrepreneurship training program (MS2019046). Publisher Copyright: © 2021 ACM.

PY - 2021/10

Y1 - 2021/10

N2 - Background Suicide is a global public health and mental health problem. With the rapid development of internet technology, more and more people tend to express their suicidal tendencies and suicidal intentions online. The difference of emotional characteristics between high and low risk of suicide messages should be analyzed to help identify suicide risk and provide early intervention. Methods The "tree hole"intelligent robot captures message data, then randomly selects the same number of high and low suicide risk messages manually, and the high frequency keywords of high and low suicide risk messages are obtained by word segmentation and a TF-IDF algorithm. The keywords are analyzed by Gephi software, and the emotion dictionary provided by Boson is used to judge the emotional tendency of high and low suicide risk users. Results The emotional score of high suicide risk messages was -3.511 ∼ 2.514, averaging (-0.225±0.405), while the total score of low suicide risk messages was -4.547 ∼ 3.403, averaging (-0.121±0.628). Low suicide risk messages mainly focused on negative emotions, interpersonal relationships and social support, while high suicide risk messages mainly centered on invited suicide, means, locations and time of suicide. Conclusion There are differences in emotional characteristics between high and low suicide risk messages. The higher the suicide risk, the more obvious the negative tendency of the users' emotions. More attention is needed to the greater potential for suicide among this group of users and psychological support and interventions should be included.

AB - Background Suicide is a global public health and mental health problem. With the rapid development of internet technology, more and more people tend to express their suicidal tendencies and suicidal intentions online. The difference of emotional characteristics between high and low risk of suicide messages should be analyzed to help identify suicide risk and provide early intervention. Methods The "tree hole"intelligent robot captures message data, then randomly selects the same number of high and low suicide risk messages manually, and the high frequency keywords of high and low suicide risk messages are obtained by word segmentation and a TF-IDF algorithm. The keywords are analyzed by Gephi software, and the emotion dictionary provided by Boson is used to judge the emotional tendency of high and low suicide risk users. Results The emotional score of high suicide risk messages was -3.511 ∼ 2.514, averaging (-0.225±0.405), while the total score of low suicide risk messages was -4.547 ∼ 3.403, averaging (-0.121±0.628). Low suicide risk messages mainly focused on negative emotions, interpersonal relationships and social support, while high suicide risk messages mainly centered on invited suicide, means, locations and time of suicide. Conclusion There are differences in emotional characteristics between high and low suicide risk messages. The higher the suicide risk, the more obvious the negative tendency of the users' emotions. More attention is needed to the greater potential for suicide among this group of users and psychological support and interventions should be included.

KW - Artificial intelligence

KW - Emotional characteristics analysis

KW - Suicide risk

KW - Weibo "tree hole"

UR - http://www.scopus.com/inward/record.url?scp=85122078147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85122078147&partnerID=8YFLogxK

U2 - 10.1145/3500931.3501027

DO - 10.1145/3500931.3501027

M3 - Conference contribution

AN - SCOPUS:85122078147

T3 - ACM International Conference Proceeding Series

SP - 562

EP - 567

BT - ISAIMS '21

PB - Association for Computing Machinery

T2 - 2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021

Y2 - 29 October 2021 through 31 October 2021

ER -

He T, Zheng Y, Bai J, Chen P, Ma Y, Fu G et al. Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk. In ISAIMS '21: Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences. Association for Computing Machinery. 2021. p. 562-567. (ACM International Conference Proceeding Series). doi: 10.1145/3500931.3501027

Analysis of emotional characteristics of Weibo "tree hole" users with different suicide risk

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this