Article Preview
TopMany studies such as those of (Manisha et al., 2019), (Ramírez et al. 2020) (Kaur et al., 2021; Chang et al., 2022) have focused on building a performance report of five Machine Learning algorithms called Support Vector Machine, Random Forest, Decision Tree, Naïve Bayes, and Prism, with the aim of identifying, classifying suicide related text on twitter and providing to the research related to the suicide ideation on communication networks.
Effective methods are now available to analyze the feelings expressed in social networks (Dilan., 2021), (Hu et al., 2018). Several recent studies take advantage of this work for the detection and monitoring of suicidal ideation (Awwalu et al., 2020), (Rabani et al., 2020), (Levis et al., 2021) and depressive states (Cash et al., 2020), (Yao et al., 2021). These notes were analysed by developing supervised and unsupervised classifiers to identify the topics discussed as well as the emotions expressed by people who took action (Awwalu et al., 2020), (Meraliyev et al., 2021).
Rabani et al. (2020) use well-known machine learning algorithms for multi-classification of Suicidal risk on social media so that individuals having high risk could be identified and counselled properly to save precious human lives. The data has been experimented through four popular machine learning algorithms: Logistic Regression, Multinomial Naïve Bayes, Support Vector Machine and Decision tree. The results generated are impressive with F1 Score ranging from 74% to 97%. The Best performing algorithm was Decision tree that achieved an F-measure of 97%, 94% and 96% for classifying suicidal text into three levels of concern.