Sentiment Analysis on Twitter Data for Depression Detection

Depression is currently the leading cause of disability worldwide, significantly increasing the disease burden.Depression impacts a person's thoughts, behavior, and quality of life.Since people nowadays tend to discuss their sentiments and thoughts regarding their mental health on social media, several researchers have recently investigated the analysis of social media material to identify and track sad users.Twitter is a popular platform for voicing people's opinions simply and directly.Therefore, numerous researchers have used Twitter to gain insights into depression.However, sentiment analysis (SA) becomes more complicated when the tweets combine two languages.This study aims to detect depression from tweets written in Malay and English languages.The data is retrieved from Twitter and pre-processed using the pre-processing approaches.Next, sentiments are extracted and labeled as positive, neutral, or negative.Bag of words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) are the feature extraction techniques applied to the sentiments.Machine Learning (ML) classifiers such as Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), and Long Short-Term Memory (LSTM) architecture, a Deep Learning (DL) technique, are used to analyze the dataset.The models' performance assessment includes the four standard measures, Receiver Operating Characteristic (ROC), and Area Under the Curve (AUC).The result shows that Support Vector Machine is the ideally suited model for our ongoing study.