A large proportion of Depression Disorder patients do not receive an effective diagnosis, which makes it necessary to find a more objective assessment to facilitate a more rapid and accurate diagnosis of depression. Speech data is easy to acquire clinically, its association with depression has been studied, although the actual predictive effect of voice features has not been examined. Thus, we do not have a general understanding of the extent to which voice features contribute to the identification of depression. In this study, we investigated the significance of the association between voice features and depression using binary logistic regression, and the actual classification effect of voice features on depression was re-examined through classification modeling. Nearly 1000 Chinese females participated in this study. Several different datasets was included as test set. We found that 4 voice features (PC1, PC6, PC17, PC24, P<0.05, corrected) made significant contribution to depression, and that the contribution effect of the voice features alone reached 35.65% (Nagelkerke's R²). In classification modeling, voice data based model has consistently higher predicting accuracy(F-measure) than the baseline model of demographic data when tested on different datasets, even across different emotion context. F-measure of voice features alone reached 81%, consistent with existing data. These results demonstrate that voice features are effective in predicting depression and indicate that more sophisticated models based on voice features can be built to help in clinical diagnosis.

Depression is one of the most common mental illnesses but remains underdiagnosed. Suicide, as a core symptom of depression, urgently needs to be monitored at an early stage, i.e., the suicidal ideation (SI) stage. Depression and subsequent suicidal ideation should be supervised on social media. In this research, we investigated depression and concomitant suicidal ideation by identifying individuals’ linguistic characteristics through machine learning approaches. On Weibo, we sampled 487,251 posts from 3196 users from the depression super topic community (DSTC) as the depression group and 357,939 posts from 5167 active users on Weibo as the control group. The results of the logistic regression model showed that the SCLIWC (simplified Chinese version of LIWC) features such as affection, positive emotion, negative emotion, sadness, health, and death significantly predicted depression (Nagelkerke’s R² = 0.64). For model performance: F-measure = 0.78, area under the curve (AUC) = 0.82. The independent samples’ t-test showed that SI was significantly different between the depression (0.28 ± 0.5) and control groups (−0.29 ± 0.72) (t = 24.71, p < 0.001). The results of the linear regression model showed that the SCLIWC features, such as social, family, affection, positive emotion, negative emotion, sadness, health, work, achieve, and death, significantly predicted suicidal ideation. The adjusted R² was 0.42. For model performance, the correlation between the actual SI and predicted SI on the test set was significant (r = 0.65, p < 0.001). The topic modeling results were in accordance with the machine learning results. This study systematically investigated depression and subsequent SI-related linguistic characteristics based on a large-scale Weibo dataset. The findings suggest that analyzing the linguistic characteristics on online depression communities serves as an efficient approach to identify depression and subsequent suicidal ideation, assisting further prevention and intervention.

A great many of empirical researches have proved that longtime exposure to violent video game can lead to a series of negative effects. Although research has focused on the neural basis of the correlation between violent video game and aggression, little is known whether the spontaneous brain activity is associated with violent video game exposure. To address this question, we measured the spontaneous brain activity using resting-state functional magnetic resonance imaging (fMRI). We used the amplitude of low-frequency fluctuations (ALFF) and fractional ALFF (fALFF) to quantify spontaneous brain activity. The results showed there is no significant difference in ALFF, or fALFF, between violent video game group and the control part, indicating that long time exposure to violent video games won’t significantly influence spontaneous brain activity, especially the core brain regions such as execution control, moral judgment and short-term memory. This implies the adverse impact of violent video games is exaggerated.

Background: Large language models (LLMs) are increasingly being used for text-based emotional support. However, general-purpose LLMs may not consistently recognize emotional cues, adapt supportive strategies to contexts, or generate responses aligned with psychologically informed communication. The limited availability of large-scale, structured Chinese counseling data further constrains the development of models for context-sensitive emotional support. Objective: We developed and evaluated YuanChat, a family of specialized LLMs for context-sensitive emotional support; assessed whether E-URIAL improved response quality; and compared YuanChat with base LLMs. Methods: We constructed 2 datasets from anonymized real-world counseling sessions: ECD-3 (104,897 counselor response turns) for fine-tuning and D _gold (9413 manually annotated counselor responses). Annotations covered emotional support conversation stages (exploration, comfort, and action), counseling techniques (clarification, support, and challenge), and empathic effects. We developed 2 YuanChat variants using GLM-4-9B-Chat and Huozi 3.5 as backbone models using parameter-efficient fine-tuning with low-rank adaptation (LoRA). We then developed E-URIAL, an inference-time framework combining predicted emotion and support strategy labels with retrieved labeled exemplars. Given the dialogue history through the help seeker’s latest utterance, each model generated a counselor-style response. We compared YuanChat with GPT-4, ERNIE 4.0, CharacterGLM, GLM-4-9B-Chat, and Huozi 3.5. The evaluation comprised (1) automatic evaluation on in-domain and external datasets, assessing empathy identification and empathic expression; (2) evaluation of empathy-related situational reasoning using an expert-developed multiple-choice benchmark; (3) evaluation by clinical experts (n=8) of empathic attunement, support strategy appropriateness, perceived helpfulness, and safety and professional boundary adherence; and (4) a complementary evaluation by volunteer master’s students in clinical and counseling psychology (n=50) of response fluency, empathy, and perceived helpfulness. Results: Fine-tuning increased YuanChat-Huozi3.5’s empathic expression score from 0.57 to 0.68; empathy identification score increased from 0.54 to 0.59. In expert evaluation, YuanChat-Huozi3.5 received a higher empathic attunement score than the base Huozi3.5 model (1.279 vs 0.327; mean difference 0.952, 95% CI 0.746‐1.152). Using professional counselor responses as the reference, the mean differences for YuanChat-Huozi3.5 were 0.148, 0.079, 0.039, and 0.002 in empathic attunement, supportive appropriateness, perceived helpfulness, and safety and professional boundary adherence, respectively. No statistically significant differences were detected between YuanChat-Huozi3.5 and the counselor references (all Holm-adjusted P ≥.29). Higher scores were observed when E-URIAL was applied. When E-URIAL was applied with 3 retrieved exemplars, YuanChat-Huozi3.5 achieved an empathy identification score of 0.69 versus 0.59 without E-URIAL, an empathic expression score of 0.79 versus 0.68, and a perceived helpfulness score of 0.74 versus 0.61. Conclusions: The findings indicate that fine-tuning on real-world counseling data and annotating models with structured emotional support labels improved context-sensitive empathic responding in LLMs. Without updating model parameters, E-URIAL further improved empathy identification and empathic expression across multiple models. Together, these methods provide a scalable, theory-informed approach to enhancing the emotional support capabilities of LLMs.