access icon free Public bus commuter assistance through the named entity recognition of twitter feeds and intelligent route finding

Karachi (Pakistan) has recently been subject to violent incidents targeted primarily at civilians. These incidents are problematic for commuters who use the public bus system and who often fail to reach their work organisations due to consequent bus strikes. This series of events leads to considerable financial losses for the transport industry. This study proposes and implements safe and fast around the road (SAFAR) which is an intelligent transport Android application developed in collaboration with the local transport authority of Karachi. SAFAR provides run-time information to bus commuters regarding recent violent activities farther up from the current location of the commuters on their route. SAFAR employs live Twitter feeds to classify the manner, location, and casualty information of the violence. The authors investigate SAFAR's performance offline with three named entity recognition (NER) approaches, namely, supervised, dictionary-based, and integrated (hybrid), and show that the integrated approach has the best performance with a precision of 85%. Furthermore, SAFAR recommends alternate routes to commuters if violence is detected farther up through the A-star (A*) algorithm. An online evaluation of SAFAR with 50 real users gave a precision of ∼85% to identify violence locations. Finally, a subjective evaluation showed that SAFAR's performance is satisfactory.

Inspec keywords: graphical user interfaces; public transport; pattern classification; intelligent transportation systems; social networking (online); vehicle routing; Android (operating system); learning (artificial intelligence)

Other keywords: traffic routines; A-star algorithm; bus commuters; violent incidents; violent activities; Twitter feeds; SAFAR GUI; SAFAR performance; A* algorithm; supervised dictionary-based integrated approaches; online SAFAR evaluation; SAFAR; local transport authority; intelligent transport Android application; integrated NER; Pakistan; run-time information; safe and fast around the road; Karachi; named entity recognition; public bus system

Subjects: Knowledge engineering techniques; Traffic engineering computing; Mobile, ubiquitous and pervasive computing; Data handling techniques; Graphical user interfaces; Information networks

