Kurniawan, Arifin (2019) Analisis Sentimen Opini Film Menggunakan Metode Naïve Bayes dan Lexicon Based Features. Sarjana thesis, Universitas Brawijaya.
Abstract
Perkembangan teknologi informasi yang semakin pesat mengakibatkan banyak orang yang menulis opini mereka di media sosial seperti pada forum KASKUS. KASKUS merupakan situs forum online yang menyediakan tempat untuk mencari informasi dan berbagi hobi. Salah satunya adalah forum Movies yang berisi diskusi mengenai suatu film yang telah ditonton. Pengguna menuliskan opininya mengenai suatu film apakah film tersebut bagus atau jelek. Opini-opini tersebut dapat dianalisis untuk mengetahui bagaimana tanggapan pengguna tentang film tersebut agar menghasilkan output yang bermanfaat bagi pembuat film dengan melakukan analisis sentimen untuk mengklasifikasikan opini ke dalam kelas positif atau kelas negatif. Analisis sentimen dilakukan menggunakan metode Naïve Bayes untuk klasifikasi dan Lexicon Based Features untuk pembobotan nilai sentimen suatu kata. Proses yang dilakukan dimulai dari text preprocessing, term weighting, Naïve Bayes training, dan Naïve Bayes testing dengan pembobotan lexicon based features menggunakan kamus Barasa. Berdasarkan hasil pengujian yang dilakukan, dengan menggunakan metode Naïve Bayes dan Lexicon Based Features didapatkan nilai accuracy, precision, recall, dan f-measure sebesar 0,8, 0,8, 0,8 dan 0,8. Sedangkan dengan menggunakan metode Naïve Bayes tanpa pembobotan Lexicon Based Features didapatkan nilai accuracy, precision, recall, dan f-measure sebesar 0,95, 1, 0,9 dan 0,9474. Sehingga penggunaan metode Naïve Bayes dengan Lexicon Based Features masih belum dapat memberikan hasil lebih baik.
English Abstract
The rapid development of information technology has resulted in many people writing their opinions on social media as in the KASKUS forum. KASKUS is an online forum site that provides a place to find information and share hobbies. One is called Movies forum which contains discussions about a movie that has been watched. Users writes their opinion about a film whether the film is good or bad. These opinions can be analyzed to determine how the user feedback about the film in order to produce useful output for the filmmaker by perform sentiment analysis to classify opinions into positive or negative classes. The process of sentiment analysis was performed using methods Naïve Bayes for classification and Lexicon Based Features to weight the sentiment value of a word. The process starts from text preprocessing, term weighting, Naïve Bayes training, and Naïve Bayes testing with Lexicon Based Features weighting using Barasa’s lexicon. Based on the results of tests performed, using Naïve Bayes and Lexicon Features Based method, the values of accuracy, precision, recall, and f-measure were 0.8, 0.8, 0.8 and 0.8. While using the Naïve Bayes method without Lexicon Based Features, the values of accuracy, precision, recall, and f-measure are 0.95, 1, 0.9 and 0.9474. So, the use of Naïve Bayes and Lexicon Based Features methods still cannot provide better results.
Other obstract
-
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FILKOM/2019/666/051907858 |
| Uncontrolled Keywords: | KASKUS, film, sentiment analysis, Naïve Bayes, Lexicon Based Features, Barasa, |
| Subjects: | 000 Computer science, information and general works > 004 Computer science > 004.2 System analysis and design, computer architecture, performance evaluation |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 05 Aug 2020 07:35 |
| Last Modified: | 09 Mar 2022 04:32 |
| URI: | http://repository.ub.ac.id/id/eprint/174107 |
Preview |
Text
Arifin Kurniawan (2)ok.pdf Download (4MB) | Preview |
Actions (login required)
 |
View Item |