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.

[1]  Haim Kaplan,et al.  Better Landmarks Within Reach , 2007, WEA.

[2]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[3]  Wasan Pattara-Atikom,et al.  Social-based traffic information extraction and classification , 2011, 2011 11th International Conference on ITS Telecommunications.

[4]  Douglas E. Appelt,et al.  Introduction to Information Extraction , 1999, AI Commun..

[5]  Han Xiao,et al.  Product Named Entity Recognition Using Conditional Random Fields , 2011, 2011 Fourth International Conference on Business Intelligence and Financial Engineering.

[6]  Douglas E. Appelt,et al.  FASTUS: A Finite-state Processor for Information Extraction from Real-world Text , 1993, IJCAI.

[7]  Jing Jiang,et al.  Information Extraction from Text , 2012, Mining Text Data.

[8]  Sergey Brin,et al.  Extracting Patterns and Relations from the World Wide Web , 1998, WebDB.

[9]  Ralph Grishman,et al.  Extracting Relations with Integrated Information Using Kernel Methods , 2005, ACL.

[10]  William W. Cohen,et al.  Exploiting dictionaries in named entity extraction: combining semi-Markov extraction processes and data integration methods , 2004, KDD.

[11]  Stephen Soderland,et al.  Learning Information Extraction Rules for Semi-Structured and Free Text , 1999, Machine Learning.

[12]  Nanda Kambhatla,et al.  Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations , 2004, ACL 2004.

[13]  James Purnama,et al.  Traffic Condition Information Extraction & Visualization from Social Media Twitter for Android Mobile Application , 2011, Proceedings of the 2011 International Conference on Electrical Engineering and Informatics.