Shasha Deng

Purpose: Depressive tendency, a precursor to major depressive disorder (MDD), is frequently undetected by existing early-warning systems. Traditional methods, based on univariate metrics or subjective inventories, neglect the multidimensional interactions of biomarkers essential for accurate diagnosis. This study aims to enhance the accuracy of depressive tendency detection, thereby contributing to the reduction of MDD incidence and alleviation of its societal burden through early warning and exploratory intervention use. Design/methodology/approach: This study proposed a multidimensional model for detecting depressive tendency, integrating emotional, behavioral, cognitive, physiological and temporal features into a contextual modeling framework. The model combines bidirectional long short-term memory with an attention mechanism to improve detection accuracy and robustness. It has also been integrated into a virtual psychological intervention platform to support user interaction and exploratory intervention use. Findings: The proposed model effectively captures complex manifestations of depressive tendency, including emotional fluctuations, behavioral dynamics and physiological patterns, particularly in social media data. It outperforms existing models in detection accuracy. An exploratory study within a virtual psychological intervention platform demonstrates the model’s practical utility for early detection and intervention. Originality/value: This study integrates multidimensional psychological and physiological signals into a contextual modeling framework, overcoming limitations of traditional MDD detection methods. The proposed model enhances early detection accuracy and generalizes well across social media datasets. Its practical utility in virtual intervention use highlights its potential for proactive and personalized mental health support.

Purpose: Contemporary focus on infections and deaths in the event of pandemics may distract health institutions and medical practitioners from the psychosocial consequences of the outbreak in individuals. In light of the devastation, persistency and scarcity of pandemics, it is imperative to delve into individuals' psychological state and self-preservation instincts when confronted with the environmental danger arising from pandemic conditions and the environmental restrictions being imposed.Design/methodology/approach: Guided by the self-preservation theory, the authors advance a research model to elucidate the moderated mediation effect of secondary traumatic stress on an individual's reactions when faced with environmental danger and restriction. The authors also consider the moderating influence of environmental restriction and media use diversity. The authors subsequently validated the research model via a survey with 2,016 respondents in China. The authors employed PLS-SEM to analyze the data and assess the hypothesized paths.Findings: Analytical results revealed that secondary traumatic stress fully mediated the impact of environmental danger on external reliance but suppresses the mediating effects on internal reliance. The authors further confirmed that environmental restriction moderated the relationship between environmental danger and reliance. Furthermore, the authors attest to the moderating influence of media use diversity on the relationship between secondary traumatic stress and external reliance.Originality/value: This study not only extends the theoretical lens of self-preservation to public health emergencies but also yields practical guidelines for coping with pandemics. Insights from this study can be harnessed to aid populations worldwide in coping and recovering from pandemics.

Purpose: As convenience and anonymity, people with mental illness are increasingly willing to communicate and share information through social media platforms to receive emotional and spiritual support. The purpose of this paper is to identify the degree of depression based on people's behavioral patterns and discussion content on the Internet.Design/methodology/approach: Based on the previous studies on depression, the severity of depression is divided into four categories: no significant depressive symptoms, mild MDD, moderate MDD and severe MDD, and defined each of them. Next, in order to automatically identify the severity, the authors proposed social media digital cues to identify the severity of depression, which include textual lexical features, depressive language features and social behavioral features. Finally, the authors evaluate a system that is developed based on social media digital cues in the experiment using social media data.Findings: The social media digital cues including textual lexical features, depressive language features and social behavioral features (F1, F2 and F3) is the relatively best one to classify four different levels of depression.Originality/value: This paper innovatively proposes a social media data-based framework (SMDF) to identify and predict different degrees of depression through social media digital cues and evaluates the accuracy of the detection through social media data, providing useful attempts for the identification and intervention of depression.

BACKGROUND Background: Empirical studies have revealed that social support is a crucial determinant that affects OHISI and OHISB in online health communities. However, there is an inconsistency in the relationship between social support and health information sharing. OBJECTIVE Objective: The aim of this review is to systematically review the studies for evidence how social support and its five distinct types (information, emotional, network, esteem, and tangible support) affect online health information sharing intention and behaviour. METHODS Methods: We conducted a meta-analysis that systematically accumulated current research findings. Studies that analyzed the effect sizes from 35 articles (N=35132) representing 64 empirical sample. RESULTS Results: we found that social support is moderately correlated with users' online health information sharing intention (OHISI) and strongly correlated with online health information sharing behaviour (OHISB). Moreover, network support significantly impacts OHISI, while esteem support has the most significant effect on OHISB. Further exploration revealed that the impact of different types of social support on online health information sharing intention and behaviour is moderated by three internal characteristics of the sharer (education level, sharer's identity, and type of information shared) and two external environmental characteristics of the sharer (social culture and platform type). CONCLUSIONS Conclusions: This systematic review will provide a rationale for valuable insights for online health communities and platform managers and a more robust theoretical foundation for future research in this field. CLINICALTRIAL NO

Online depression communities give people additional opportunities to share their experiences and exchange social support to care for themselves in fighting against depression. We aimed to explore what drives patients to share in online depression communities. We used three dimensions of social capital (structural, relational, and cognitive) to explain their sharing behaviors. We further proposed that five factors (social interaction ties, a sense of shared identity, trust, expertise, and a sense of shared values) will have significant, positive effects on sharing behaviors and that there are differences among patients who have spent different lengths of time participating in online depression communities. We then chose a popular online depression community in China as our data source and obtained a dataset consisting of 31,440 posts from 197 members. Then, we employed panel data regression analyses to test all six hypotheses. The results revealed that all five factors had significant, positive effects (p < 0.01) on patients’ sharing behaviors, and the effects were significantly different across groups. Our empirical results help designers and managers of online depression communities take specific measures to facilitate community members’ access to social capital resources. Meanwhile, our results have implications for existing health management and e-health literature.

Artificial intelligence in programmatic advertising constitutes fertile grounds for marketing communication with tremendous opportunities. Yet, despite its touted benefits, contemporary implementations of programmatic advertising do not harness self-generative technologies so much so that different consumers are exposed to identical content. Consequently, we advance a smart generation system of personalized advertising copy (SGS-PAC) that can automatically personalize advertising content to align with the needs of individual consumers. Analytical results from a user experiment involving about 80 subjects underscore that personalized advertising copies generated by SGS-PAC can bolster click rate in online advertising platforms. Findings from this study bear significant implications for the application of artificial intelligence in online advertising.

Purpose: The purpose of this paper is to examine how the usage of enterprise social media (ESM) affects eventual employee turnover. Design/methodology/approach: This study developed a theoretical model based on the proposition that different ESM usage behaviors (utilitarian use, hedonic use and social use) have different effects on employee turnover, and job type and job level can moderate the effect of ESM usage on turnover. The model was examined empirically using 1,791 employee samples from a large high-tech manufacturing enterprise deploying ESM. Findings: The results indicate that the utilitarian and social use of ESM has negative effects on turnover, but the hedonic use of ESM has positive effects on turnover. Furthermore, for employees working in different job types and job levels, there are significant differences concerning the effect of ESM usage on their turnover. Practical implications: ESM managers should encourage employees to use ESM for utilitarian needs and social support but restrict excessive use of ESM for leisure. In addition, different ESM use policies depending upon job types and job levels could be adopted to retain valuable employees. Originality/value: Few studies have focused on how usage of ESM affects eventual employee turnover. Given the lack of theoretical research and empirical evidence, the authors developed a theoretical model and conducted an empirical study to fill the research gap.