Analisa Aktifitas Siswa di E-Learning Untuk Memprediksi Kelulusan Dengan Algoritma CART
Abstract views: 108
,
Abstract
Abstrak
SMAN 1 Pare sudah cukup lama menerapkan E-learning dengan menggunakan moodle, namun “Logs” yang tersimpan di Moodle belum termanfaatkan.Dengan menggunakan metode CART, aktifitas siswa yang terekam di Logs Moodle dianalisa dan dimanfaatkan untuk memprediksi kelulusan siswa pada suatu mata pelajaran.
Proses Algoritma CART adalah dengan melakukan pemilahan untuk setiap decision node menjadi dua cabang yang digunakan untuk membentuk candidate split. Selanjutnya dipilih Candidate split untuk penyusunan inisial partisi pada root node dan decision node berikutnya, adapun kriteria pemilihan tersebut berdasarkan nilai goodness of split yang terbesar.
Penerapan Algoritma CART ini diujikan pada dua kategori data, yaitu data training dan data testing dengan perbandingan 80:20, dan diperoleh hasil pada data training dengan tingkat akurasi 75,9%. Adapun pada data testing diperoleh hasil dengan tingkat akurasi 78,43%.
Kata kunci:Logs, Moodle, CART, data training, data testing.
SMAN1Parehas applied the E-learning by usingModul, but the"Logs" arestoredinthe Moodleuntapped. Byusingthe CARTmethod, students’s activity arerecordedinthe LogsMoodleanalyzedandusedtopredict thestudents' graduationina subject.
CARTalgorithmis aprocessby sortingforeachdecisionnodeinto twobrancheswhichare usedtoform thecandidatesplit. Furthermorechoose the candidatesplitforthe preparation ofthe initialpartitionfor the rootnodeandthe nextnodedecision, while theselection criteriaarebased onthe value ofthe goodness ofa splitisgreatest.
Application ofthe CARTalgorithmwas testedontwocategoriesof data, ietraining dataandtesting datawith80:20ratio, and theobtainedresultson thetraining datawithan accuracyrate of75.9%. Theresultsobtainedontesting datawithan accuracyrate of78.43%.
Keywords : Logs, Moodle, CART, training data, testing data.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
