Hamzah, Amir and RAMDHANI, TRI (2021) Sentiment Analysis untuk Opini Akademik Menggunakan Naive Bayes Classifier dan Information Gain. In: Webinar Nasional Fakultas Teknik Universitas Islam Batik Suarakarta, 31 Agustus 2021, Suarakarta. (Unpublished)
![[img]](https://eprints.akprind.ac.id/style/images/fileicons/text.png) |
Text (Seminar proceeding)
UIBS_Lengkap_cover_mkalah_sertifikat.pdf - Accepted Version Download (3MB) |
Abstract
Opinions are ideas or the results of someone's subjective thoughts in explaining or addressing something. IST AKPRIND Yogyakarta provides comment and suggestion box facilities in the learning evaluation questionnaire. Opinions that have been collected can beused to determine the sentiment of student opinions. This sentiment information can be used in in evaluating the learning process. This study aims to analyze opinion sentiment using the Naive Bayes Classifier (NBC) method with feature selection using Information Gain (IG). The dataset consists of 3999 student opinions taken from student questionnaires. The process is taken in two stages, preprocessing and analysis. The preprocessing stage includes cleaning, text folding, normalization, stemming, stopword removal, negation conversion, and tokenization. The results of this study indicate that the NBC method can analyze sentiments automatically. The accuracy test shows 93.4% of the correct analysis results. Using IG increases the accuracy to 95,5% and shortens the processing time to 2.5% faster
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Depositing User: | Amir Hamzah |
| Date Deposited: | 11 Jan 2023 03:03 |
| Last Modified: | 11 Jan 2023 03:05 |
| URI: | http://eprints.akprind.ac.id/id/eprint/1370 |
Actions (login required)
 |
View Item |