Maulidina, Mega (2020) ANALISIS SENTIMEN KOMENTAR WARGANET TERHADAP POSTINGAN INSTAGRAM MENGGUNAKAN METODE NAÏVE BAYES CLASSIFIER DAN TF-IDF (Studi Kasus: Instagram Gubernur Jawa Barat Ridwan Kamil). Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
NASKAH PUBLIKASI-5150411382 Mega Kurnia Maulidina.pdf Download (1MB) | Preview |
Abstract
Instagram is social media which is quite popular now. Their users start from children, teenager till adult, they boosted the popularity of Instagram. On one post of instagram, everyone can freely write their comments about the post of other people. Likewise, on the Instagram account of the Governor of West Java, Ridwan Kamil, namely @ridwankamil, usually criticism, praise, and insults from warganet are contained in the comments column in each of his posts. To be able to dig up information and classify a text, sentiment analysis is needed. Sentiment analysis is a branch of text mining which is used to extract, understand, and process text data. The first step is to export comments in an Instagram post and then preprocessing the data which includes, case folding, stemming, stopwords removing, URL and uniq character removing, and tokenizing. Then the word weighting is done with the term frequency – invers document frequency (TF-IDF). In this study, sentiment analysis was in the form of a classification process of textual documents into two classes, namely negative and positive sentiment classes. To determine the classification of each sentiment in the comments, the Naïve Bayes Classifier method is used Keywords: Sentiment Analysis, Naïve Bayes Classifier, TF-IDF, Instagram.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 20 Dec 2020 01:40 |
| Last Modified: | 20 Dec 2020 01:40 |
| URI: | http://eprints.uty.ac.id/id/eprint/6332 |
Actions (login required)
 |
View Item |
