A Framework to Predict Social Crimes using Twitter Tweets
C M Sreya · International Journal for Research in Applied Science and Engineering Technology · 2021
Now a day's new wave of social media technologies like facebook, blogs, twitter plays an important role in formal and informal communications.In social media like twitter, users share their ideas, thoughts, and news in under 280 characters of text.An increasing amount of data coming from social networks can be used to generate a variety of data patterns for various sorts of investigation like human social behavior, system security, criminology etc.A framework is developed to predict major sorts of social media crimes (Cyber stalking, Cyber bullying, Cyber Hacking, Cyber Harassment, and Cyber Scam) using the data obtained from social media website.The proposed system contains three modules; data (tweet) pre-processing, classifying model builder and prediction.Data is interpreted using statistical models with Python.To create the prediction model, Multinomial Naïve Bayes (MNB), K-Nearest Neighbors (KNN) or Support Vector Machine model (SVM) classifiers can be employed that classify given data into different classes of crime.Further the accuracy of the system at different levels is measured.Results shows that each of the three algorithm attain the precision, Recall and F-measure above than 0.9.