Corruption System Development Based on Indonesia’s Corruption Perception Index
Abstract
The purpose of this study is to develop the corruption system in Indonesia based on online news as it is considered to reflect Indonesia’s current condition. The government has an important role in economic growth. However, there are still many civil servants who abuse their positions to do corruption. The central government should pay more attention to each region to avoid corruption cases. For developing a mapping system, Naïve Bayes classifier is needed to classify news about corruption and non-corruption. N-Gram and Hash Table were used to map corruption cases based on Indonesia’s administrative territory. The experimental results showed that Naïve Bayes classification achieved 100% accuracy for training and testing. However, N-Gram and Hash Table achieved 85% accuracy for mapping the location of the article. © 2018 ICIC International.
