International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Mining Twitter for Road Traffic Event Detection

Author : Sujith M S ¹ Rahamathulla K ²

Date of Publication :7th May 2016

Abstract: a road traffic event detection, provides information for emergency traffic control and management purposes. Twitter is rapidly emerging as a efficient tool for the contribution and spreading of information that has an immense value for increasing awareness of traffic incidents. In this paper, a system for road traffic event detection from tweet analysis is presented. The system fetches tweets from Twitter according to several search criteria, processes the tweets by applying text mining techniques and finally classifies the tweets. The aim is to assign the appropriate class label to each tweet, whether related to a traffic event or not. The class labels used are non-traffic, traffic due to congestion or crash, and traffic due to external events. A combination of multi-class Support Vector Machine (SVM) and Decision tree classification algorithm is being implemented to classify tweets that reflect road traffic conditions. This can possibly help the drivers and concerned authorities to identify the traffic conditions in specified places.

Reference :

1. D Andrea,Ducange,Lazzerini,Marcellon. Real-time detection of traffic from twitter stream analysis,intelligent transportation systems, IEEE transactions on, 16(4), 2269- 2283.(2015).
2. Zhang, Shen. ”using twitter to enhance traffic incident awareness.”,intelligent transportation systems (itsc), 2015 ieee 18th international conference on. Ieee, 2015.
3. Wanichayapong, Napong, et al., social-based traffic information extraction and classification., .its telecommunications (itst), 2011 11th international conference on. Ieee, 2011.
4. Sakaki, Takeshi, et al., real-time event extraction for driving information from social sensors.,, cyber technology in automation, control, and intelligent systems (cyber), 2012 ieee international conference on. Ieee,2012
5. Hasby, Muhammad, And Masayu Leylia Khodra, optimal path finding based on traffic information extraction from twitter.,,ict for smart society (iciss), 2013 international conference on. Ieee, 2013
6. Wang,Al-Rubaie,Davies,Clarke, ”real time road traffic monitoring alert based on incremental learning from tweets”,.in evolving and autonomous learning systems (eals), 2014 ieee symposium on (pp. 50-57).ieee.(2014, december)
7. GUTIERREZ, C., FIGUERIAS, P., OLIVEIRA, P., COSTA, R.,JARDIM-goncalves,twitter mining for traffic events detection, . In science and informationconference (sai), 2015 (pp. 371-378). Ieee.(2015, july).
8. PARIKH, RUCHI, AND KAMALAKAR KARLAPALEM., ET: events from tweets., ,proceedings of the 22nd international conference on world wide web companion. International world wide web conferences steering committee, 2013.
9. MADANI, AMINA, OMAR BOUSSAID, AND DJAMEL EDDINE ZEGOUR., WHATS HAPPENING: A SURVEY OF TWEETS EVENT DETECTION., INNOV 2014 (2014): 3rd.
10. Nguyen, Thao, ”investigation of combining SVM and decision tree for emotion classification, multimedia, seventh IEEE INTERNATIONAL SYMPOSIUM ON. IEEE, 2005.
11. Sakaki, Takeshi, Masahide Okazaki, and yoshikazu matsuo., tweet analysis for real-time event detection and earthquake reporting system development, knowledge and data engineering, IEEE transactions on 25.4 (2013):919- 931.
12. mathur, a., and g. M. Foody., multiclass and binary SVM classification:implications for training and classification users., geoscience and remote sensing letters, ieee 5.2 (2008): 241-245.
13. duan, kai-bo, and s. Sathiya keerthi.,which is the best multiclass SVM method? An empirical study., multiple classifier systems. Springer berlin heidelberg, 2005. 278- 285.
14. takahashi, fumitake, and shigeo abe., d. ”decisiontree-based multiclass support vector machines.” Neural information processing, 2002.iconip’02. Proceedings of the 9th international conference on. Vol. 3.ieee, 2002.
15. perera, kushani, and dileeka dias., a. An intelligent driver guidance tool using location based services., spatial data mining and geographical knowledge services (icsdm), 2011 ieee international conference on.ieee, 2011.
16. using the twitter search api — twitter developers. [online]. Available: https://dev.twitter.com/docs/using-search. [accessed: 25- aug-2015].
17. lee, k., palsetia, d., narayanan, r., patwary, m. M. A., agrawal, a., & choudhary, a. (2011, december). Twitter trending topic classification. In data mining workshops (icdmw), 2011 ieee 11th international conference on (pp. 251-258). Ieee.
18. n. Cristianini and j. Shawe-taylor, an introduction to support vector machines and other kernel-based learning methods. Cambridge university press, 2000.
19. safavian, s. Rasoul, and david landgrebe. "a survey of decision tree classifier methodology." (1990).
20. d. M. Blei and j. D. Lafferty, “a correlated topic model of science,” the annals of applied statistics, vol. 1, no. 1, pp. 17–35, 2007.
21. y.-c. Wang, m. Burke, and r. E. Kraut, “gender, topic, and audience response: an analysis of user-generated content on facebook,” in proceedings of the sigchi conference on human factors in computing systems, 2013, pp. 31–34
22. quinlan, j. Ross. "induction of decision trees." machine learning 1.1 (1986): 81-106.
23. j. Weston and c. Watkins. Multi-class support vector machines. Technical report csd-tr-98-04, department of computer science, royal holloway,university of london, 1998.