Optimal path finding based on traffic information extraction from Twitter

Numerous path-finding applications do not take into account the actual condition on the road such as congestion or traffic situations. Since people share traffic information on Twitter, finding optimal route should consider this information. We discuss about Twitter-based traffic information extraction and its usage as heuristic in optimal path finding. Our system is divided into two modules: extraction information and path finding. We employed classification approach for developing information extraction system. The steps in extraction information module are tokenization, normalization, named entity recognition, template element task, relation extraction, and information filling. According to our experiments, Named Entity Relationship (NER) task gave out an average F-measure of 91.2% while Relation Extraction (RE) task resulted in 80.7%. The path finding module is divided into several steps which are heuristic extraction, route planning, and visualization. Our system displays a map with marked route based on traffic information extracted from Twitter.