Deep Learning for Depression Detection Using Twitter Data

Today social media became a communication line among people to share their happiness,sadness,and anger with their end-users.It is necessary to know people’s emotions are very important to identify depressed people from their messages.Early depression detection helps to save people’s lives and other dangerous mental diseases.There are many intelligent algorithms for predicting depression with high accuracy,but they lack the definition of such cases.Several machine learning methods help to identify depressed people.But the accuracy of existing methods was not satisfactory.To overcome this issue,the deep learning method is used in the proposed method for depression detection.In this paper,a novel Deep Learning Multi-Aspect Depression Detection with Hierarchical Atten-tion Network(MDHAN)is used for classifying the depression data.Initially,the Twitter data was preprocessed by tokenization,punctuation mark removal,stop word removal,stemming,and lemmatization.The Adaptive Particle and grey Wolf optimization methods are used for feature selection.The MDHAN classifies the Twitter data and predicts the depressed and non-depressed users.Finally,the proposed method is compared with existing methods such as Convolutional Neur-al Network(CNN),Support Vector Machine(SVM),Minimum Description Length(MDL),and MDHAN.The suggested MDH-PWO architecture gains 99.86%accuracy,more significant than frequency-based deep learning models,with a lower false-positive rate.The experimental result shows that the proposed method achieves better accuracy,precision,recall,and F1-measure.It also mini-mizes the execution time.

An Automated and Real-time Approach of Depression Detection from Facial Micro-expressions

Depression is a mental psychological disorder that may cause a physical disorder or lead to death.It is highly impactful on the socialeconomical life of a person;therefore,its effective and timely detection is needful.Despite speech and gait,facial expressions have valuable clues to depression.This study proposes a depression detection system based on facial expression analysis.Facial features have been used for depression detection using Support Vector Machine(SVM)and Convolutional Neural Network(CNN).We extracted micro-expressions using Facial Action Coding System(FACS)as Action Units(AUs)correlated with the sad,disgust,and contempt features for depression detection.A CNN-based model is also proposed in this study to auto classify depressed subjects from images or videos in real-time.Experiments have been performed on the dataset obtained from Bahawal Victoria Hospital,Bahawalpur,Pakistan,as per the patient health questionnaire depression scale(PHQ-8);for inferring the mental condition of a patient.The experiments revealed 99.9%validation accuracy on the proposed CNN model,while extracted features obtained 100%accuracy on SVM.Moreover,the results proved the superiority of the reported approach over state-of-the-art methods.

EliteVec: Feature Fusion for Depression Diagnosis Using Optimized Long Short-Term Memory Network

Globally,depression is perceived as the most recurrent and risky disor-der among young people and adults under the age of 60.Depression has a strong influence on the usage of words which can be observed in the form of written texts or stories posted on social media.With the help of Natural Language Proces-sing(NLP)and Machine Learning(ML)techniques,the depressive signs expressed by people can be identified at the earliest stage from their Social Media posts.The proposed work aims to introduce an efficacious depression detection model unifying an exemplary feature extraction scheme and a hybrid Long Short-Term Memory network(LSTM)model.The feature extraction process combines a novel feature selection method called Elite Term Score(ETS)and Word2Vec to extract the syntactic and semantic information respectively.First,the ETS method leverages the document level,class level,and corpus level prob-abilities for computing the weightage/score of the terms.Then,the ideal and per-tinent set of features with a high ETS score is selected,and the Word2vec model is trained to generate the intense feature vector representation for the set of selected terms.Finally,the resultant word vector obtained is called EliteVec,which is fed to the hybrid LSTM model based on Honey Badger optimizer with population reduction technique(PHB)which predicts whether the input textual content is depressive or not.The PHB algorithm is integrated to explore and exploit the opti-mal hyperparameters for strengthening the performance of the LSTM network.The comprehensive experiments are carried out with two different Twitter depres-sion corpus based on accuracy and Root Mean Square Error(RMSE)metrics.The results demonstrated that the proposed EliteVec+LSTM+PHB model outperforms the state-of-art models with 98.1%accuracy and 0.0559 RMSE.

Attention-Based Bi-LSTM Model for Arabic Depression Classification

Depression is a common mental health issue that affects a large percentage of people all around the world.Usually,people who suffer from this mood disorder have issues such as low concentration,dementia,mood swings,and even suicide.A social media platform like Twitter allows people to communicate as well as share photos and videos that reflect their moods.Therefore,the analysis of social media content provides insight into individual moods,including depression.Several studies have been conducted on depression detection in English and less in Arabic.The detection of depression from Arabic social media lags behind due the complexity of Arabic language and the lack of resources and techniques available.In this study,we performed a depression analysis on Arabic social media content to understand the feelings of the users.A bidirectional long short-term memory(Bi-LSTM)with an attention mechanism is presented to learn important hidden features for depression detection successfully.The proposed deep learning model combines an attention mechanism with a Bi-LSTM to simultaneously focus on discriminative features and learn significant word weights that contribute highly to depression detection.In order to evaluate our model,we collected a Twitter dataset of approximately 6000 tweets.The data labelling was done by manually classifying tweets as depressed or not depressed.Experimental results showed that the proposed model outperformed state-of-the-art machine learning models in detecting depression.The attention-based BiLSTM model achieved 0.83%accuracy on the depression detection task.