Pengklasifikasian Topik Hadits Terjemahan Bahasa Indonesia Menggunakan Latent Semantic Indexing dan Support Vector Machine

Hadith is used as the source of Islamic law othen than Qur’an, Ijma, Ijtihad and Qiyas, hadith is the second of Islamic law after the Qur’an. This study attempted to build a system than can classify shahih hadith of Bukhari in Indonesian Translation. This topic was chosen to help Muslims who want to understand from each hadith is in the form of informations, prohibitions or suggestion. Support Vector Machine was chosen because it can perform classification by providing good performance for dataset with a large number of features. Latent Semantic Indexing as a feature selection method was chosen because it can reduce features by eliminationg unimportant features (noise term). This study also using Bootstrap Aggregating (Bagging) method to improve accuracy of the classification system. The accuracy results show that by using Latent Semantic Indexing and Bootstrap Aggregating on Support Vector Machine classification single label system is 84% on polynomial kernel and 84.67% on RBF kernel