A mental disorder early warning approach by observing depression symptom in social diary

Fang, Ying-En; Tai, Chih-Hua; Chang, Yue-Shan; Fan, Chih-Tien

doi:10.1109/smc.2014.6974225

Cited by 7 publications

(2 citation statements)

References 11 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In research papers by Fang et al. (2014) and Nadeem (2016), the authors made use of the frequencies of words for both classes of users (i.e., depressed and normal) and made use of different machine learning algorithms to classify them into the meaningful class. Nadeem (2016) used the word‐cloud to visually give insights for the sentiment expressed by the choice of words of the users.…”

Section: Literature Reviewmentioning

confidence: 99%

Tracing prodromal behaviour by analysing data patterns from social media with ensemble machine learning approach

Joshi

Patwardhan

2022

Int Social Sci J

View full text Add to dashboard Cite

This paper presents a novel solution for tracing prodromal behaviour of Twitter users for early detection and prevention of mental illness. A very large number of people are using Twitter to share their daily happenings. This is creating a rich source of data portraying individual behaviour. Machine learning can be used to screen individual users who show prodromal behavioural change over a period and need to consult a psychiatrist. The system comprises of an ensemble model with multiple modules including classification and clustering in addition to lexicon‐based approach, and, for the final verdict, a voting system which emphasises a better precision model is proposed. The model has been validated and tested on standard Self‐Reported Mental Health Diagnoses dataset and promises to give a better result than the baseline.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Tracing prodromal behaviour by analysing data patterns from social media with ensemble machine learning approach

Joshi

Patwardhan

2022

Int Social Sci J

View full text Add to dashboard Cite

show abstract

“…Based on the psychological diagnosis results of linguistic analyses, an online suicide prevention and psychological intervention system could be established for LBC. Fang, Chang, and Fan extracted characteristic words related to mental disorders through text matching of depressive dairies published on social media, and then scored them [ 20 ]. When the score exceeded a certain level, the system would automatically send messages to the patient’s friends, alerting them that the patient might need psychological support.…”

Section: Introductionmentioning

confidence: 99%

Psychological Well-Being of Left-Behind Children in China: Text Mining of the Social Media Website Zhihu

Lyu

Chow

Hwang

et al. 2022

IJERPH

View full text Add to dashboard Cite

China’s migrant population has significantly contributed to its economic growth; however, the impact on the well-being of left-behind children (LBC) has become a serious public health problem. Text mining is an effective tool for identifying people’s mental state, and is therefore beneficial in exploring the psychological mindset of LBC. Traditional data collection methods, which use questionnaires and standardized scales, are limited by their sample sizes. In this study, we created a computational application to quantitively collect personal narrative texts posted by LBC on Zhihu, which is a Chinese question-and-answer online community website; 1475 personal narrative texts posted by LBC were gathered. We used four types of words, i.e., first-person singular pronouns, negative words, past tense verbs, and death-related words, all of which have been associated with depression and suicidal ideations in the Chinese Linguistic Inquiry Word Count (CLIWC) dictionary. We conducted vocabulary statistics on the personal narrative texts of LBC, and bilateral t-tests, with a control group, to analyze the psychological well-being of LBC. The results showed that the proportion of words related to depression and suicidal ideations in the texts of LBC was significantly higher than in the control group. The differences, with respect to the four word types (i.e., first-person singular pronouns, negative words, past tense verbs, and death-related words), were 5.37, 2.99, 2.65, and 2.00 times, respectively, suggesting that LBC are at a higher risk of depression and suicide than their counterparts. By sorting the texts of LBC, this research also found that child neglect is a main contributing factor to psychological difficulties of LBC. Furthermore, mental health problems and the risk of suicide in vulnerable groups, such as LBC, is a global public health issue, as well as an important research topic in the era of digital public health. Through a linguistic analysis, the results of this study confirmed that the experiences of left-behind children negatively impact their mental health. The present findings suggest that it is vital for the public and nonprofit sectors to establish online suicide prevention and intervention systems to improve the well-being of LBC through digital technology.

show abstract

Intend to analyze Social Media feeds to detect behavioral trends of individuals to proactively act against Social Threats

Jindal

Sharma

2018

Procedia Computer Science

View full text Add to dashboard Cite

A mental disorder early warning approach by observing depression symptom in social diary

Cited by 7 publications

References 11 publications

Tracing prodromal behaviour by analysing data patterns from social media with ensemble machine learning approach

Tracing prodromal behaviour by analysing data patterns from social media with ensemble machine learning approach

Psychological Well-Being of Left-Behind Children in China: Text Mining of the Social Media Website Zhihu

Intend to analyze Social Media feeds to detect behavioral trends of individuals to proactively act against Social Threats

Contact Info

Product

Resources

About