ABSTRACT
The COVID-19 pandemic has caused substantial damage to global health. Even though three years have passed, the world continues to struggle with the virus. Concerns are growing about the impact of COVID-19 on the mental health of infected individuals, who are more likely to experience depression, which can have long-lasting consequences for both the affected individuals and the world. Detection and intervention at an early stage can reduce the risk of depression in COVID-19 patients. In this paper, we investigated the relationship between COVID-19 infection and depression through social media analysis. Firstly, we managed a dataset of COVID-19 patients that contains information about their social media activity both before and after infection. Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression. Thirdly, we proposed a deep neural network for early prediction of depression risk. This model considers daily mood swings as a psychiatric signal and incorporates textual and emotional characteristics via knowledge distillation. Experimental results demonstrate that our proposed framework outperforms baselines in detecting depression risk, with an AUROC of 0.9317 and an AUPRC of 0.8116. Our model has the potential to enable public health organizations to initiate prompt intervention with high-risk patients. © 2023 ACM.
ABSTRACT
Depression has a large impact on one’s personal life, especially during the COVID-19 pandemic. People have been trying to develop reliable methods for the depression detection task. Recently, methods based on deep learning have attracted much attention from the research community. However, they still face the challenge that data collection and annotation are difficult and expensive. In many real-world applications, only a small number of or even no training data are available. In this context, we propose a Prompt-based Topic-modeling method for Depression Detection (PTDD) on low-resource data, aiming to establish an effective way of depression detection under the above challenging situation. Instead of learning discriminating features from a small amount of labeled data, the proposed framework turns to leverage the generalization power of pretrained language models. Specifically, based on the question-and-answer routine during the interview, we first reorganize the text data according to the predefined topics for each interviewee. Via the prompt-based framework, we then predict whether the next-sentence prompt is emotionally positive or not. Finally, the depression detection task can be achieved based on the obtained topicwise predictions through a simple voting process. In the experiments, we validate the effectiveness of our model under several low-resource data settings. The results and analysis demonstrate that our PTDD achieves acceptable performance when only a few training samples or even no training samples are available. IEEE
ABSTRACT
Depression is one of the leading factors in global disability and a top driver for suicides. Studies have shown that depression has an effect on language usage. In recent years, especially during the COVID pandemic, social media platforms have become the de facto platform for many individuals to self-disclose or discuss mental health issues like depression. This trend presents a unique opportunity for researchers and healthcare professionals to detect potential mental illnesses for early intervention or treatment by taking advantage of the recent advances in machine learning approaches. Existing depression detection methods on social media, however, suffer from two major limitations. First, these solutions heavily rely on the amount, quality, and type of user-posted content. Second, the overlooked social circle impact should be leveraged to enhance the prediction capabilities. In this paper, we propose a depression detection framework, MentalNet, based on heterogeneous graph convolution by capturing users' interactions (replies, mentions, and quotetiveets) with their friends on social media and differentiating the intimacy of users' social circles (e.g., family, friends, or acquaintances). Specifically, we formulate the problem of depression detection on social media as a graph classification problem by representing users' social circles in the format of heterogeneous graphs. MentalNet embraces three modules, (1) extraction of ego-network node features, (2) construction of user interaction graphs, and (3) depression detection based on heterogeneous graph classification. The extensive experiments on Twitter data demonstrate that MentalNet consistently and significantly outperforms the state-of-the-art methods in terms of all the effectiveness metrics. Compared to the baseline methods, MentalNet is able to effectively predict early depression in Twitter users with up to 24% improvement on F1 score. © 2022 IEEE.
ABSTRACT
Depression is a common cause of increased suicides worldwide, and studies have shown that the number of patients suffering from major depressive disorder (MDD) increased several-fold during the COVID-19 pandemic, highlighting the importance of disease detection and depression management, while increasing the need for effective diagnostic tools. In recent years, machine learning and deep learning methods based on electroencephalography (EEG) have achieved significant results in the field of automatic depression detection. However, most current studies have focused on a small number of EEG signal channels, and experimental data require special processing by professionals. In this study, 128 channels of EEG signals were simply filtered and 24-fold leave-one-out cross-validation experiments were performed using 2DCNN-LSTM classifier, support vector machine, K-nearest neighbor and decision tree. The current results show that the proposed 2DCNN-LSTM model has an average classification accuracy of 95.1% with an AUC of 0.98 for depression detection of 6-second participant EEG signals, and the model is much better than 72.05%, 79.7% and 79.49% for support vector machine, K nearest neighbor and decision tree. In addition, we found that the model achieved a 100% probability of correctly classifying the EEG signals of 300-second participants.
