自杀风险识别是自杀预防的重要环节,但传统的自陈量表筛查存在虚报/漏报率高的局限。通过两步连续实验对主题统觉测验（TAT）进行的改编实现了基于TAT的小程序自助施测方案,并获取音频及文本数据用于机器学习建模,构建了针对自杀意念的自杀风险识别模型。结果发现,在测验耗时更短的情况下,该模型取得了与前人研究相比综合指数更优的模型效果;词频分析及关键词共线网络分析发现高自杀风险组被试在叙述文本中提及了更多与自杀、自伤相关的词汇以及主题,且使用了更多的排除词。经改编后的TAT小程序施测方案流程标准化且施测便捷,后续可收集更多高质量的样本以构建泛化性能更优的模型,应用于自杀风险识别的辅助评估中。
Abstract
Suicide is not only a personal tragedy, but also has far-reaching effects. Identifying suicide risk is an important part of suicide prevention. Because traditional suicide risk screening methods based on self-report scales have a high rate of misreporting/underreporting, it is important to find an objective and effective identification tool.
Although previous studies on the establishment of suicide risk identification models through audio data have yielded good results, the test materials used lacked theoretical support and were time-consuming. Besides, the lack of a standardized process made it difficult to collect large data to train a model that could be applied. Therefore, this study aims to adapt the widely used Thematic Apperception Test (TAT) by two steps. Firstly, adapting the test materials into an online test to build a model, and then developing a WeChat app to obtain high-quality audio data in a standardized process to build a suicide risk model.
Study 1 began by adapting a standardized process for online administration of the TAT using the Tencent meetings. The audio of 64 subjects (High Risk Group: 34; Low Risk Group: 30) who completed the test was included in the analysis. After pre-processing, speech and text features were extracted for machine learning modeling, and four classifiers (SVM, LR, RF, KNN) were used to build the model. It was found that (1)Three pictures in the TAT test constructed the best performing classification models. Take Picture 5 in TAT for example, the LR model achieved an average ACC= .80 and an average AUC= .90. The best performing models were LR and SVM. (2) The analysis of narrative duration revealed that the subjects in the crisis group in this test generally had longer narrative durations. (3) Word frequency analysis of the full-length text using KH Coder found more words related to suicide, self-injury, and negative emotions mentioned in the narrative texts of the subjects in the crisis group, and more themes about suicide and self-injury in the narratives of the subjects in the crisis group were found through Keyword Co-occurrence Network analysis. The results of Study 1 confirm the feasibility of administering a TAT online and applying speech and text features to identify suicide risk, but the test is still time-consuming and requires a subject to administer it, so there may be experimenter bias.
To further standardize the process, reduce the test time and enhance the convenience of the test, and thus improve the applicability of the adapted TAT, we further conducted Study 2. In this Study, a WeChat app was designed and implemented, and two images from Study 1 (Figure 5 and Figure 10) were used as test materials and administered by the subjects themselves. A total of 58 subjects' audio was included in the analysis (High Risk Group: 29; Low Risk Group: 29). Four classifier models were selected for feature extraction and evaluated for effectiveness. The LR model trained with the data set extracted from the combined audio in Figure 5 and Figure 10 achieved the best results of all models in terms of ACC metrics (mean ACC= .83, mean AUC= .89). The results of the study suggest that modeling using audio data generated from a participant self-administered test can also yield satisfactory results. The constructed model achieved better modeling results with a better composite index compared to previous studies when the test took less time. The short administration time, ease of administration, and standardized procedure of the adapted TAT applet also facilitated the collection of more high-quality samples for the construction of a better generalized model to be used as an aid in the identification of suicide risk.
关键词
自杀风险识别 /
主题统觉测验 /
机器学习 /
语音识别 /
文本分析
Key words
suicide risk identification /
thematic apperception test /
machine learning /
speech recognition /
text analysis
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 高一虹, 孟玲. (2019). 自杀倾向的话语表述——大学生“走饭”微博分析. 外语与外语教学, 1, 43-55.
[2] 管理, 郝碧波, 刘天俐, 程绮瑾, 叶兆辉, 朱廷劭. (2015). 新浪微博用户中自杀死亡和无自杀意念者特征差异的研究. 中华流行病学杂志, 36(5), 421-425.
[3] 吉沅洪. (2020). 图片物语: 主题统觉测试(TAT)心理案例分析. 华东师范大学出版社.
[4] 李献云, 费立鹏, 童永胜, 李可进, 张亚利, 张艳萍, 牛雅娟. (2010). Beck自杀意念量表中文版在社区成年人群中应用的信效度. 中国心理卫生杂志, 24(4), 250-255.
[5] 王呈珊, 宋新明, 朱廷劭, 张钟杰, 刘天俐. (2021). 一位自杀博主遗言评论留言的主题分析. 中国心理卫生杂志, 35(2), 121-126.
[6] 王梦茜. (2020). 自杀在线预防: 愿他们鼓起勇气, 踏过荆棘. 教育家, 38, 35-37.
