PROJECT TITLE:

Real-Time Detection of Traffic From Twitter Stream Analysis - 2015

ABSTRACT:

Social networks have been recently used as a supply of data for event detection, with particular reference to road tie up and car accidents. During this paper, we tend to gift a real-time monitoring system for traffic event detection from Twitter stream analysis. The system fetches tweets from Twitter according to several search criteria; processes tweets, by applying text mining techniques; and at last performs the classification of tweets. The aim is to assign the acceptable class label to every tweet, as related to a traffic event or not. The traffic detection system was used for real-time monitoring of several areas of the Italian road network, allowing for detection of traffic events almost in real time, often before on-line traffic news net sites. We have a tendency to used the support vector machine as a classification model, and we achieved an accuracy worth of ninety five.75p.c by solving a binary classification drawback (traffic versus nontraffic tweets). We tend to were additionally ready to discriminate if traffic is caused by an external event or not, by solving a multiclass classification problem and getting an accuracy worth of eighty eight.89p.c.