Rangkuman Paper: Case-Based Reasoning Adaptive E-Learning System Based on Visual-Auditory-Kinesthetic Learning Styles
1. Latar Belakang
Paper ini membahas peningkatan kualitas pendidikan melalui teknologi, khususnya adaptive e-learning. Fokus utamanya adalah mengatasi tantangan pembelajaran, seperti ketidaksesuaian gaya belajar siswa dengan metode pengajaran yang digunakan guru. Dengan memanfaatkan teknologi, sistem e-learning adaptif yang mendukung gaya belajar Visual, Auditory, dan Kinesthetic (VAK) dirancang untuk merekomendasikan materi yang sesuai dengan preferensi belajar siswa.
2. Metodologi
Penelitian ini menggunakan metode Case-Based Reasoning (CBR) untuk merekomendasikan materi pembelajaran berdasarkan gaya belajar siswa. Algoritma Nearest Neighbor digunakan untuk mencocokkan kasus baru dengan kasus lama dalam basis pengetahuan. Proses CBR meliputi:
- Retrieve: Mencari kasus serupa dalam basis data.
- Reuse: Memberikan rekomendasi materi.
- Revise: Menyesuaikan materi jika diperlukan.
- Retain: Menyimpan kasus baru ke basis pengetahuan.
Instrumen utama adalah kuesioner VAK untuk mengidentifikasi gaya belajar setiap siswa.
3. Hasil dan Analisis
- Identifikasi Gaya Belajar: Dari 34 siswa yang diuji, distribusi gaya belajar adalah Auditory (35%), Visual (33%), dan Kinesthetic (32%).
- Peningkatan Nilai Siswa: Sebelum menggunakan sistem, nilai rata-rata siswa tidak mencapai Minimum Mastery Criteria (MMC). Setelah implementasi e-learning adaptif, rata-rata nilai meningkat hingga 85, melampaui MMC sebesar 75.
- Penerimaan Sistem: Sistem diuji menggunakan User Acceptance Testing (UAT) dengan tingkat penerimaan sebesar 91%.
4. Kesimpulan
- Sistem e-learning adaptif dapat mengidentifikasi dan menyesuaikan materi berdasarkan gaya belajar siswa (VAK).
- Penggunaan CBR dan algoritma Nearest Neighbor terbukti efektif dalam meningkatkan hasil belajar siswa.
- Rata-rata nilai siswa meningkat secara signifikan setelah implementasi e-learning adaptif.
5. Rekomendasi
- Menambahkan fitur pencatatan aktivitas siswa untuk membantu guru memantau efektivitas pembelajaran.
- Memvalidasi materi dan soal ujian yang direkomendasikan untuk mengukur keberhasilan pembelajaran.
- Mengembangkan algoritma lain untuk rekomendasi materi yang lebih akurat.
Paper ini menunjukkan bagaimana teknologi dapat diintegrasikan ke dalam pendidikan untuk menciptakan pengalaman belajar yang lebih personal dan efektif.
Summary of the Paper: Case-Based Reasoning Adaptive E-Learning System Based on Visual-Auditory-Kinesthetic Learning Styles
1. Background
This paper discusses improving the quality of education through technology, particularly adaptive e-learning. Its main focus is addressing the challenges of learning, such as the mismatch between students’ learning styles and teaching methods used by educators. Leveraging technology, an adaptive e-learning system supporting Visual, Auditory, and Kinesthetic (VAK) learning styles was designed to recommend materials that align with students’ learning preferences.
2. Methodology
The study employs the Case-Based Reasoning (CBR) method to recommend learning materials based on students’ learning styles. The Nearest Neighbor algorithm is utilized to match new cases with previous cases stored in a knowledge base. The CBR process includes the following stages:
- Retrieve: Finding similar cases in the database.
- Reuse: Providing material recommendations.
- Revise: Adjusting materials if necessary.
- Retain: Storing new cases in the knowledge base.
The primary instrument is a VAK questionnaire to identify each student’s learning style.
3. Results and Analysis
- Learning Style Identification: Among 34 tested students, the distribution of learning styles was Auditory (35%), Visual (33%), and Kinesthetic (32%).
- Student Performance Improvement: Before using the system, the students’ average scores did not meet the Minimum Mastery Criteria (MMC). After implementing adaptive e-learning, the average score increased to 85, surpassing the MMC of 75.
- System Acceptance: The system was tested using User Acceptance Testing (UAT) with an acceptance rate of 91%.
4. Conclusion
- The adaptive e-learning system can identify and customize materials based on students’ learning styles (VAK).
- The use of CBR and the Nearest Neighbor algorithm has proven effective in improving student learning outcomes.
- The students’ average scores improved significantly after implementing the adaptive e-learning system.
5. Recommendations
- Add activity-tracking features to help teachers monitor the effectiveness of the learning process.
- Validate the recommended materials and test questions to measure learning success accurately.
- Explore other intelligent algorithms for more precise material recommendations.
This paper demonstrates how technology can be integrated into education to create a more personalized and effective learning experience.
