Alghowinem Sharifa, Gedeon Tom, Goecke Roland, Cohn Jeffrey F, Parker Gordon
Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA, with Prince Sultan University, Riyadh, Saudi Arabia and with the Australian National University, Canberra, Australia.
Australian National University, Canberra, Australia.
IEEE Trans Affect Comput. 2023 Jan-Mar;14(1):133-152. doi: 10.1109/taffc.2020.3035535. Epub 2020 Nov 10.
Given the prevalence of depression worldwide and its major impact on society, several studies employed artificial intelligence modelling to automatically detect and assess depression. However, interpretation of these models and cues are rarely discussed in detail in the AI community, but have received increased attention lately. In this study, we aim to analyse the commonly selected features using a proposed framework of several feature selection methods and their effect on the classification results, which will provide an interpretation of the depression detection model. The developed framework aggregates and selects the most promising features for modelling depression detection from 38 feature selection algorithms of different categories. Using three real-world depression datasets, 902 behavioural cues were extracted from speech behaviour, speech prosody, eye movement and head pose. To verify the generalisability of the proposed framework, we applied the entire process to depression datasets individually and when combined. The results from the proposed framework showed that speech behaviour features (e.g. pauses) are the most distinctive features of the depression detection model. From the speech prosody modality, the strongest feature groups were F0, HNR, formants, and MFCC, while for the eye activity modality they were left-right eye movement and gaze direction, and for the head modality it was yaw head movement. Modelling depression detection using the selected features (even though there are only 9 features) outperformed using all features in all the individual and combined datasets. Our feature selection framework did not only provide an interpretation of the model, but was also able to produce a higher accuracy of depression detection with a small number of features in varied datasets. This could help to reduce the processing time needed to extract features and creating the model.
鉴于抑郁症在全球的流行及其对社会的重大影响，多项研究采用人工智能建模来自动检测和评估抑郁症。然而，人工智能社区很少详细讨论这些模型和线索的解释，但最近受到了越来越多的关注。在本研究中，我们旨在使用一个由多种特征选择方法组成的框架来分析常用的特征及其对分类结果的影响，这将为抑郁症检测模型提供一种解释。所开发的框架从不同类别的38种特征选择算法中聚合并选择最有前景的特征来对抑郁症检测进行建模。使用三个真实世界的抑郁症数据集，从言语行为、言语韵律、眼球运动和头部姿势中提取了902个行为线索。为了验证所提出框架的通用性，我们将整个过程分别应用于各个抑郁症数据集以及组合后的数据集。所提出框架的结果表明，言语行为特征（如停顿）是抑郁症检测模型中最具特色的特征。在言语韵律模态中，最强的特征组是基频（F0）、谐噪比（HNR）、共振峰和梅尔频率倒谱系数（MFCC），而在眼球活动模态中是左右眼球运动和注视方向，在头部模态中是偏航头部运动。使用所选特征（尽管只有9个特征）对抑郁症检测进行建模在所有单独和组合的数据集中都优于使用所有特征。我们的特征选择框架不仅为模型提供了解释，而且还能够在不同数据集中用少量特征产生更高的抑郁症检测准确率。这有助于减少提取特征和创建模型所需的处理时间。
