ANALISIS SENTIMEN KOMENTAR PADA INDEKS KINERJA DOSEN FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN KALIJAGA MENGGUNAKAN NAIVE BAYES CLASSIFIER

BAMA ABPAMA SEVSA, NIM. 14650019 (2018) ANALISIS SENTIMEN KOMENTAR PADA INDEKS KINERJA DOSEN FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN KALIJAGA MENGGUNAKAN NAIVE BAYES CLASSIFIER. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

[img]
Preview
Text (ANALISIS SENTIMEN KOMENTAR PADA INDEKS KINERJA DOSEN FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN KALIJAGA MENGGUNAKAN NAIVE BAYES CLASSIFIER)
14650019_BAB-I_V_DAFTAR-PUSTAKA.pdf - Published Version

Download (2MB) | Preview
[img] Text (ANALISIS SENTIMEN KOMENTAR PADA INDEKS KINERJA DOSEN FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN KALIJAGA MENGGUNAKAN NAIVE BAYES CLASSIFIER)
14650019_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version
Restricted to Registered users only

Download (3MB)

Abstract

UIN Sunan Kalijaga Yogyakarta has a system for measure lecturer performance Index in the Academic Information System that commonly referred to as IKD (Lecture Performance Index). The IKD assessment is filled by students at the end of the semester before Final Examination by filling out a questionnaire and writing criticisms and suggestions on lecture activities. From this critique and suggestion data can be seen whether what students write is a negative, neutral, or positive assessment by using sentiment analysis. Sentiment Analysis of critical and suggestions data on IKD using the Naive Bayes Classifier method. Naive Bayes Classifier is a classification method by utilizing probability and statistics. The data used were 8249 data with a composition of 3000 training data with labels and 5249 test data without labels. The result of sentiment analysis of critical and suggestions data on IKD using the Naive Bayes Classifier method shows that the accuracy using TF-IDF weighting is larger than the accuracy using TF weighting. The accuracy using TF-IDF weighting is 73.9% and TF weighting is 72.8%. This accuracy value is obtained by using the evaluation for classification model called K-Fold Cross Validation method from 3000 training data that has been labeled before.

Item Type: Thesis (Skripsi)
Additional Information: Muhammad Didik Rohmad Wahyudi, S.T, M.T
Uncontrolled Keywords: Analisis Sentimen, Indeks Kinerja Dosen, Naive Bayes Classifier, K-Fold Cross Validation
Subjects: Tehnik Informatika
Divisions: Fakultas Sains dan Teknologi > Teknik Informatika (S1)
Depositing User: H. Zaenal Arifin, S.Sos.I., S.IPI.
Date Deposited: 21 Mar 2019 14:06
Last Modified: 21 Mar 2019 14:06
URI: http://digilib.uin-suka.ac.id/id/eprint/34024

Share this knowledge with your friends :

Actions (login required)

View Item View Item
Chat Kak Imum