Detection of Suicidal Tweets Based On Naïve Bayes Algorithm

The pandemic has created a trend where most people have become addicted to the social media express thoughts, opinions, share reviews and also their daily life online. This contributed increasing volume of data over platforms. Based on these situations, been analyzed for benefits businesses organizations. Various sentiment analysis research conducted obtain public opinions such as products situations. Twitter one visited due platform’s convenience easiness in texting messages. proposed analyze detection suicidal intention. is help many depressed who affected by Covid-19 analyzing thoughts Identifying this behaviour tweets can be first step suicide prevention. objective explore Naïve Bayes algorithm’s capability detect ideation tweets. were scrapped during Malaysia’s lockdown May 2021 using Tweepy library. There 5439 that based “stress”, “anxiety”, “depression” “suicide” keywords. evaluation results shown algorithm produced good acceptable performance detecting with 80.39% accuracy. result more are actually duirng pandemic, especilly lockdown. Future works would compare other well-known classifiers consider scrapping processing non-English words from platforms Facebook Instagram.