Akurasi Prediksi Nilai Mahasiswa menggunakan Informasi Kontekstual pada Personalisasi Sistem Rekomendasi
DOI:
https://doi.org/10.33592/jutis.v9i1.1285Keywords:
user collaborative filtering, KNN, informasi kontekstualAbstract
Pembelajaran online, terutama di pendidikan tinggi, semakin mendapat perhatian di banyak negara dalam sepuluh tahun terakhir karena memberikan beberapa keuntungan bagi pelajar termasuk fleksibilitas pembelajaran ruang dan waktu. Keterlibatan siswa dalam pembelajaran online memiliki faktor penting bagi siswa untuk menyelesaikan program studinya dan mencapai tujuan pembelajaran yang direncanakan. Tidak seperti pembelajaran di kelas, pembelajaran online tidak menyediakan sumber daya seperti instruktur untuk mempertahankan keterlibatan siswa tetapi Sistem Manajemen Pembelajaran (LMS). Salah satu pendekatan untuk meningkatkan keterlibatan siswa adalah dengan mempersonalisasi materi pembelajaran yang dikelola secara otomatis oleh LMS. Paper ini menyajikan hasil eksperimen sistem rekomendasi context-aware yang tertanam di LMS untuk meningkatkan keterlibatan siswa dalam pembelajaran online dengan mempersonalisasi materi pembelajaran yang direkomendasikan kepada siswa yang ditargetkan. Metode Penelitian menggunakan metode user collaborative filtering dengan pendekatan K-Nearest Neighbor (KNN) terkait prediksi nilai mahasiswa dengan menambahkan fitur informasi kontekstual. Hasil Penelitian ini membuktikan bahwa metode KNN dengan k=3 memiliki akurasi hasil prediksi mencapai 85%. Hasil penelitian ini menunjukkan bahwa informasi kontekstual sebagai fitur tambahan pada profil siswa meningkatkan korelasi antara nilai aktual dan nilai prediksi menggunakan user collaborative filtering.
References
[2] Chen, C. M., Lee, H. M., & Chen, Y. H. (2005). Personalized e-learning system using Item Response Theory. Computers and Education, 44(3), 237–255.
https://doi.org/10.1016/j.compedu.2004.01.006
[3] Chournazidis, A. J. (2013). Functionality and Feasibility of Knowledge Management in Enterprises. Procedia - Social and Behavioral Sciences, 73, 327–336.
https://doi.org/10.1016/j.sbspro.2013.02.059
[4] Kerkiri, T., Manitsaris, A., & Mavridou, A. (2007). Reputation metadata for recommending personalised e-learning resources. SMAP07 - Second International Workshop on Semantic Media Adaptation and Personalization, 110–115.
https://doi.org/10.1109/SMAP.2007.4414396
[5] Klašnja-mili, A. (2015). Recommender systems in e-learning environments : a survey of the state-of-the-art and possible extensions. https://doi.org/10.1007/s10462-015-9440-z
[6] Liu, F. J., & Shih, B. jiun. (2008). E-learning activity-based material recommendation system. Interactive Technology and Smart Education, 4(4), 200–207.
https://doi.org/10.1108/17415650880001105
[7] Mahmood, T., & Ricci, F. (2009). Improving recommender systems with adaptive conversational strategies. Proceedings of the 20th ACM Conference on Hypertext and Hypermedia - HT ’09, January, 73. https://doi.org/10.1145/1557914.1557930
[8] Murad, D. F., Hassan, R., Wahi, W., & Wijanarko, B. D. (2020). A User-Item Collaborative Filtering System to Predict Online Learning Outcome. Advances in Science, Technology and Engineering Systems, 5(5), 117–121. https://doi.org/10.25046/aj050516
[9] Murad, D. F., Heryadi, Y., Isa, S. M., & Budiharto, W. (2020). Personalization of Study Material based on Predicted Final Grades using Multi-criteria User-collaborative Filtering Recommender System. Education and Information Technologies, May(III). https://doi.org/10.1007/s10639-020-10238-9
[10] Nie, M., Xiong, Z., Zhong, R., Deng, W., & Yang, G. (2020). Career choice prediction based on campus big data-mining the potential behavior of college students. Applied Sciences (Switzerland), 10(8). https://doi.org/10.3390/APP10082841
[11] Rechkoski, L., Ajanovski, V. V, & Mihova, M. (2018). Evaluation of grade prediction using model-based collaborative filtering methods. 2018 IEEE Global Engineering Education Conference (EDUCON), 1096–1103. https://doi.org/10.1109/EDUCON.2018.8363352
[12] Ricci, F., Rokach, L., & Shapira, B. (2011). Introduction to Recommender Systems Handbook. In Recommender Systems Handbook, Springer, Boston, MA, 1–35. https://doi.org/10.1007/978-0-387-85820-3
[13] Sheehan, M., & Park, Y. (2012). pGPA: A personalized grade prediction tool to aid student success. RecSys’12 - Proceedings of the 6th ACM Conference on Recommender Systems, 309–310. https://doi.org/10.1145/2365952.2366027
[14] Song, Y., Ji, W., & Liu, S. (2017). Research on personalized hybrid recommendation system. IEEE CITS 2017 - 2017 International Conference on Computer, Information and Telecommunication Systems, 133–137. https://doi.org/10.1109/CITS.2017.8035321
[15] Taghipour, N., Kardan, A., & Ghidary, S. (2007). Usage-based web recommendations: a reinforcement learning approach. … of the 2007 ACM Conference on …, 113–120. https://doi.org/10.1145/1297231.1297250
[16] Thai-Nghe, N., Drumond, L., Horváth, T., Nanopoulos, A., & Schmidt-Thieme, L. (2011). Matrix and Tensor Factorization for Predicting Student Performance. Undefined. https://www.semanticscholar.org/paper/Matrix-and-Tensor-Factorization-for-Predicting-Thai-Nghe-Drumond/7b8023dbac03bff5bd283ab1b5929ec4cbdf77b7
[17] Vijay, D., Bohra, A., Singh, V., Akhtar, S. S., & Shrivastava, M. (2018). Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text. 128–135. https://doi.org/10.18653/v1/n18-4018
[18] Yousafzai, B. K., Hayat, M., & Afzal, S. (2020). Application of machine learning and data mining in predicting the performance of intermediate and secondary education level student. Education and Information Technologies. https://doi.org/10.1007/s10639-020-10189-1
[19] Za, O. R. (2002). Building a Recommender Agent for e-Learning Systems.
