Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model (2405.04128v1)

Published 7 May 2024 in cs.CL, cs.SD, and eess.AS

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. M. Naghavi, “Global, regional, and national burden of suicide mortality 1990 to 2016: systematic analysis for the global burden of disease study 2016,” bmj, vol. 364, 2019.
  2. X.-L. Cao, B.-L. Zhong, Y.-T. Xiang, G. S. Ungvari, K. Y. Lai, H. F. Chiu, and E. D. Caine, “Prevalence of suicidal ideation and suicide attempts in the general population of China: a meta-analysis,” The International Journal of Psychiatry in Medicine, vol. 49, no. 4, pp. 296–308, 2015.
  3. R. Chen, J. An, and J. Ou, “Suicidal behaviour among children and adolescents in China,” The Lancet Child & Adolescent Health, vol. 2, no. 8, pp. 551–553, 2018.
  4. M. S. Gould, A. M. Lake, H. Galfalvy, M. Kleinman, J. L. Munfakh, J. Wright, and R. McKeon, “Follow-up with callers to the national suicide prevention lifeline: Evaluation of callers’ perceptions of care,” Suicide and Life-Threatening Behavior, vol. 48, no. 1, pp. 75–86, 2018.
  5. M. S. Gould, A. M. Lake, J. L. Munfakh, H. Galfalvy, M. Kleinman, C. Williams, A. Glass, and R. McKeon, “Helping callers to the national suicide prevention lifeline who are at imminent risk of suicide: Evaluation of caller risk profiles and interventions implemented,” Suicide and Life-Threatening Behavior, vol. 46, no. 2, pp. 172–190, 2016.
  6. T. K. Witte, M. S. Gould, J. L. H. Munfakh, M. Kleinman, T. E. Joiner Jr, and J. Kalafat, “Assessing suicide risk among callers to crisis hotlines: A confirmatory factor analysis,” Journal of clinical psychology, vol. 66, no. 9, pp. 941–964, 2010.
  7. L. Zhao, Z. Li, Y. Tong, M. Wu, C. Wang, Y. Wang, and N. H. Liu, “Comparisons of characteristics between psychological support hotline callers with and without covid-19 related psychological problems in China,” Frontiers in Psychiatry, vol. 12, p. 648974, 2021.
  8. F. F.-T. Shaw and W.-H. Chiang, “An evaluation of suicide prevention hotline results in taiwan: Caller profiles and the effect on emotional distress and suicide risk,” Journal of Affective Disorders, vol. 244, pp. 16–20, 2019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0165032718310243
  9. R. Ramchand, L. Jaycox, P. Ebener, M. L. Gilbert, D. Barnes-Proby, and P. Goutam, “Characteristics and proximal outcomes of calls made to suicide crisis hotlines in California,” Crisis, 2016.
  10. L. Tavi and S. Werner, “A phonetic case study on prosodic variability in suicidal emergency calls.” International Journal of Speech, Language & the Law, vol. 27, no. 1, 2020.
  11. Z.-L. Wang, P.-H. Huang, W.-Y. Hsu, and H.-H. Huang, “Self-adapted utterance selection for suicidal ideation detection in lifeline conversations,” in Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023, pp. 1436–1446.
  12. R. Iyer, “A unified approach to suicide risk detection using text and voice.” Ph.D. dissertation, School of Health Sciences, Swinburne University of Technology, 2023.
  13. S. Salmi, S. Mérelle, R. Gilissen, R. van der Mei, and S. Bhulai, “Detecting changes in help seeker conversations on a suicide prevention helpline during the COVID-19 pandemic: in-depth analysis using encoder representations from transformers,” BMC public health, vol. 22, no. 1, p. 530, 2022.
  14. M. Grootendorst, “BERTopic: Neural topic modeling with a class-based TF-IDF procedure,” arXiv preprint arXiv:2203.05794, 2022.
  15. M. Alabdulla, Y. Iqbal, H. G. A. Mohamed, D. Shinith, R. A. Buenaventura, K. A. W. Smith, M. Hamideh, and S. Ouanes, “Management of suicide and self-harm risk by the national mental health helpline in the state of qatar,” BJPsych open, vol. 9, no. 3, p. e97, 2023.
  16. S. Liu, A. Mallol-Ragolta, E. Parada-Cabaleiro, K. Qian, X. Jing, A. Kathan, B. Hu, and B. W. Schuller, “Audio self-supervised learning: A survey,” Patterns, vol. 3, no. 12, 2022.
  17. Y. Du, Z. Liu, J. Li, and W. X. Zhao, “A survey of vision-language pre-trained models,” arXiv preprint arXiv:2202.10936, 2022.
  18. T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., “Language models are few-shot learners,” Advances in neural information processing systems, vol. 33, pp. 1877–1901, 2020.
  19. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
  20. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark et al., “Learning transferable visual models from natural language supervision,” in International conference on machine learning.   PMLR, 2021, pp. 8748–8763.
  21. T. He, G. Fu, Y. Yu, F. Wang, J. Li, Q. Zhao, C. Song, H. Qi, D. Luo, H. Zou et al., “Towards a psychological generalist ai: A survey of current applications of large language models and future prospects,” arXiv preprint arXiv:2312.04578, 2023.
  22. S. Schneider, A. Baevski, R. Collobert, and M. Auli, “Wav2Vec: Unsupervised pre-training for speech recognition,” arXiv preprint arXiv:1904.05862, 2019.
  23. A. Baevski, Y. Zhou, A. Mohamed, and M. Auli, “Wav2Vec 2.0: A framework for self-supervised learning of speech representations,” Advances in neural information processing systems, vol. 33, pp. 12 449–12 460, 2020.
  24. W.-N. Hsu, B. Bolte, Y.-H. H. Tsai, K. Lakhotia, R. Salakhutdinov, and A. Mohamed, “HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 3451–3460, 2021.
  25. A. Radford, J. W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever, “Robust speech recognition via large-scale weak supervision,” in International Conference on Machine Learning.   PMLR, 2023, pp. 28 492–28 518.
  26. A. Nfissi, W. Bouachir, N. Bouguila, and B. Mishara, “Unlocking the emotional states of high-risk suicide callers through speech analysis,” in 2024 IEEE 18th International Conference on Semantic Computing (ICSC).   IEEE, 2024, pp. 33–40.
  27. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  28. R. Ardila, M. Branson, K. Davis, M. Henretty, M. Kohler, J. Meyer, R. Morais, L. Saunders, F. M. Tyers, and G. Weber, “Common voice: A massively-multilingual speech corpus,” in Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), 2020, pp. 4211–4215.
  29. K. Park and T. Mulc, “CSS10: A collection of single speaker speech datasets for 10 languages,” Interspeech, 2019.
  30. Surfing.ai, “ST-CMDS-20170001 1, free st chinese mandarin corpus,” https://www.openslr.org/38/, 2017, accessed: 2024-04-10.
  31. V. Panayotov, G. Chen, D. Povey, and S. Khudanpur, “Librispeech: an asr corpus based on public domain audio books,” in 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP).   IEEE, 2015, pp. 5206–5210.
  32. A. Conneau, M. Ma, S. Khanuja, Y. Zhang, V. Axelrod, S. Dalmia, J. Riesa, C. Rivera, and A. Bapna, “Fleurs: Few-shot learning evaluation of universal representations of speech,” in 2022 IEEE Spoken Language Technology Workshop (SLT).   IEEE, 2023, pp. 798–805.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now