Pengelompokan Ulasan Aplikasi Belajar Online Zenius Menggunakan Metode Self Organizing Maps (SOM) dan K-Means

Damayanti, Nur Anisa (2021) Pengelompokan Ulasan Aplikasi Belajar Online Zenius Menggunakan Metode Self Organizing Maps (SOM) dan K-Means. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211940005014-Undergraduate_Thesis.pdf] Text
06211940005014-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (2MB) | Request a copy

Abstract

Aplikasi belajar online atau edutech semakin digemari oleh siswa maupun orang tua karena menawarkan kepraktisan dan kemudahan, apalagi di situasi pandemi yang mengharuskan siswa untuk belajar di rumah. Salah satu aplikasi belajar online yang menjadi pelopor di Indonesia adalah Zenius Education. Semakin bertambahnya pengguna, Zenius dituntut untuk meningkatkan kualitas layanannya. Ulasan pengguna aplikasi Zenius sangat berguna bagi developer dalam melakukan improvement atau perbaikan pada aplikasinya. Penelitian ini akan melakukan pengelompokan ulasan pada rating 1 sampai dengan 5 untuk mendapatkan informasi lebih rinci terkait kelemahan dan kelebihan aplikasi. Data ulasan didapatkan dari hasil scraping Google Play dan didapatkan total 13.357 ulasan dalam periode 1 Januari 2020 sampai 28 Januari 2021. Pengelompokan dilakukan dengan dua metode yaitu Self Organizing Maps (SOM) dan K-Means dengan model kata bigram. Pengelompokan atau clustering yang dilakukan pada setiap rating berhasil mendapatkan informasi lebih banyak terkait pengalaman pengguna selama menggunakan aplikasi, dan dari informasi tersebut bisa diberikan beberapa rekomendasi untuk perbaikan. Evaluasi hasil clustering berdasarkan nilai Silhouette dan Davies Bouldin menunjukkan bahwa metode K-Means memberikan hasil yang lebih baik daripada metode Self Organizing Maps (SOM) pada semua rating.
================================================================================================
Online learning applications are increasingly favored by students and parents because they offer practicality and convenience, especially in a pandemic situation that requires students to study at home. One of the online learning applications that has become a pioneer in Indonesia is Zenius Education. Zenius needs to improve the quality of its services, along with the increasing number of users. Zenius application user reviews are very useful for developers to make improvements to their application. This study will group reviews on a rating of 1 to 5 to get more detailed information regarding the weaknesses and strengths of the application. The user reviews data was obtained from the scraping of Google Play and a total of 13,357 reviews were obtained in the period January 1, 2020 to January 28, 2021. The clustering is done using the Self Organizing Maps (SOM) and K-Means method with the bigram model. The clustering carried out on each rating managed to get more information related to the user experience while using the application, and from those information can be given some recommendations for improvement. Evaluation of clustering results based on Silhoutte and Davies Bouldin values shows that the K-Means method gives better results than the SOM method on all ratings

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Bigram, K-Means, SOM, Teks Clustering, Ulasan, Reviews, Text Clustering
Subjects: Q Science > QA Mathematics > QA278.55 Cluster analysis
Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Nur Anisa Damayanti
Date Deposited: 04 Sep 2021 07:47
Last Modified: 04 Sep 2021 07:47
URI: http://repository.its.ac.id/id/eprint/91573

Actions (login required)

View Item View Item