Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model

• URL: http://arxiv.org/abs/2405.04128v1
• Date: Tue, 7 May 2024 08:53:25 GMT
• Title: Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model
• Authors: Zhonglong Chen, Changwei Song, Yining Chen, Jianqiang Li, Guanghui Fu, Yongsheng Tong, Qing Zhao,
• Abstract summary: We developed a negative emotion recognition model and a fine-grained multi-label classification model using a large-scale pre-trained model. Our experiments indicate that the negative emotion recognition model achieves a maximum F1-score of 76.96%.
• Score: 12.942304409369747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Suicide and suicidal behaviors remain significant challenges for public policy and healthcare. In response, psychological support hotlines have been established worldwide to provide immediate help to individuals in mental crises. The effectiveness of these hotlines largely depends on accurately identifying callers' emotional states, particularly underlying negative emotions indicative of increased suicide risk. However, the high demand for psychological interventions often results in a shortage of professional operators, highlighting the need for an effective speech emotion recognition model. This model would automatically detect and analyze callers' emotions, facilitating integration into hotline services. Additionally, it would enable large-scale data analysis of psychological support hotline interactions to explore psychological phenomena and behaviors across populations. Our study utilizes data from the Beijing psychological support hotline, the largest suicide hotline in China. We analyzed speech data from 105 callers containing 20,630 segments and categorized them into 11 types of negative emotions. We developed a negative emotion recognition model and a fine-grained multi-label classification model using a large-scale pre-trained model. Our experiments indicate that the negative emotion recognition model achieves a maximum F1-score of 76.96%. However, it shows limited efficacy in the fine-grained multi-label classification task, with the best model achieving only a 41.74% weighted F1-score. We conducted an error analysis for this task, discussed potential future improvements, and considered the clinical application possibilities of our study. All the codes are public available.

Related papers

• Enhanced Large Language Models for Effective Screening of Depression and Anxiety [44.81045754697482]
  This paper introduces a pipeline for synthesizing clinical interviews, resulting in 1,157 interactive dialogues (PsyInterview) EmoScan distinguishes between coarse (e.g., anxiety or depressive disorders) and fine disorders (e.g., major depressive disorders) and conducts high-quality interviews.
  arXiv  Detail & Related papers  (2025-01-15T12:42:09Z)
• Deep Learning-Based Feature Fusion for Emotion Analysis and Suicide Risk Differentiation in Chinese Psychological Support Hotlines [18.81118590515144]
  This study introduces a method that combines pitch acoustic features with deep learning-based features to analyze and understand emotions expressed during hotline interactions. Using data from China's largest psychological support hotline, our method achieved an F1-score of 79.13% for negative binary emotion classification. Our findings suggest that emotional fluctuation intensity and frequency could serve as novel features for psychological assessment scales and suicide risk prediction.
  arXiv  Detail & Related papers  (2025-01-15T10:09:38Z)
• MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders [59.515827458631975]
  Mental health disorders are one of the most serious diseases in the world. Privacy concerns limit the accessibility of personalized treatment data. MentalArena is a self-play framework to train language models.
  arXiv  Detail & Related papers  (2024-10-09T13:06:40Z)
• An Exploratory Deep Learning Approach for Predicting Subsequent Suicidal Acts in Chinese Psychological Support Hotlines [13.59130559079134]
  The accuracy of scale-based predictive methods for suicide risk assessment can vary widely depending on the expertise of the operator. This study is the first to apply deep learning to long-term speech data to predict suicide risk in China.
  arXiv  Detail & Related papers  (2024-08-29T11:51:41Z)
• Depression Detection and Analysis using Large Language Models on Textual and Audio-Visual Modalities [25.305909441170993]
  Depression has proven to be a significant public health issue, profoundly affecting the psychological well-being of individuals. If it remains undiagnosed, depression can lead to severe health issues, which can manifest physically and even lead to suicide.
  arXiv  Detail & Related papers  (2024-07-08T17:00:51Z)
• Measuring Non-Typical Emotions for Mental Health: A Survey of Computational Approaches [57.486040830365646]
  Stress and depression impact the engagement in daily tasks, highlighting the need to understand their interplay. This survey is the first to simultaneously explore computational methods for analyzing stress, depression, and engagement.
  arXiv  Detail & Related papers  (2024-03-09T11:16:09Z)
• PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents [68.50571379012621]
  Psychological measurement is essential for mental health, self-understanding, and personal development. PsychoGAT (Psychological Game AgenTs) achieves statistically significant excellence in psychometric metrics such as reliability, convergent validity, and discriminant validity.
  arXiv  Detail & Related papers  (2024-02-19T18:00:30Z)
• Conceptualizing Suicidal Behavior: Utilizing Explanations of Predicted Outcomes to Analyze Longitudinal Social Media Data [2.76101452577748]
  The COVID-19 pandemic has escalated mental health crises worldwide. Suicide can result from social factors such as shame, abuse, abandonment, and mental health conditions like depression. As these conditions develop, signs of suicidal ideation may manifest in social media interactions.
  arXiv  Detail & Related papers  (2023-12-13T17:15:12Z)
• Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China [50.12173157902495]
  The study included 134 participants, split into three groups: Emohaa (CBT-based), Emohaa (Full) and control. Emohaa is a conversational agent that provides cognitive support through CBT-based exercises and guided conversations. It also emotionally supports users by enabling them to vent their desired emotional problems.
  arXiv  Detail & Related papers  (2022-09-21T08:23:40Z)
• An ensemble deep learning technique for detecting suicidal ideation from posts in social media platforms [0.0]
  This paper proposes a LSTM-Attention-CNN combined model to analyze social media submissions to detect suicidal intentions. The proposed model demonstrated an accuracy of 90.3 percent and an F1-score of 92.6 percent.
  arXiv  Detail & Related papers  (2021-12-17T15:34:03Z)
• When a crisis strikes: Emotion analysis and detection during COVID-19 [96.03869351276478]
  We present CovidEmo, 1K tweets labeled with emotions. We examine how well large pre-trained language models generalize across domains and crises.
  arXiv  Detail & Related papers  (2021-07-23T04:07:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.