Traffic Condition Monitoring Using Social Media Analytics

Scientist and practitioner seek innovations that analyze traffic big data for reducing congestion. In this chapter, we propose a framework for traffic condition monitoring using social media data analytics. This involves sentiment analysis and cluster classification utilizing the big data volume readily available through Twitter microblogging service. Firstly, we examine some key aspects of big data technology for traffic, transportation and information engineering systems. Secondly, we consider Parts of Speech tagging utilizing the simplified Phrase-Search and Forward-Position-Intersect algorithms. Then, we use the k-nearest neighbor classifier to obtain the unigram and bigram; followed by application of Naїve Bayes Algorithm to perform the sentiment analysis. Finally, we use the Jaccard Similarity and the Term Frequency-Inverse Document Frequency for cluster classification of traffic tweets data. The preliminary results show that the proposed methodology, comparatively tested for accuracy and precision with another approach employing Latent Dirichlet Allocation is sufficient for predicting traffic flow in order to effectively improve the road traffic condition.