[7] 喻婷, 胡德英, 许珂, 周依, 滕芬. (2020). 自杀风险非传统评估法的研究进展. 护理研究, 34(1), 86-90.
[8] Basu, J. (2014). Psychologists' ambivalence toward ambiguity: Relocating the projective test debate for multiple interpretative hypotheses. Journal of Projective Psychology and Mental Health, 21(1), 25-36.
[9] Beck, A. T., & Steer, R. A. (1991). Manual for the beck scale for suicide ideation. Psychological Corporation.
[10] Bedford A., Watson R., Lyne J., Tibbles J., Davies F., & Deary I. J. (2010). Mokken scaling and principal components analyses of the CORE-OM in a large clinical sample. Clinical Psychology and Psychotherapy, 17(1), 51-62.
[11] Belouali A., Gupta S., Sourirajan V., Yu J. W., Allen N., Alaoui A., & Reinhard M. J. (2021). Acoustic and language analysis of speech for suicidal ideation among US veterans. BioData Mining, 14(1), 11.
[12] Bernert R. A., Hilberg A. M., Melia R., Kim J. P., Shah N. H., & Abnousi F. (2020). Artificial intelligence and suicide prevention: A systematic review of machine learning investigations. International Journal of Environmental Research and Public Health, 17(16), 5929.
[13] Boudreaux E. D., Rundensteiner E., Liu F. F., Wang B., Larkin C., Agu E., & Davis-Martin R. E. (2021). Applying machine learning approaches to suicide prediction using healthcare data: Overview and future directions. Frontiers in Psychiatry, 12, 707916.
[14] Coll-Florit M., Climent S., Sanfilippo M., & Hernández-Encuentra E. (2021). Metaphors of depression. Studying first person accounts of life with depression published in blogs. Metaphor and Symbol, 36(1), 1-19.
[15] Cummins N., Scherer S., Krajewski J., Schnieder S., Epps J., & Quatieri T. F. (2015). A review of depression and suicide risk assessment using speech analysis. Speech Communication, 71(1), 10-49.
[16] D'mello, S. K., & Kory, J. (2015). A review and meta-analysis of multimodal affect detection systems. ACM Computing Surveys, 47(3), 1-36.
[17] Ellis T. E., Rufino K. A., & Green K. L. (2016). Implicit measure of life/death orientation predicts response of suicidal ideation to treatment in psychiatric inpatients. Archives of Suicide Research, 20(1), 59-68.
[18] Gao R., Hao B. B., Li H., Gao Y. S., & Zhu T. S. (2013). Developing simplified Chinese psychological linguistic analysis dictionary for microblog. International conference on brain and health informatics , Springer.
[19] Johar, S. (2015). Emotion, affect and personality in speech: The Bias of language and paralanguage. Springer.
[20] Millner A. J., Augenstein T. M., Visser K. H., Gallagher K., Vergara G. A., D' Angelo E. J., & Nock M. K. (2019). Implicit cognitions as a behavioral marker of suicide attempts in adolescents. Archives of Suicide Research, 23(1), 47-63.
[21] Pestian J. P., Santel D., Sorter M., Bayram U., Connolly B., Glauser T., & Cohen K. (2020). A machine learning approach to identifying changes in suicidal language. Suicide and Life-Threatening Behavior, 50(5), 939-947.
[22] Pestian J. P., Sorter M., Connolly B., Bretonnel Cohen K., McCullumsmith C., Gee J. T., & Group, S. T. M. R. (2017). A machine learning approach to identifying the thought markers of suicidal subjects: A prospective multicenter trial. Suicide and Life-Threatening Behavior, 47(1), 112-121.
[23] Rodriguez J. D., Perez A., & Lozano J. A. (2010). Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), 569-575.
[24] Rustad R. A., Small J. E., Jobes D. A., Safer M. A., & Peterson R. J. (2003). The impact of rock videos and music with suicidal content on thoughts and attitudes about suicide. Suicide and Life-Threatening Behavior, 33(2), 120-131.
[25] Torous J., Larsen M. E., Depp C., Cosco T. D., Barnett I., Nock M. K., & Firth J. (2018). Smartphones, sensors, and machine learning to advance real-time prediction and interventions for suicide prevention: A review of current progress and next steps. Current Psychiatry Reports, 20(7), 51
[26] Zhang Y., Hu J., Evans C., Jin L. W., Wu M. Y., Wang C. Y., & Chen G. P. (2020). Psychometric properties of the Chinese version of the clinical outcomes in routine evaluation-outcome measure (CORE-OM). British Journal of Guidance and Counselling, 48(2), 289-299.
基金
*本研究得到国家自然科学基金青年项目（31900767）“心理咨询中咨访关系的神经基础:基于来访者和咨询师大脑同步性的研究”、上海市科技计划项目资助（20dz2260300）和中央高校基本科研业务费专项资金的资助
PDF(984 KB)