ABSTRACT
Introduction: As a biomarker of depression, speech signal has attracted the interest of many researchers due to its characteristics of easy collection and non-invasive. However, subjects' speech variation under different scenes and emotional stimuli, the insufficient amount of depression speech data for deep learning, and the variable length of speech frame-level features have an impact on the recognition performance. Methods: The above problems, this study proposes a multi-task ensemble learning method based on speaker embeddings for depression classification. First, we extract the Mel Frequency Cepstral Coefficients (MFCC), the Perceptual Linear Predictive Coefficients (PLP), and the Filter Bank (FBANK) from the out-domain dataset (CN-Celeb) and train the Resnet x-vector extractor, Time delay neural network (TDNN) x-vector extractor, and i-vector extractor. Then, we extract the corresponding speaker embeddings of fixed length from the depression speech database of the Gansu Provincial Key Laboratory of Wearable Computing. Support Vector Machine (SVM) and Random Forest (RF) are used to obtain the classification results of speaker embeddings in nine speech tasks. To make full use of the information of speech tasks with different scenes and emotions, we aggregate the classification results of nine tasks into new features and then obtain the final classification results by using Multilayer Perceptron (MLP). In order to take advantage of the complementary effects of different features, Resnet x-vectors based on different acoustic features are fused in the ensemble learning method. Results: Experimental results demonstrate that (1) MFCC-based Resnet x-vectors perform best among the nine speaker embeddings for depression detection; (2) interview speech is better than picture descriptions speech, and neutral stimulus is the best among the three emotional valences in the depression recognition task; (3) our multi-task ensemble learning method with MFCC-based Resnet x-vectors can effectively identify depressed patients; (4) in all cases, the combination of MFCC-based Resnet x-vectors and PLP-based Resnet x-vectors in our ensemble learning method achieves the best results, outperforming other literature studies using the depression speech database. Discussion: Our multi-task ensemble learning method with MFCC-based Resnet x-vectors can fuse the depression related information of different stimuli effectively, which provides a new approach for depression detection. The limitation of this method is that speaker embeddings extractors were pre-trained on the out-domain dataset. We will consider using the augmented in-domain dataset for pre-training to improve the depression recognition performance further.
ABSTRACT
Depression has become a global concern, and COVID-19 also has caused a big surge in its incidence. Broadly, there are two primary methods of detecting depression: Task-based and Mobile Crowd Sensing (MCS) based methods. These two approaches, when integrated, can complement each other. This paper proposes a novel approach for depression detection that combines real-time MCS and task-based mechanisms. We aim to design an end-to-end machine learning pipeline, which involves multimodal data collection, feature extraction, feature selection, fusion, and classification to distinguish between depressed and non-depressed subjects. For this purpose, we created a real-world dataset of depressed and non-depressed subjects. We experimented with: various features from multi-modalities, feature selection techniques, fused features, and machine learning classifiers such as Logistic Regression, Support Vector Machines (SVM), etc. for classification. Our findings suggest that combining features from multiple modalities perform better than any single data modality, and the best classification accuracy is achieved when features from all three data modalities are fused. Feature selection method based on Pearson's correlation coefficients improved the accuracy in comparison with other methods. Also, SVM yielded the best accuracy of 86%. Our proposed approach was also applied on benchmarking dataset, and results demonstrated that the multimodal approach is advantageous in performance with state-of-the-art depression recognition techniques.
ABSTRACT
Early depression detection is crucial for both people at risk and the whole society. After the COVID-19 pandemic, the depression level is expected to get higher. Social media is an affluent source of users' opinions and feelings that can be used to detect depression. Depression detection from users' tweets is a challenging task that many researchers have tried to tackle recently as it depends on the whole tweet context. This work introduces a machine learning-based approach for depression detection from tweets. We first obtained a tweets depression detection dataset and use it to train different machine learning and deep learning models for depression detection. We trained some classical machine learning models, then we also fine-tuned the state-of-the-art transformer-based pre-trained language models like BERT, RoBERTa, MobileBERT, and DistilBERT. Our best model was RoBERTa gaining a 78.85 percent F1-score on the test set. This model has then been used to pseudo-label two different datasets of about 4.35 million tweets from about 1 million Twitter users related to COVID-19 and vaccination to gain more deep insights on COVID-19 effect on the depression level of social media users. We show that depression level got doubled from four percent to eight percent from the beginning to the end of March 2020. Depression also increased after nearly two years to reach 15 percent in December 2021. The boosting of the level of depression should be taken into consideration by mental health institutions. © 2022 IEEE.
ABSTRACT
Depression is one of the major causes of increased number of cases of mental illness and suicides all over the globe now a days. A person suffering from anxiety, sadness, depression or suicidal thoughts finds it easier to express his emotions on social media platforms. Thus, the messages or content shared by a person on social media platforms is the best way to detect the mental condition of a person by analysing these messages. Today’s situation of pandemic covid19 also increased the cases of depression. In this paper we have used Natural Language processing techniques and deep learning methods to create a model to predict such mental conditions like depression. The model created using LSTM-CNN gives better accuracy of 97% when compared to the other base models of logistic regression, Naïve Bayes, Random Forest and Decision Tree. © 2022 American Institute of Physics Inc.. All rights reserved.
