Automating Public Complaint Classification Through JakLapor Channel: A Case Study of Jakarta, Indonesia

Keyphrases

• Accuracy Rate 50%
• Adaptive Boosting Algorithm 50%
• Classification Model 50%
• Classification Results 50%
• Complaints Classification 100%
• Count Vectorizer 50%
• Digital Transformation 50%
• DKI Jakarta 100%
• Extreme Gradient Boosting(XGBoost) 50%
• Feature Extraction 100%
• Feature Extraction Methods 50%
• Indonesia 100%
• Integrated Policy 50%
• Jakarta 100%
• Latent Semantic Analysis 50%
• Machine Learning Models 100%
• Multiple Machines 50%
• N-gram 50%
• Provincial Government 50%
• Public Complaints 100%
• Random Forest 50%
• Random Forest Method 50%
• Service Features 50%
• Support Vector Machine 50%
• Surrounding Environment 50%
• Term Frequency-inverse Document Frequency (TF-IDF) 100%
• Transformation Program 50%

Computer Science

• adaptive boosting 33%
• Boosting Algorithms 33%
• Case Study 100%
• Classification Models 33%
• classification result 33%
• Digital Transformation 33%
• Extreme Gradient Boosting 66%
• Feature Extraction 100%
• Inverse Document Frequency 33%
• Learning System 66%
• Machine Learning 66%
• Multiple Machine 33%
• Program Transformation 33%
• Random Decision Forest 66%
• Service Feature 33%
• Support Vector Machine 33%
• Surrounding Environment 33%