Crime pattern detection using online social media
Raja Ashok Bolla · 2014
In this research, we show online social networks can be used to study crime detection problems. Crime is defined as an act harmful not only to the individual involved, but also to the community as a whole. It is also a forbidden act that is punishable by law. Crimes are social nuisances that place heavy financial burdens on society. Here we look at use of data mining followed by sentiment analysis on online social networks, to help detect the crime patterns. Twitter is an online social networking and microblogging service that enables users to post brief text updates, also referred to as tweets. These updates can convey important information about the author. A filter was designed to extract tweets from cities deemed to be either the most dangerous or the safest in the United States (US). A geographic analysis revealed a correlation between these tweets and the crimes that occurred in the corresponding cities. Over 100,000 crime-related tweets were collected over a period of 20 days. Sentiment analysis techniques were conducted on these tweets to analyze the crime intensity of a particular location. This type of study will help reveal the crime rate of a location in real-time. Although the results of this test helped in detecting crime patterns, the sentiment analysis techniques did not always guarantee the proper results. We conclude with applications of this type of study and how it can be improved by applying media to text processing techniques.