Extraction of Characteristics of Time in “Tree Hole” Data

Authors

  • Xiaomin Jing The Information Department, Beijing University of Technology, Beijing, China https://orcid.org/0000-0002-2775-6305
  • Shaofu Lin Beijing Institute of Smart City, Beijing University of Technology, Beijing, China
  • Zhisheng Huang Department of Computer Science, Vrije University Amsterdam, Amsterdam, The Netherlands

DOI:

https://doi.org/10.2991/jaims.d.201209.001

Keywords:

Depression, Microblog, Tree hole, Knowledge graph, Time characteristics, Rescue

Abstract

Statistics show that 15 percent of depressed people died by suicide, and more than 50 percent of depressed people are thinking about suicide. Worldwide, depression has become the second leading cause of death among people aged 15–29. This paper focus on the “tree hole” message data on microblog, and conducts data visualization research from different granularity, such as quarter, month, and analyses activity of message during holiday based on the knowledge graph, so as to obtain the national time distribution characteristics of the potential risk of mental health for the reference of social institutions’ monitoring and rescue and government departments’ decision-making. According to the time distribution rule of “tree hole” data, the relatively high occurrence time and possible reasons for depression and suicide are found, so that manpower could be reasonably deployed for effective prevention and rescue.

References

L. Guan, B. Hao, A pilot study of differences in behavioral and linguistic characteristics between Sina suicide microblog users and Sina microblog users without suicide idea[J], Chin. J. Epidemiol. 36 (2015), 421–425. https://europepmc.org/article/med/ 26080626

R. Cyganiak, D. Wood, M. Lanthaler, RDF 1.1 concepts and abstract syntax, 2014. https://www.researchgate.net/publication/ 259671336_RDF_11_Concepts_and_Abstract_Syntax

T. Goodwin, S.M. Harabagi, Automatic generation of a qualified medical knowledge graph and its usage for retrieving patient cohorts from electronic medical records, in IEEE Seventh International Conference on Semantic Computing, Irvine, CA, USA, 2013.

V. Zamborlini, R. Hoekstra, M.D. Silveira, C. Pruski, A. ten Teije, F. van Harmelen, Inferring recommendation interactions in clinical guidelines, Semantic. Web. 7 (2016), 421–446.

H. Bai, X. Ma, The incidence of depression in college students is increasing year by year. High incidence of freshmen and juniors[N], China Youth News. (2019). https://baijiahao.baidu. com/s?id=1639908146264436155&wfr=spider&for=pc

J. Li, H. Tong, Y. Zhang et al., Study on the relationship between the pathological time of Heyi and the onset time of depression in Mongolian medicine [J], Global Chin. Med. 9 (2016), 678–683.

Y. Jie, H. Zhi-Sheng, Q. Hu, Integration of adverse reaction knowledge of antidepressants with knowledge graph of depression and its applications[J], China Digit. Med. (2017).

Z. Huang, J. Yang, F.V. Harmelen et al., Constructing knowledge graphs of depression[J], Int. Conf. Health Inf. Sci. 10594 (2017), 149–161.

Z. Huang, Y. Min, F. Lin, D. Xie, Temporal characteristics of suicide information in social media[J], China Digit. Med. (2019). https://CNKI:SUN:YISZ.0.2019-03-005

P. Yu, Discussion on the seasonal onset of depression in traditional Chinese medicine[J], Chin. Arch. Tradit. Chin. Med. (2006).

M. Zhu, Discussion on the etiology of depression[J], Cont. Med. Forum. 13 (2015), 158–159. https://CNKI:SUN:QYWA.0.2015- 09-138

Published

2021-05-05

How to Cite

1.
Jing X, Lin S, Huang Z. Extraction of Characteristics of Time in “Tree Hole” Data. JAIMS [Internet]. 2021 May 5 [cited 2023 Feb. 4];1(3-4):43-8. Available from: http://oapublishing-jaims.com/jaims/article/view/78