Penerapan naive bayes classifier menggunakan fitur ekstraksi n-gram untuk mendeteksi review spam bahasa Indonesia

Mukti, Setyaji (2018) Penerapan naive bayes classifier menggunakan fitur ekstraksi n-gram untuk mendeteksi review spam bahasa Indonesia. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text COVER.pdf - Accepted Version Download (1MB)
Preview	Text ABSTRACT.pdf - Accepted Version Download (41kB) | Preview
Preview	Text ABSTRAK.pdf - Accepted Version Download (57kB) | Preview
Preview	Text BAB I.pdf - Accepted Version Download (197kB) | Preview
Preview	Text BAB II.pdf - Accepted Version Download (303kB) | Preview
Preview	Text BAB III.pdf - Accepted Version Download (622kB) | Preview
	Text BAB IV.pdf - Accepted Version Restricted to Registered users only Download (437kB)
Preview	Text BAB V.pdf - Accepted Version Download (118kB) | Preview
Preview	Text DAFTAR PUSTAKA.pdf - Accepted Version Download (82kB) | Preview

Abstract

Reviews have many and varied valuable information that is usually used for buyers and sellers to make a decision. Unfortunately, the freedom that is given to user to make a review have make some irresponsible people to use it for their own fortune by making review spam. Furthermore, in existing work on extracting review like mining opinion, have a little awareness about this kind of spam. In this report, will classify review spam Bahasa by using Naive Bayes Classifier with n-gram. By comparing the value of n in n-gram, obtain the highest accuracy 80.44% is with n = 1-2 and how big the effect given by n-gram for classifying review spam Bahasa. Satisfactory results are obtained with the Naive Bayes Classifier using feature extraction n-gram and how important to determine the value of n on the n-gram in obtaining a good accuracy. Keywords: classification, machine learning, naive bayes, opinion, review, supervised learning, spam, text mining.

Actions (login required)

View Item