Two Text Classifiers in Online Discussion: Support Vector Machine vs Back-Propagation Neural Network

Abstract: The purpose of this research is to compare the performance of two text classifiers; support vector machine (SVM) and back-propagation neural network (BPNN) within categorize messages from an online discussion. SVM has been recognized as one of the best algorithm for text categorization. BPNN is also a popular categorization method that can handle linear and non linear problems and can achieve good result. However, using SVM and BPNN in online discussion is rare. In this research, several SVM data are trained in multi-class categorization to classify the same set with BPNN. The effectiveness of these two text classifiers are measured and then statistically compared based on error rate, precision, recall and F-measure. The experimental result shows that for text message categorization in online discussion, the performances of SVM outperform BPNN in term of error rate and precision; and falls behind BPNN in term of recall and F-measure.

Keywords: text categorization, support vector machine, back-propagation neural network

Author: E. Erlin, R. Rahmiati, Unang Rio

Journal Code: jptkomputergg140034

Artikel Terkait :

Jp Teknik Komputer gg 2014

• Research on Keyhole Diameter’s Vision Measurement Based on Parallel Technology
• Strain Transfer and Test Research of Stick-up Fiber Bragg Grating Sensors
• Matrix Mask Overlapping and Convolution Eight Directions for Blood Vessel Segmentation on Fundus Retinal Image
• Application Status of the Barkhausen Effect in Nondestructive Testing
• The New Complex-Valued Wavelet Neural Network
• A Review of Current Control Strategy for Single-Phase Grid-Connected Inverters
• Wireless Power Transfer by Using Solar Energy
• One-Time Password Implementation on Lego Mindstorms NXT
• Simple HAWT Prototype Efficiency at Small Scale Wind Speed
• Combine Target Extraction and Enhancement Methods to Fuse Infrared and LLL Images
• Batik Image Retrieval Based on Color Difference Histogram and Gray Level Co-Occurrence Matrix
• A Novel Part-of-Speech Set Developing Method for Statistical Machine Translation
• A Different Single-Phase Hybrid Five-Level Voltage-Source Inverter Using DC-Voltage Modules
• Multi Population Evolutionary Programming Approach for Distributed Generation Installation
• Failure Mechanism Analysis and Failure Number Prediction of Wind Turbine Blades
• Searching and Visualization of References in Research Documents
• Self-learning PID Control for X-Y NC Position Table with Uncertainty Base on Neural Network
• Adaptive Control of Space Robot Manipulators with Task Space Base on Neural Network
• Planar Finger-Shaped Antenna Used in Ultra-Wideband Wireless Systems
• Information Interchange Layer based on Classification of Information Use (IU)
• A Novel Multi-focus Image Fusion Method Based on Non-negative Matrix Factorization
• A Decision Tree Based on Spatial Relationships for Predicting Hotspots in Peatlands
• Traveling-Wave-Based Fault Location in Electrical Distribution Systems with Digital Simulations
• Multi-focus Image Fusion with Sparse Feature Based Pulse Coupled Neural Network
• Measuring Information Security Awareness of Indonesian Smartphone Users