Predicting subjective well-being in a high-risk sample of Russian mental health app users

Predicting Prefecture-Level Well-Being Indicators in Japan Using Search Volumes in Internet Search Engines: Infodemiology Study

BACKGROUND

In recent years, the adoption of well-being indicators by national governments and international organizations has emerged as an important tool for evaluating state governance and societal progress. Traditionally, well-being has been gauged primarily through economic metrics such as gross domestic product, which fall short of capturing multifaceted well-being, including socioeconomic inequalities, life satisfaction, and health status. Current well-being indicators, including both subjective and objective measures, offer a broader evaluation but face challenges such as high survey costs and difficulties in evaluating at regional levels within countries. The emergence of web log data as an alternative source of well-being indicators offers the potential for more cost-effective, timely, and less biased assessments.

OBJECTIVE

This study aimed to develop a model using internet search data to predict well-being indicators at the regional level in Japan, providing policy makers with a more accessible and cost-effective tool for assessing public well-being and making informed decisions.

METHODS

This study used the Regional Well-Being Index (RWI) for Japan, which evaluates prefectural well-being across 47 prefectures for the years 2010, 2013, 2016, and 2019, as the outcome variable. The RWI includes a comprehensive approach integrating both subjective and objective indicators across 11 domains, including income, job, and life satisfaction. Predictor variables included z score-normalized relative search volume (RSV) data from Google Trends for words relevant to each domain. Unrelated words were excluded from the analysis to ensure relevance. The Elastic Net methodology was applied to predict RWI using RSVs, with α balancing ridge and lasso effects and λ regulating their strengths. The model was optimized by cross-validation, determining the best mix and strength of regularization parameters to minimize prediction error. Root mean square errors (RMSE) and coefficients of determination (R2) were used to assess the model's predictive accuracy and fit.

RESULTS

An analysis of Google Trends data yielded 275 words related to the RWI domains, and RSVs were collected for 211 words after filtering out irrelevant terms. The mean search frequencies for these words during 2010, 2013, 2016, and 2019 ranged from -1.587 to 3.902, with SDs between 3.025 and 0.053. The best Elastic Net model (α=0.1, λ=0.906, RMSE=1.290, and R2=0.904) was built using 2010-2016 training data and 2-13 variables per domain. Applied to 2019 test data, it yielded an RMSE of 2.328 and R2 of 0.665.

CONCLUSIONS

This study demonstrates the effectiveness of using internet search log data through the Elastic Net machine learning method to predict the RWI in Japanese prefectures with high accuracy, offering a rapid and cost-efficient alternative to traditional survey approaches. This study highlights the potential of this methodology to provide foundational data for evidence-based policy making aimed at enhancing well-being.

Predicting social media users' indirect aggression through pre-trained models

Indirect aggression has become a prevalent phenomenon that erodes the social media environment. Due to the expense and the difficulty in determining objectively what constitutes indirect aggression, the traditional self-reporting questionnaire is hard to be employed in the current cyber area. In this study, we present a model for predicting indirect aggression online based on pre-trained models. Building on Weibo users' social media activities, we constructed basic, dynamic, and content features and classified indirect aggression into three subtypes: social exclusion, malicious humour, and guilt induction. We then built the prediction model by combining it with large-scale pre-trained models. The empirical evidence shows that this prediction model (ERNIE) outperforms the pre-trained models and predicts indirect aggression online much better than the models without extra pre-trained information. This study offers a practical model to predict users' indirect aggression. Furthermore, this work contributes to a better understanding of indirect aggression behaviors and can support social media platforms' organization and management.

Association of family function and suicide risk in teenagers with a history of self-harm behaviors: mediating role of subjective wellbeing and depression

Background

A history of self-harm behaviors is closely associated with subsequent suicide death. Although many factors associated with suicide have been identified, it remains unclear how these factors interact to influence suicide risk, especially among teenagers with a history of self-harm behaviors.

Methods

Data were collected from 913 teenagers with a history of self-harm behaviors through a cross-sectional study. The Family Adaptation, Partnership, Growth, Affection, and Resolve index was used to assess teenagers' family function. The Patient Health Questionnaire-9 and the Generalized Anxiety Disorder-7 were used to evaluate depression and anxiety in teenagers and their parents, respectively. The Delighted Terrible Faces Scale was used to assess teenagers' perception of subjective wellbeing. The Suicidal Behaviors Questionnaire-Revised was used to evaluate teenagers' suicide risk. Student's t-test, one-way ANOVA, multivariate linear regression, Pearson's correlation, and a structural equation model (SEM) were applied to data analysis.

Results

Overall, 78.6% of teenagers with a history of self-harm behaviors were at risk for possible suicide. Female gender, severity of teenagers' depression, family function, and subjective wellbeing were significantly associated with suicide risk. The results of SEM suggested that there was a significant chain mediation effect of subjective wellbeing and depression between family function and suicide risk.

Conclusion

Family function was closely associated with suicide risk in teenagers with a history of self-harm behaviors, and depression and subjective wellbeing were sequential mediators in the association between family function and suicide risk.

Factors Affecting the Use of Social Networks and Its Effect on Anxiety and Depression among Parents and Their Children: Predictors Using ML, SEM and Extended TAM

Previous research has found support for depression and anxiety associated with social networks. However, little research has explored parents' depression and anxiety constructs as mediators that may account for children's depression and anxiety. The purpose of this paper is to test the influence of different factors on children's depression and anxiety, extending from parents' anxiety and depression in Jordan. The authors recruited 857 parents to complete relevant web survey measures with constructs and items and a model based on different research models TAM and extended with trust, analyzed using SEM, CFA with SPSS and AMOS, and ML methods, using the triangulation method to validate the results and help predict future applications. The authors found support for the structural model whereby behavioral intention to use social media influences the parent's anxiety and depression which correlate to their offspring's anxiety and depression. Behavioral intention to use social media can be enticed by enjoyment, trust, ease of use, usefulness, and social influences. This study is unique in exploring rumination in the context of the relationship between parent-child anxiety and depression due to the use of social networks.

Predicting Intrinsic and Extrinsic Goal Contents Pursuit on Social Media

Goal contents pursuit reflects the motivational personality and can be an excellent indicator to predict individuals' life satisfaction and daily behaviors. However, due to the expense and subjective bias of questionnaires, it is challenging to obtain individual data and explore the effects of goal contents pursuit in conventional studies. Social media provides individuals with a communication context that can be used as a proxy to infer personality based on a massive of media footprints information. This study obtained 456 Weibo active users' self-reports of goal contents pursuit scale and their online behaviors that is established to train a competent machine learning model, which then successfully identifies the classification of intrinsic and extrinsic goals. From the perspective of Weibo users' features (i.e., basic, interactive, linguistic, and emotional features), the systematic comparison shows the significant differences in the pursuit level of intrinsic and extrinsic goals. This study advances the methodology of employing machine learning and online data to objectively delineate individual goal contents pursuit and paves the way to explore a massive number of individuals' personalities and behaviors.