Social-based traffic information extraction and classification

摘要: Social networks such as Twitter and Facebook are popular, personal, real-time in nature. We found that there exists a significant number of traffic information congestion, incidents, weather Twitter. However, an algorithm is needed to extract classify the before publishing (re-tweeting) becoming useful for others. Traffic was extracted from using syntactic analysis then further classified into two categories: point link. This method can 2,942 tweets category with 76.85% accuracy 331 link 93.23% accuracy. Our system report real-time.