ABSTRACT
The risk for depression and anxiety increased as people adjusted to a new normal after the COVID-19 pandemic. Early detection and appropriate onset treatment and support can reduce the consequences of depression. Automatic detection of depression in social media has recently become an important area of investigation. However, because of the lack of extensive annotated data, we propose a method for using a model that learns to answer a depression questionnaire and apply it to make populationlevel predictions. We used the eRisk 2021 Task 3 training dataset to build an automated model to fill the Beck's Depression Inventory (BDI) questionnaire. We selected the best performing model for each group of questions based on predefined metrics and consolidated those models into one model (called the BDI _Multi_Model). The BDI _Multi_Model achieved better performance than the state-of-the-art for this challenging task. Then, we used this model for inference on a Canadian population dataset and compared its predictions with the statistics of the most recent mental health survey conducted by Statistics Canada. The correlation between the inference of the answered questionnaire based on our BDI _Multi_Model and the official statistics showed a strong Pearson correlation of 0:90.
ABSTRACT
This study proposes depression detection systems based on the i-vector framework for classifying speakers as depressed or healthy and predicting depression levels according to the Beck Depression Inventory-II (BDI-II). Linear and non-linear speech features are investigated as front-end features to i-vectors. To take advantage of the complementary effects of features, i-vector systems based on linear and non-linear features are combined through the decision-level fusion. Variability compensation techniques, such as Linear Discriminant Analysis (LDA) and Within-Class Covariance Normalization (WCCN), are widely used to reduce unwanted variabilities. A more generalizable technique than the LDA is required when limited training data are available. We employ a support vector discriminant analysis (SVDA) technique that uses the boundary of classes to find discriminatory directions to address this problem. Experiments conducted on the 2014 Audio-Visual Emotion Challenge and Workshop (AVEC 2014) depression database indicate that the best accuracy improvement obtained using SVDA is about 15.15% compared to the uncompensated i-vectors. In all cases, experimental results confirm that the decision-level fusion of i-vector systems based on three feature sets, TEO-CB-Auto-Env+Δ, Glottal+Δ, and MFCC+Δ+ΔΔ, achieves the best results. This fusion significantly improves classifying results, yielding an accuracy of 90%. The combination of SVDA-transformed BDI-II score prediction systems based on these three feature sets achieved RMSE and MAE of 8.899 and 6.991, respectively, which means 29.18% and 30.34% improvements in RMSE and MAE, respectively, over the baseline system on the test partition. Furthermore, this proposed combination outperforms other audio-based studies available in the literature using the AVEC 2014 database.
Subject(s)
Depression , Speech , Databases, Factual , Depression/diagnosis , Discriminant Analysis , EmotionsABSTRACT
COVID-19 has caused physical, emotional, and psychological distress for people. Due to COVID-19 norms, people were restricted to their homes and could not interact with other people, due to which they turned to social media to express their state of mind. In this paper, we implemented a system using TensorFlow, which consists of multilayer perceptron (MLP), convolutional neural networks (CNN), and long short-term memory (LSTM), which works on preprocessing, semantic information on our manually extracted dataset using Twint scraper. The models were used for classifying tweets, based upon whether they indicate depressive behavior or not. We experimented for different optimizer algorithms and their related hyperparameters for all the models. The highest accuracy was achieved by MLP using sentence embeddings, which gave an accuracy of 94% over 50 epochs, closely followed by the other two. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
During the coronavirus pandemic, the number of depression cases has dramatically increased. Several depression sufferers disclose their actual feeling via social media. Thus, big data analytics on social networks for real-time depression detection is proposed. This research work detected the depression by analyzing both demographic characteristics and opinions of Twitter users during a two-month period after having answered the Patient Health Questionnaire-9 used as an outcome measure. Machine learning techniques were applied as the detection model construction. There are five machine learning techniques explored in this research which are Support Vector Machine, Decision Tree, Naïve Bayes, Random Forest, and Deep Learning. The experimental results revealed that the Random Forest technique achieved higher accuracy than other techniques to detect the depression. This research contributes to the literature by introducing a novel model based on analyzing demographic characteristics and text sentiment of Twitter users. The model can capture depressive moods of depression sufferers. Thus, this work is a step towards reducing depression-induced suicide rates.
ABSTRACT
Cases of mental health issues are increasing continuously and have sped up due to COVID-19. There are high chances of developing mental health issues such as depression, anxiety, schizophrenia, and dementia after 2–3 months of COVID-19 diagnosis. In this paper, a review and meta-analysis of machine intelligence approaches—namely, machine learning, deep learning (deep learning with hybrid boosting), and machine vision methods—for mental health issues and depression detection were presented. Meta-analysis was performed in four parts. The first part focused on the publication trends, criteria for inclusion and exclusion, and the current methodological scenario. The second part was intended for the methods and their advantages and limitations. It covered mental health issues and depression detection techniques along with the challenges. The third part focused on the discussion and applicability of datasets. The fourth part focused on the complete analysis and discussion along with suggestive measures;moreover, it covered the overall analysis, including the methodological impact, result impact, current trends, and some suggestions based on the limitations and challenges. © The Authors.