Aini, Syarifah (2024) Analisis Sentimen Terhadap Ulasan Aplikasi Sevima Edlink Menggunakan Lexicon Based Dan Support Vector Machine (SVM). Undergraduate thesis, Politeknik Negeri Bengkalis.
![[img]](http://eprints.polbeng.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
1. TA-6304201316-Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (158kB) |
|
Text (Bab I Pendahuluan)
2. TA-6304201316-Bab I Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (231kB) |
|
Text (Daftar Pustaka)
3. TA-6304201316-Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (208kB) |
|
Text (Full Text)
4. TA-6304201316-Full Text.pdf - Submitted Version Restricted to Registered users only Available under License Creative Commons Attribution Share Alike. Download (6MB) | Request a copy |
Abstract
The Sevima Edlink application has become an important solution in education, facilitating the online learning process for lecturers and students. However, as with other applications, Sevima Edlink also received several reviews from users that were not in line with the rating given. Therefore, this research proposes sentiment analysis using the Lexicon Based method and Support Vector Machine (SVM) on reviews of the Sevima Edlink application on the Play Store. This research aims to determine the results of sentiment analysis in the form of tendencies (positive, negative or neutral) towards reviews of the Sevmia Edlink application using Lexicon Based and Support Vector Machine (SVM). Apart from that, to find out the accuracy of the two methods. This research uses 1500 user reviews with a dataset split of 70:30, the research results show that the majority of reviews tend to be negative. However, through classification using Lexicon Based, the majority of reviews were classified as positive, while SVM produced a classification that was more similar to manual labeling results. SVM shows the highest accuracy of 91%, while Lexicon Based has an accuracy of 64%. From the results of this research it can be concluded that SVM has better performance in recognizing complex sentiment patterns in application reviews. This research provides important insights for application developers to improve quality and increase user satisfaction.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Uncontrolled Keywords: | Sentiment Analysis, Clasification, Sevima Edlink, Lexicon Based, Support Vector Machine (SVM) | ||||||||||||
| Subjects: | 410 ILMU TEKNIK > 450 TEKNIK ELEKTRO DAN INFORMATIKA > 458 Teknik Informatika | ||||||||||||
| Divisions: | Jurusan Teknik Informatika > Sarjana Terapan Rekayasa Perangkat Lunak > TUGAS AKHIR | ||||||||||||
| Depositing User: | Rekayasa Perangkat Lunak C 2024 | ||||||||||||
| Date Deposited: | 15 Jul 2024 03:08 | ||||||||||||
| Last Modified: | 16 Jul 2024 03:09 | ||||||||||||
| URI: | http://eprints.polbeng.ac.id/id/eprint/12643 |
Actions (login required)
 |
View Item |
