Social media and other online websites have rich traffic information. How to extract and mine useful traffic information from online web data to address transportation problems has become a valuable and interesting research topic in current data-explosive era. In this chapter, we introduce a traffic analytic system with online web data. The proposed system can collect online data, use machine learning and natural language processing methods to extract traffic events, analyze traffic sentiment, and reason traffic scenarios. We also present some results based on the proposed system and techniques in practice.

Chapter Contents:

• 2.1 Introduction
• 2.2 Literature review
• 2.3 Methodology
• 2.3.1 System overview
• 2.3.1.1 Data collection
• 2.3.1.2 Data preprocessing
• 2.3.1.3 Modeling and mining
• 2.3.1.4 Applications
• 2.3.2 Main algorithms and models
• 2.3.2.1 Latent Dirichlet allocation
• 2.3.2.2 Word embedding
• 2.3.2.3 Bayesian network
• 2.3.2.4 Deep learning
• 2.4 Some results
• 2.4.1 Traffic sentiment analysis and monitoring system
• 2.4.2 Traffic event detection
• 2.4.3 Traffic status prediction
• 2.4.4 Semantic reasoning for traffic congestion
• 2.5 Conclusion
• References

Inspec keywords: social networking (online); learning (artificial intelligence); road traffic control; data mining; natural language processing; Web sites

Other keywords: online data; traffic analytic system; traffic events; traffic sentiment; traffic information; traffic analytics; online Web data; online Web sites

Subjects: Natural language interfaces; Traffic engineering computing; Knowledge engineering techniques; Information networks