Tia, Khoirunnisa (2025) IMPLEMENTASI ALGORITMA NAÏVE BAYES UNTUK KLASIFIKASI KESULITAN MAHASISWA DALAM PEMBELAJARAN JARAK JAUH (PJJ). Diploma thesis, UIN Raden Intan Lampung.
|
PDF
Download (3MB) |
|
|
PDF
Restricted to Repository staff only Download (11MB) |
Abstract
ABSTRAK Penggunaan Algoritma Naïve Bayes dalam penelitian klasifikasi data secara cepat dan akurat belum banyak dieksplorasi. Di sisi lain, masalah mengenai kesulitan mahasiswa dalam Pembelajaran Jarak Jauh (PJJ) juga belum banyak dikaji secara mendalam. Survei APJII mencatat 59,19% responden tidak puas terhadap pelaksanaan PJJ. Penelitian ini bertujuan untuk mengidentifikasi kesulitan mahasiswa dalam Pembelajaran Jarak Jauh (PJJ) menggunakan Algoritma Naïve Bayes. Model Naïve Bayes dievaluasi berdasarkan akurasi dan presisi hasil klasifikasi. Sampel penelitian sebanyak 250 responden yang dikumpulkan dengan metode Purposive Sampling dan Snowball Sampling. Analisis data menggunakan analisis data teks dengan melakukan pre-processing, pelabelan data, dan eksplorasi data menggunakan wordcloud, dan pembagian data menggunakan Stratified K-Fold Cross-Validation. Hasil evaluasi menunjukan model klasifikasi menggunakan Algoritma Naïve Bayes memiliki tingkat ketepatan yang tinggi dalam mengklasifikasi data teks, meskipun ada sebagian kecil data yang diprediksi dengan kurang tepat. Nilai akurasi memperkuat bahwa model sudah cukup handal. Hasil penelitian dari analisis data teks memberikan informasi bahwa kesulitan yang dialami mahasiswa dalam PJJ bersifat multidimensi. Algoritma Naïve Bayes berhasil mengklasifikasi jenis kesulitan mahasiswa dengan performa yang sangat baik, dengan rata-rata akurasi sebesar 95.50% dan evaluasi data aktual dan data prediksi mencapai akurasi 92.42% dengan presisi yang tinggi pada tiap kelasnya. Kata Kunci : Naïve Bayes, Klasifikasi, Pembelajaran Jarak Jauh (PJJ), Kesulitan Mahasiswa, Akurasi, Presisi, Analisis Teks, Cross Validation. ABSTRACT The use of the Naïve Bayes algorithm in fast and accurate data classification research has not been widely explored. On the other hand, the issue of students' difficulties in distance learning (DL) has also not been studied in depth. A survey by APJII noted that 59.19% of respondents were dissatisfied with the implementation of DL. This study aims to identify the challenges faced by students in Distance Learning (DL) using the Naïve Bayes Algorithm. The Naïve Bayes model was evaluated based on the accuracy and precision of the classification results. The research sample consisted of 250 respondents collected using Purposive Sampling and Snowball Sampling methods. Data analysis was conducted using text data analysis, including pre processing, data labeling, and data exploration using word clouds, as well as data division using Stratified K-Fold Cross-Validation. The evaluation results show that the classification model using the Naïve Bayes algorithm has a high level of accuracy in classifying text data, although there is a small portion of data that is predicted with less accuracy. The accuracy value reinforces that the model is quite reliable. The results of the text data analysis indicate that the difficulties experienced by students in distance learning are multidimensional. The Naïve Bayes algorithm successfully classified the types of student difficulties with excellent performance, achieving an average accuracy of 95.50% and an accuracy of 92.42% in evaluating actual and predicted data, with high precision in each class. Keywords : Naïve Bayes, Classification, Distance Learning (DL), Student Difficulties, Accuracy, Precision, Text Analysis, Cross Validation.
| Item Type: | Thesis (Diploma) |
|---|---|
| Subjects: | Sistem Informasi |
| Divisions: | Fakultas Sains dan Teknologi > Sistem Informasi |
| Depositing User: | LAYANAN PERPUSTAKAAN UINRIL REFERENSI |
| Date Deposited: | 28 Aug 2025 04:11 |
| Last Modified: | 28 Aug 2025 04:11 |
| URI: | https://repository.radenintan.ac.id/id/eprint/39859 |
Actions (login required)
![]() |
View Item |


