Traffic and road conditions monitoring system using extracted information from Twitter

Keyphrases

• Twitter 100%
• Geocoding 100%
• Location Information 100%
• Traffic Condition Monitoring 100%
• Condition Monitoring System 100%
• Road Condition Monitoring 100%
• F1 Score 66%
• Named Entity Recognition 66%
• Geographic Information System 33%
• Support Vector Machine 33%
• Social Media 33%
• Tweet Classification 33%
• Tweets 33%
• Closed-circuit Television 33%
• Public Use 33%
• Logistic Regression 33%
• Traffic-related 33%
• Part-of 33%
• Text Mining Techniques 33%
• Bag of Visual Words (BoVW) 33%
• Nave Bayes 33%
• Success Rate 33%
• Recognition-based 33%
• Best Model 33%
• Road Condition 33%
• N-gram 33%
• Unigram 33%
• Feature Representation 33%
• Feature Combination 33%
• Text-dependent 33%
• Twitter Data 33%
• Traffic Information 33%
• Traffic Jam 33%
• Road Traffic 33%
• Random Forest 33%
• Information Extraction 33%
• Traffic Condition 33%
• Word Frequency 33%
• Term Frequency-inverse Document Frequency (TF-IDF) 33%
• Logistic Support 33%
• Regression Vectors 33%
• Extractor 33%
• Logistic Regression Classifier 33%
• Relevance Classification 33%
• Daily Traffic 33%
• Traffic Monitoring System 33%
• Supervised Classification Algorithm 33%
• Forest Logistics 33%
• ArcPy 33%
• Traffic Disturbance 33%
• Spatial Interfaces 33%
• Coordinate Information 33%
• Web-based Visualization 33%
• Congested Road 33%
• Data Location 33%

Computer Science

• Twitter 100%
• Monitoring System 100%
• Condition Monitoring 100%
• Extracted Information 100%
• Location Information 100%
• Logistic Regression 66%
• Named Entity Recognition 66%
• Information System 33%
• Support Vector Machine 33%
• Social Media 33%
• Circuit Television 33%
• Classification Algorithm 33%
• Nave Bayes 33%
• Text Mining 33%
• Supervised Classification 33%
• Random Decision Forest 33%
• Information Extraction 33%
• Geographic Information 33%
• Inverse Document Frequency 33%
• Logistics Support 33%
• Traffic Information 33%
• Traffic Monitoring 33%