IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      PENGEMBANGAN DAN EVALUASI CHATBOT PEMBELAJARAN BERPIKIR KOMPUTASIONAL BERBASIS RAG DAN LLM

      Thumbnail
      View/Open
      Cover (398.9Kb)
      Fulltext (1.144Mb)
      Lampiran (476.4Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      TAJ, MUHAMMAD AJISAKA ARSYI
      Herdiyeni, Yeni
      Giri, Endang Purnama
      Metadata
      Show full item record
      Abstract
      Computational Thinking (CT) merupakan mata kuliah wajib di Institut Pertanian Bogor yang konsisten menimbulkan kesulitan bagi mahasiswa, sementara metode pengajaran yang ada belum mengakomodasi keragaman gaya belajar. Penelitian ini mengembangkan dan mengevaluasi sistem chatbot pembelajaran CT berbasis LLM yang diintegrasikan dengan Retrieval-Augmented Generation (RAG), dengan profil kognitif multi-dimensi mahasiswa (Felder-Silverman, Kolb, dan Taksonomi Bloom) sebagai konteks prompt. Evaluasi kuantitatif terhadap 210 kasus uji sintetis dalam tujuh kategori membandingkan kondisi dengan dan tanpa RAG, dilengkapi kuesioner persepsi 20 mahasiswa. Hasil menunjukkan kinerja retrieval sangat baik (Precision@K 1,00; Recall@K 0,95; Mean Similarity 0,75). Kondisi RAG menghasilkan Faithfulness lebih tinggi (0,69 vs 0,64) dan Hallucination Risk lebih rendah (0,21 vs 0,24), meski Answer Accuracy sedikit lebih rendah (88,6% vs 90,5%) akibat desain baseline yang minimalis. Persepsi pengguna mengonfirmasi relevansi respons sistem. Temuan ini membuktikan RAG meningkatkan keselarasan dan menekan halusinasi LLM pada domain pembelajaran teknis.
       
      Computational Thinking (CT) is a mandatory course at Institut Pertanian Bogor that consistently poses difficulties for students, while existing teaching methods fail to accommodate diverse learning styles. This study develops and evaluates an LLM-based CT tutoring chatbot integrated with Retrieval-Augmented Generation (RAG) using multi-dimensional student cognitive profiles (Felder Silverman, Kolb, and Bloom's Taxonomy) as prompt context. Quantitative evaluation on 210 synthetic test cases across seven categories compared conditions with and without RAG, supplemented by a perception questionnaire from 20 students. Results show strong retrieval performance (Precision@K 1,00; Recall@K 0,95; Mean Similarity 0,75). The RAG condition yielded higher Faithfulness (0,69 vs 0,64) and lower Hallucination Risk (0,21 vs 0,24), though Answer Accuracy was slightly lower (88,6% vs 90,5%) due to a minimalist baseline design. User perception confirms system response relevance. These findings demonstrate that RAG improves response alignment and reduces hallucination risk in a technical learning domain.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/177927
      Collections
      • UF - Computer Science [163]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository