2016 International Conference on Frontiers of Information Technology (FIT) (2016)
Dec. 19, 2016 to Dec. 21, 2016
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FIT.2016.048
In this paper, we present an intelligent, state-of-the-art, mobile-based transportation system called SAFAR (Safe and Fast around the Road), which provides dynamic information to Karachi bus commuters concerning any type of violence incident which has occurred farther ahead from their current location on the current bus route. Using named entity recognition techniques, we have trained SAFAR to recognize the location and method of violence incident along with the casualty information (if available) from live Twitter news feeds. Using the well-known A* heuristic search algorithm, SAFAR also recommends alternative routes to reach the destination in case of any violence up ahead. SAFAR has a competitive violence detection accuracy of 80% on a test corpus as well as in an online evaluation with real users. Finally, a subjective evaluation of these users reveals satisfactory performance of SAFAR across several dimensions.
Training, Twitter, Testing, Electronic mail, Computer science, Roads,Twitter, Bus Commuters, Expert System, Android, Violence Detection, Named Entity Recognition
Tariq Mahmood, Ghulam Mujtaba, Liyana Shuib, Nikkishah Zulfiqar Ali, Amir Bawa, Saima Karim, "Mobile-Based Intelligent Transportation for Bus Commuters Based on Twitter Analytics", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 223-228, 2016, doi:10.1109/FIT.2016.048