用於憂鬱症偵測之多模態時間注意力網路

Multimodal Time-Aware Attention Networks for Depression Detection

鄭如君(Ju-Chun Cheng)

指導教授 ： 陳良弼

國立清華大學/電機資訊學院/資訊系統與應用研究所/碩士(2021年)

摘要

憂鬱症是一種很常見的心理疾病，當病情嚴重時會有自殘或自殺的想法及行為，但因為資源不足、沒有病識感或擔心社會觀感等原因使得只有少部分的患者得到治療。隨著科技的發展，全球一半以上的人口在社群媒體上隨時隨地分享他們的想法及心情，使得社群媒體的資料很適合用於研究憂鬱症。我們在研究中使用Instagram這個平台的資料做憂鬱症偵測。我們用主題標籤(hashtag)來搜集使用者，並根據他們的自我陳述將他們標記為憂鬱或非憂鬱。我們同時使用了文字、圖片以及發文時間來偵測憂鬱症。此外，我們認為發文間隔是很重要的資訊，因此使用了適用於不規則時間間隔的長短期記憶模型，並使用注意力機制根據發文的重要程度給予不同的權重。實驗結果顯示我們提出的方法優於先前的研究，達到95.6%的F1-score。除了在Instagram得到良好的表現外，我們的方法在Twitter上的憂鬱症偵測也得到不錯的結果。這些都顯示了我們的模型能夠作為精神科醫師評估病人時的參考資料，也能幫助社群媒體使用者更了解自己的心理健康狀況。

關鍵字

憂鬱症偵測 ； 深度學習 ； 社群媒體

並列摘要

Depression is a common mental disorder, which may lead to suicide when the condition is severe. With the advancement of technology, there are billions of people who share their thoughts and feelings on social media at any time and from any location. Social media data has therefore become a valuable resource to study and detect the depression of the user. In our work, we use Instagram as the platform to study depression detection. We use hashtags to find users and label them as depressive or non-depressive according to their self-statement. Text, image, and posting time are used jointly to detect depression. Furthermore, the time interval between posts is important information when studying medical-related data. In this thesis, we use time-aware LSTM to handle the irregularity of time intervals in social media data and use an attention mechanism to pay more attention to the posts that are important for detecting depression. Experiment results show that our model outperforms previous work with an F1-score of 95.6%. In addition to the good performance on Instagram, our model also outperforms state-of-the-art methods in detecting depression on Twitter with an F1-score of 90.8%. This indicates the potential of our model to be a reference for psychiatrists to assess the patient; or for users to know more about their mental health condition.

並列關鍵字

Depression Detection ； Deep Learning ； Social Media

參考文獻

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., . . . Tucker, P. (2016). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, (pp. 265-283).

An, M., Wang, J., Li, S., & Zhou, G. (2020). Multimodal Topic-Enriched Auxiliary Learning for Depression Detection. Proceedings of the 28th International Conference on Computational Linguistics, (pp. 1078–1089).

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. Proceedings of the International Conference on Learning Representations.

Baytas, I. M., Xiao, C., Zhang, X., Wang, F., Jain, A. K., & Zhou, J. (2017). Patient Subtyping via Time-Aware LSTM Networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (pp. 65-74).

Beck, A. T., Steer, R. A., & Brown, G. K. (1996). Beck Depression Inventory-II.