Cyber Crime Identifying Using Machine Learning Techniques - Based Sentiment Analysis

Social media analytics is a form of information analytics that is quite important in today's cyber situation. Cybercrime is criminal behaviour based on computers and internet networks. Cybercriminals usually hack systems to obtain the personal information of victims. There are many types of cybercrimes. There are four types of cybercrimes: Phishing scams, Hacking, Cyber Stalking and Cyber Bullying. This research aims to help the process analysis by the Police or investigative institutions of the private sector in knowing the results of public sentiment on social media related to current cyber crimes. Ciber Crime identifying using machine learning techniques, based sentiment analysis. Method used for sentiment analysis related to cybercrime is Random Forest, Naïve Bayes, and KNN. The highest accuracy value of the three methods tried is the Naive Bayes algorithm of 99.45%. The highest precision value uses the Naive Bayes algorithm of 99.80%, and the highest recall value uses the random forest algorithm of 100%.