Selected Article

Title

CRIME PREDICTION USING SOCIAL SENTIMENT AND SOCIO-FACTOR

Description

Crime prediction becomes very important trend and akey technique in crime analysis to identify the optimal patrol strategy forpolice department. Many researchers have found number of techniques andsolutions to analyze crime, using data mining techniques. These studies canhelp to speed up and computerize the process of crime analysis processes. However, the pattern of crime is flexible, italways changes and grows. With social media, user posts and discusses eventpublicly. These textual data of every user has contextual information of user’sdaily activities. These posts generate unstructured data that can be used fordata prediction. As shown by previous research, twitter sentiment enable topredict crime in Chicago, United States. However, existed model on crimeprediction was incorporating the use of socio factors. Therefore, the studyaims to model crime prediction using social media content with additionalsocio-factors. The research approach is consisted of a combination of sentimentanalysis from Twitter and social-factors with Kernel Density Estimation.Lexicon-base methods will be applied for sentiment analysis, and the modelevaluation is measured with the help of logistic regression.