MACHINE LEARNING ALGORITHMS COMPARATIVE STUDY ON SUICIDAL TEXT

Abstract

Machine learning is a branch of artificial intelligence that allows computers to recognize and exploit patterns in data to make predictions. Machine learning has become grown in popularity in recent years, particularly in the field of computer science, as it has been linked to a wide range of applications, including fraud detection, structured data, and recommender systems. Raw data, but vital client information, is constantly generated on social networking sites. However, when this data is mined using diverse methodologies, such as machine learning techniques, it becomes increasingly valuable. Moreover, a few studies showed a significant link between social media and suicide, this client-generated data could be used to potentially save lives, particularly of vulnerable social media users. We intend to contribute to the study of suicide communication on social media with our investigation. We evaluated the performance of the three machine learning algorithms: Naive Bayes, Random Forest, and Support Vector Machine by recognizing and classifying suicide-related information from Twitter.