Early Detection of Depression Based on Textual Information in Social Media
Zhang Mengna1, Wang Junyan2, Long Yang3, Zhang Haofeng4*, Hu Yong1
1(Department of Preventive Health,Hospital of Nanjing University of Science and Technology, Nanjing 210094, China) 2(School of Computer Science and Engineering, University of New South Wales, Sydney 2052, Australia) 3(Department of Computer Science, Durham University, Durham DH13LE, UK) 4(School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China)
Abstract：The traditional method of diagnosing depression is through face-to-face assessment and conversation. However, many patients with depression are reluctant to seek medical attention at an early stage, which makes their condition worse. In order to judge the situation of patients with depression in the early stage, a detection model using time series features of social media textual information and multi-instance learning was proposed in this work. Considering that depressive symptoms will not appear immediately, the use of time series samples will be very important. Therefore, the unsupervised LSTM was used to extract time series features, binary classification was implemented by training a classifier, and a multi-instance learning model was exploited to solve the problem of unbalanced samples. Naive Bayes classifiers, random forests, multivariate social network learning and multimodal depression dictionary learning were used as benchmark methods firstly, and then the multi-instance learning with unsupervised LSTM time series functions was employed to detect depression more accurately. On the basis of the MDDL dataset, 200 survey subjects totally 7946 tweets were selected, and the training-test ratio was set as 8:2. Experimental results were following: the accuracy, precision, recall and F1 score reached 75.0%, 76.0%, 73.0%, and 74.5%, respectively, which demonstrated that it was feasible to use machine learning for early depression detection through text data in social media. In addition, a large number of ablation studies also verified that the method using time series features could achieve better performance than the traditional benchmark methods.
基金资助:国家自然科学基金(61872187,62072246);英国医学研究委员会创新基金(Medical Research Council (MRC) Innovation Fellowship (UK) under Grant No. MR/S003916/1)
通讯作者:* E-mail:zhanghf@njust.edu.cn
引用本文:
张梦娜, 王君岩, 龙洋, 张浩峰, 胡勇. 基于社交媒体中文本信息的早期抑郁症检测[J]. 中国生物医学工程学报, 2022, 41(1): 21-30.
Zhang Mengna, Wang Junyan, Long Yang, Zhang Haofeng, Hu Yong. Early Detection of Depression Based on Textual Information in Social Media. Chinese Journal of Biomedical Engineering, 2022, 41(1): 21-30.
[1] 刘潇雅,刘爽,郭冬月,等. 抑郁症脑电特异性研究进展[J]. 中国生物医学工程学报, 2020, 39(3):351-361. [2] National Institute of Mental Health (NIMH). Depression [DB/OL]. https://www.nimh.nih.gov/health/topics/depression/index.shtml, 2018-02-01/2021-03-07. [3] World Health Organization. Depression [DB/OL], https://www.who.int/news-room/fact-sheets/detail/depression, 2020-01-30/2021-03-07. [4] 季淑梅,苏新乐,荀兴苗,等. 大学生焦虑人群情绪冲突反应的脑功能网络研究[J].中国生物医学工程学报, 2020, 39(2): 145-151. [5] NHS Digital. Adult Psychiatric Morbidity Survey: Survey of Mental Health and Wellbeing [DB/OL]. https://digital.nhs.uk/data-and-information/ publications/statistical/adult-psychiatric-morbidity-survey/adult-psychiatric-morbidity-survey-survey-of-mental-health-and-wellbeing-england-2014, 2020-03-02/2021-03-07. [6] 美国精神医学学会. 精神障碍诊断与统计手册[M]. 第5版. 北京: 北京大学出版社, 2016. [7] Castillo R, Carlat D, Millon T, et al. Diagnostic and statistical manual of mental disorders [M]. Washington DC: American Psychiatric Association Press, 2007. [8] 冯静雯,赖虹宇,邓伟,等. 精神分裂症和抑郁症患者静息态脑电功率谱熵的对照研究[J]. 中国生物医学工程学报, 2019, 38 (4): 385-391. [9] Gratch J, Artstein R, Lucas G, et al. The distress analysis interview corpus of human and computer interviews[C] // Proceedings of the Ninth International Conference on Language Resources and Evaluation. Reykjavik: European Language Resources Association, 2014: 3123-3128. [10] Srimadhur N, Lalitha S. An end-to-end model for detection and assessment of depression levels using speech [J]. Procedia Computer Science, 2020, 171: 12-21. [11] Ma Xingchen, Yang Hongyu, Chen Qiang, et al. DepAudioNet: an efficient deep model for audio based depression classification[C]// Procedings of the Sixth Audio-Visual Emotion Challenge and