Tracking Commuter Train Intrudion Through Twitter Crawling
DOI:
https://doi.org/10.34123/jurnalasks.v8i1.14Keywords:
Twitter crawling, social network mining, commuter train, information extractionAbstract
Nowadays, Twitter is a very popular social media, especially in Indonesia. Tweets can be used as a data source to explore information. PT KAI (Kereta Api Indonesia) Commuter Jabodetabek (Jakarta, Bogor, Depok, Tangerang, Bekasi) (PT KCJ) has an official account, Twitter @CommuterLine, to disseminate information related to commuter train. One of important information regularly published in @CommuterLine account are information about commuter train intrusion. PT KCJ uses specific tweet format and certain hashtag to inform people about the intrusion. Intrusion information that is usually published is time of the intrusion, name of the station, train number and train line. #InfoLintas and #InfoLanjut hashtag are used to easier tweet searching. Information extraction processes are adopted to automatically extract commuter train intrusion information from @CommuterLine account Twitter. The statistical analysis about commuter train tweets are visualized in tables and graphs. A prototype system in the form of mobile application is developed to track commuter train intrusion based on the result of the information extraction.
Downloads
References
[2] F. Nooralahzadeh, V. Arunachalam, C. Chiru, “2012 Presidential Elections on Twitter -- An Analysis of How the US and French Election were Reflected in Tweets”, 19th International Conference on Control Systems and Computer Science (CSCS), 2014.
[3] A.W. Wijayanto, “Desain Sistem Terintegrasi Analisis Persepsi Publik pada Media Sosial Berbasis Internet of Thing untuk Pendukung e-Government Studi Kasus : Badan Pusat Statistik”, Konferensi dan Temu Nasional Teknologi Informasi dan Komunikasi (TIK) untuk Indonesia, 2014.
[4] S. K. Endarnoto, S. Pradipta, A. S. Nugroho, J. Purnama, “Traffic Condition Information Extraction & Visualization from Social Media Twitter for Android Mobile Application”, International Conference on Electrical Engineering and Informatics, 2011.
[5] A. Lamb, M. J. Paul, M. Dredze, “Separating Fact from Fear: Tracking Flu Infections on Twitter”, Proceedings of NAACL-HLT 2013, pages 789–795, 2013.
[6] R. Hanifah, S. H. Supangkat, A. Purwarianti, “Twitter Information Extraction for Smart City, Case Study: Traffic Congestion of Bandung”, International Conference on ICT For Smart Society (ICISS), 2014.
[7] http://www.cs.waikato.ac.nz/ml/weka/ (Accessed: 15 March 2015).
[8] M. A. Russell, Mining the Social Web, Second Edition, O’Reilly Media, Inc, USA, 2014.
