IMPLEMENTASI INTELLIGENT TUTORING SYSTEM BERBASIS LARGE LANGUAGE MODEL DAN VISUALISASI DINAMIS PADA PLATFORM PEMBELAJARAN STRUKTUR DATA

Dhi'fan Razaqa, . (2026) IMPLEMENTASI INTELLIGENT TUTORING SYSTEM BERBASIS LARGE LANGUAGE MODEL DAN VISUALISASI DINAMIS PADA PLATFORM PEMBELAJARAN STRUKTUR DATA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (177kB)
[img] Text
AWAL.pdf
Download (890kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (232kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (535kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (207kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (206kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository staff only
Download (98kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (32MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (382kB)

Abstract

The development of Industry 4.0 has increased demand for digital talent with strong technical competencies, yet higher education institutions in Indonesia still struggle to align their curricula with industry needs. This gap is evident in the Data Structures course, where 76,1% of students at the Faculty of Computer Science, UPN Veteran Jakarta, felt inadequately prepared for technical job selection tests. This study aims to design, implement, and evaluate a web-based data structures learning platform integrating an Intelligent Tutoring System (ITS) with a Large Language Model (LLM) and Retrieval Augmented Generation (RAG), supported by dynamic visualization, gamification, and storytelling. The Rapid Application Development (RAD) method was applied through Requirements Planning, User Design, Construction, and Cutover stages, with initial data collected via questionnaire from 46 students. Evaluation covered Black Box Testing, User Acceptance Testing (UAT) using the PSSUQ instrument, RAG performance assessment via the Ragas framework, and real-time performance testing. Results showed all 15 functional scenarios ran without errors, an Overall PSSUQ score of 1,769 out of 7,0 (lower is better), and a RAG Context Precision of 0,911. As standard Ragas metrics are incompatible with Socratic tutoring systems, three custom metrics were developed, yielding a Socratic Score of 0,867, Analogy Score of 0,733, and Alignment Score of 1,000, confirming Oracle's effectiveness as a Socratic tutor.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2210511091] [Pembimbing 1: Musthofa Galih Pradana] [Pembimbing 2: Radinal Setyadinsa] [Penguji 1: Ridwan Raafi'udin] [Penguji 2: Muhammad Panji Muslin]
Uncontrolled Keywords: Data Structures, Dynamic Visualization, Gamification, Intelligent Tutoring System, Large Language Model, Retrieval Augmented Generation
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: DHI'FAN RAZAQA
Date Deposited: 02 Sep 2026 05:12
Last Modified: 02 Sep 2026 05:12
URI: http://repository.upnvj.ac.id/id/eprint/51005

Actions (login required)

View Item View Item