Workshop. Amsterdam: IEEE, 2016: 35-42. [12] Zhao Ziping, Bao Zhongtian, Zhang Zixing, et al. Hierarchical attention transfer networks for depression assessment from speech[C]// Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: IEEE, 2020:7159-7163. [13] Vázquez-Romero A, Gallardo-Antolín A. Automatic detection of depression in speech using ensemble convolutional neural networks [J]. Entropy, 2020, 22(6): 688. [14] Negi H, Bhola T, Pillai M, et al. A novel approach for depression detection using audio sentiment analysis[C] // Proceedings of 4th International Conference on Computers & Management. Delhi: Elsevier, 2018:43-46. [15] Carneiro de Melo W, Granger E, Hadid A. Depression detection based on deep distribution learning [C] // Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP). Taipei: IEEE, 2019: 4544-4548. [16] Yang Le, Jiang Dongmei, Han Weijing, et al. DCNN and DNN based multi-modal depression recognition[C] // Proceedings of the 2017 7th International Conference on Affective Computing and Intelligent Interaction. San Antonio: IEEE, 2017: 484-489. [17] Yang Le, Jiang Dongmei, Sahli H. Integrating deep and shallow models for multi-modal depression analysis-hybrid architectures [J]. IEEE Transactions on Affective Computing, 2021, 12(1): 239-253. [18] Qureshi S, Saha S, Dias M. Multitask representation learning for multimodal estimation of depression level [J]. IEEE Intelligent Systems, 2019, 35(5): 45-52. [19] Park M, Cha C, and Cha M. Depressive moods of users portrayed in twitter[C] // Proceedings of the ACM SIGKDD Workshop on healthcare informatics (HI-KDD), New York: ACM, 2012:1-8. [20] Choudhury M, Gamon M, Counts S, et al. Predicting depression via social media[C] // Proceedings of the 27th Conference on Artificial Intelligence. Bellevue: AAAI, 2013: 1-10. [21] Shen Guangyao, Jia Jia, Nie Liqiang, et al. Depression detection via harvesting social media: A multimodal dictionary learning solution[C] // Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne: Morgan Kaufmann, 2017, 3838-3844. [22] Kingma D, Ba J. Adam: A method for stochastic optimization[C] // Proceedings of the International Conference on Learning Representations. Venue, San Diego: ICLR, 2015:1-14. [23] Scholkopf B, Herbrich R, Smola A. A generalized representer theorem[C] //Proceedings of the International Conference on Computational Learning Theory. Amsterdam: Springer, 2001: 416-426. [24] Chang Chih-Chung and Lin Chih-Jen. LIBSVM: a library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):27:1-27. [25] Russell S, Norvig P. Artificial intelligence: A modern approach [M]. Malaysia: Pearson Education Limited, 2016. [26] McCallum A, Nigam K. A comparison of event models for naive Bayes text classification[C] // Proceedings of the Fifteenth Conference on Artificial Intelligence Workshop. Palo Alto: AAAI, 1998: 41-48. [27] Ho T. Random decision forests[C] // Proceedings of the 3rd International Conference on Document Analysis and Recognition. Montreal: IEEE, 1995: 278-282. [28] Song Xuemeng, Nie Liqiang, Zhang Luming, et al. Multiple social network learning and its application in volunteerism tendency prediction[C] // Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Santiago: ACM, 2015: 213-222. [29] Islam M, Kabir M, Ahmed A, et al. Depression detection from social network data using machine learning techniques[J]. Health information science and systems, 2018, 6(1): 1-12. [30] Cacheda F, Fernandez D, Novoa F, et al. Early detection of depression: social network analysis and random forest techniques [J]. Journal of Medical Internet Research, 2019, 21(6): e12554. [31] Lin C, Hu P, Su H, et al. Sensemood: Depression detection on social media[C]//Proceedings of the 2020 International Conference on Multimedia Retrieval. Taiwan: ACM, 2020: 407-411. [32] Gui T, Zhang Q, Zhu L, et al. Depression Detection on Social Media with Reinforcement Learning[C]//China National Conference on Chinese Computational Linguistics. Kunming: Springer, 2019: 613-624. [33] Jang B, Kim I, Kim J. Word2vec convolutional neural networks for classification of news articles and tweets [J]. PLoS ONE, 2019, 14(8): 1-20. [34] Hu X, Shu J, Jin Z. Depression tendency detection model for Weibo users based on Bi-LSTM[C]//2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). Dalian: IEEE, 2021: 785-790.
