Comparative analysis of Mechanisms for Categorization and Moderation of User Generated Text Contents on a Social E-Governance Forum
Journal Title: Mathematical and Software Engineering - Year 2017, Vol 3, Issue 1
Abstract
This paper presents a comparative analysis of two mechanisms for an automated categorization and moderation of User Generated Text Contents (UGTCs) on a social e-governance forum. Posts on the forum are categorized into “relevant”, “irrelevant but interesting” and “must be removed”. Relevant posts are those posts that are capable of supporting government decisions; irrelevant but interesting category consists of posts that are not relevant but can entertain or enlighten other users; must be removed posts consists of abusive or obscene posts. Two classifiers, Support Vector Machine (SVM) with One-Vs-The-Rest technique and Multinomial Naive Bayes were trained, evaluated and compared using Scikit-learn. The results show that SVM with an accuracy score of 96% on test set performs better than Naive Bayes with 88.6% accuracy score on the same test set.
Authors and Affiliations
Imeobong Frank Inyang, Simeon Ozuomba, Chinedu Pascal Ezenkwu
Keywords
Related Articles
- EP ID EP326786
- DOI -
- Views 152
- Downloads 0
Web Based Information System for Heat Supply Monitoring
The paper presents web based information system for heat supply monitoring. The proposed model and information system for gathering data from heating station heat-flow meters and regulators is software realized. The nov...
Empirical Valuation of Multi-Parameters and RMSE-Based Tuning Approaches for the Basic and Extended Stanford University Interim (SUI) Propagation Models
In this paper, the prediction performance evaluation of Stanford University Interim (SUI) Model and the extended SUI model are presented. More importantly, the effectiveness of two model tuning approaches, namely, RMSE-b...
System for Information Extraction from News Sites
The present paper deals with a system for crawling and content extraction from news sites. The system of web crawlers extracts textual and graphic information and checks for multimedia content availability. A part of the...
Design of Web-Based Customer Relation Management Application for Power Distribution Company: A Case Study of PHCN Owerri Business Unit
In this paper, the design of web-based customer care application for power distribution company is presented with Power Holding Company of Nigeria (PHCN) Owerri business unit as the case study. The system is developed t...
Predictive Models for Post-Operative Life Expectancy after Thoracic Surgery
This paper studies data mining techniques used in medical diagnosis, particularly for predicting chance of survival of a patient after undergoing thoracic surgery. We discuss models built using decision trees, naive Baye...