Detection of Depression from Arabic Tweets Using Machine Learning

• DOI: 10.61356/smij.2024.11103
• Publication Date: 2024-03-02T21:04:40Z
• Authors: Areej Alzoubi; Ahmad Alaiad; Khaled Alkhattib; Ahed J Alkhatib; Aseel Abu Aqoulah; Almo’men Bellah A...; Ola Hayajnah
• Keywords: Depression

Depression has become the disease of times and caused suffering disruption in lives millions people around world all ages. Method: We obtained 16,581 Arabic tweets, whether they express depression or not, symptoms contain for 1439 Arab Twitter users. classified user is depressed not. used many machine learning algorithms: DT, RF, Mutational Naïve Bayes, AdaBoost , we also feature extraction like BOW TF-IDF. The result: Our experiments showed that Bayes with TF-IDF had highest accuracy 86% when rating tweets. Conclusion: Caring mental health very important, as some measures must be taken to maintain early stages infection.