FADILAH, MUHAMMAD REYHAN (2025) KOMPARASI METODE NAIVE BAYES DAN SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI PAHAMIFY. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (539kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (222kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (275kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (340kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (823kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (149kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (212kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (523kB) |
Abstract
The development of information technology has led to the emergence of digital learning applications such as Pahamify. User reviews on the Google Play Store serve as an important data source for evaluating service quality. However, developers often struggle to accurately understand user perceptions due to discrepancies between ratings and review content. This study aims to analyze user sentiment in Pahamify app reviews and compare the performance of Naive Bayes and Support Vector Machine (SVM) classification algorithms to determine the most effective method. Review data was collected from the Google Play Store and underwent a series of steps: web scraping, preprocessing, data splitting, and word weighting using TF-IDF. In this study, the data was divided into training and testing datasets with a ratio of 70:30 and 80:20. The test results showed that the Naive Bayes model, using two data division scenarios of 80:20 and 70:30, achieved an overall model accuracy of 82%, precision of 88%, and recall of 13% in the 80:20 scenario, and an overall model accuracy of 82% and recall of 100% in the 70:30 scenario. The SVM model in the 70:30 scenario achieved an accuracy of 86%, precision of 69%, and recall of 50% for the negative class, as well as precision of 88% and recall of 94% for the positive class. accuracy increased to 86%, with precision of 69% and recall of 50%. Based on these results, it can be concluded that the SVM algorithm has more effective and accurate performance for sentiment analysis of user reviews of the Pahamify app. Keywords: Sentiment Analysis, Pahamify App, Naive Bayes, Support Vector Machine (SVM), Google Play Store. Perkembangan teknologi informasi telah mendorong munculnya aplikasi pembelajaran digital seperti Pahamify. Ulasan pengguna di Google Play Store menjadi sumber data penting untuk mengevaluasi kualitas layanan. Namun, para pengembang sering kali kesulitan untuk memahami persepsi pengguna secara akurat karena adanya ketidakcocokan antara rating dan isi ulasan. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Pahamify dan membandingkan kinerja algoritma klasifikasi Naive Bayes dan Support Vector Machine (SVM) untuk menentukan metode yang paling efektif. Data ulasan diambil dari Google Play Store dan melalui serangkaian tahapan: web scraping, preprocessing, splitting data, dan pembobotan kata menggunakan TF-IDF. Dalam penelitian ini, data dibagi menjadi data latih dan data uji dengan perbandingan 70:30 dan 80:20. Hasil pengujian menunjukkan bahwa model Naive Bayes Dengan menggunakan dua skenario pembagian data 80:20 dan 70:30, skenario 80:20, akurasi model keseluruhan 82%, akurasi 88%, recall 13%, skenario 70:30, akurasi model 82% recall 100%. Model SVM Pada skenario 70:30, model mencapai akurasi sebesar 86%, precision 69% dan recall 50% untuk kelas negatif, serta precision 88% dan recall 94% untuk kelas positif. Untuk kelas positif, akurasi meningkat menjadi 86%, dengan precision 69%, recall 50%. Berdasarkan hasil tersebut, dapat disimpulkan bahwa algoritma SVM memiliki kinerja yang lebih efektif dan akurat untuk analisis sentimen ulasan pengguna aplikasi Pahamify. Kata Kunci: Analisis Sentimen, Aplikasi Pahamify, Naive Bayes, Support Vector Machine (SVM), Google Play Store.
Actions (login required)
 |
View Item |