References

    1. 1)
      • 28. McCallum, A., Freitag, D., Pereira, F.C.: ‘Maximum entropy Markov models for information extraction and segmentation’. ICML, 2000, pp. 591598.
    2. 2)
      • 22. Twitter4J: ‘Documentation’, 2014. Available at: https://dev.twitter.com/docs.
    3. 3)
      • 9. Krüger, R., Lohmann, S., Thom, D., et al: ‘Using social media content in the visual analysis of movement data’. 2nd Workshop on Interactive Visual Text Analytics, 2012.
    4. 4)
      • 21. Singh, B., Xu, K.: ‘Real time prediction of road traffic condition in London via twitter and related sources by’ (Middlesex University, 2012).
    5. 5)
      • 29. Kumar, A., Jiang, M., Fang, Y.: ‘Where not to go?: detecting road hazards using twitter’. Proc. of the 37th Int. ACM SIGIR Conf. on Research & Development in Information Retrieval, 2014, pp. 12231226.
    6. 6)
      • 10. Solon, O.: ‘Transport network re-routed based on mobile phone data’, 2013. Available at: http://www.wired.co.uk/news/archive/2013--05/1/bus-routes-mobile-data.
    7. 7)
      • 19. MacEachren, A.M., Robinson, A.C., Jaiswal, A., et al: ‘Geo-twitter analytics: applications in crisis management’. 25th Int. Cartographic Conf., 2011, pp. 38.
    8. 8)
      • 1. WorldPopulationReview: ‘Karachi Population 2015’, 2015. Available at http://worldpopulationreview.com/world-cities/karachi-population/.
    9. 9)
      • 26. Bikel, D.M., Schwartz, R., Weischedel, R.M.: ‘An algorithm that learns what's in a name’, Mach. Learn., 1999, 34, pp. 211231.
    10. 10)
      • 5. Moens, M.-F.: ‘Information extraction: algorithms and prospects in a retrieval context’, vol. 21 (Springer Science & Business Media, 2006).
    11. 11)
      • 11. Susan: ‘Israeli start-up provides real-time bus information’, 29 July 2013. Available at: http://www.thetransitwire.com/2013/07/29/israeli-start-up-provides-real-time-bus-information/.
    12. 12)
      • 23. Zia, T., Abbas, M.P.A.a.Q.: ‘Comparative study of feature selection approaches for Urdu text categorization’, Malaysian J. Comput. Sci., 2015, 28, pp. 93109.
    13. 13)
      • 14. Fishbach, S.: ‘Mobile Commons & New York MTA Launch Bus Time’, 2012. Available at: https://www.mobilecommons.com/blog/2012/01/mobile-commons-new-york-mta-launch-bus-time-press-release/.
    14. 14)
      • 16. OC: ‘OC Bus Tracker’, 2013. Available at: http://www.ocbustracker.com/d/.
    15. 15)
      • 3. KUTC: Karachi Urban Transport Carportaion, 2013. Available at http://www.kutckcr.com.
    16. 16)
      • 12. Georgetown: ‘New mobile App allows users to track guts buses’, 2013. Available at: http://www.georgetown.edu/news/nextguts-georgetown-mobile-app.html.
    17. 17)
      • 17. Google: ‘Live London Bus Tracker’, 2013. Available at: https://play.google.com/store/apps/details?id=com.appeffectsuk.bustracker&hl=en.
    18. 18)
      • 15. NEXTBus: ‘NEXTBus’, 2013. Available at: http://www.nextbus.com/predictor/agencySelector.jsp.
    19. 19)
      • 7. Wermter, J., Tomanek, K., Hahn, U.: ‘High-performance gene name normalization with GeNo’, Bioinformatics, 2009, 25, pp. 815821.
    20. 20)
      • 20. Thom, D., Bosch, H., Koch, S., et al: ‘Spatiotemporal anomaly detection through visual analysis of geolocated twitter messages’. Pacific visualization Symp. (PacificVis), 2012 IEEE, 2012, pp. 4148.
    21. 21)
      • 2. Jabri, P.: ‘One Strike Day in Karachi Causes Rs3.15bn Loss to Economy’, 2012. Available at http://www.brecorder.com/top-news/108-pakistan-top-news/62082-one-strike-day-in-karachi-causes-rs315bn-loss-to-economy.html.
    22. 22)
      • 25. Sokolova, M., Lapalme, G.: ‘A systematic analysis of performance measures for classification tasks’, Inf. Process. Manage., 2009, 45, pp. 427437.
    23. 23)
      • 18. MacEachren, A.M., Jaiswal, A., Robinson, A.C., et al: ‘Senseplace2: Geotwitter analytics support for situational awareness’. Visual Analytics Science and Technology (VAST), 2011 IEEE Conf. on, 2011, pp. 181190.
    24. 24)
      • 8. Russell, S., Norvig, P.: ‘Artificial intelligence: a modern approach’, 1995.
    25. 25)
      • 24. Shafiei, M., Wang, S., Zhang, R., et al: ‘Document representation and dimension reduction for text clustering’. Data Engineering Workshop, 2007 IEEE 23rd Int. Conf. on, 2007, pp. 770779.
    26. 26)
      • 27. Michalski, R.S., Carbonell, J.G., Mitchell, T.M.: ‘Machine learning: an artificial intelligence approach’ (Springer Science & Business Media, 2013).
    27. 27)
      • 6. Mahmood, T., Mujtaba, G., Shuib, L., et al: ‘Mobile-based intelligent transportation for bus commuters based on twitter analytics’. Frontiers of Information Technology (FIT), 2016 Int. Conf. on, 2016, pp. 223228.
    28. 28)
      • 4. Manning, C.D., Schütze, H.: ‘Foundations of statistical natural language processing’, vol. 999 (MIT Press, 1999).
    29. 29)
      • 13. Minnesota: ‘Next Bus’, 2011. Available at: http://www1.umn.edu/pts/bus/nextbus.html.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2016.0224
Loading

Related content

content/journals/10.1049/iet-its.2016.0224
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading