Husniah, Lailatul (2025) Pembangkitan Level Puzzle Adaptif Secara Prosedural Untuk Estimasi Kinerja Pemain Pada Penilaian Berbasis Permainan Operasi Aritmatika Dasar Bilangan Bulat. Doctoral thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 07111960010015-Doctoral.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
07111960010015-Doctoral.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy |
Abstract
Mengestimasi kemampuan pemain yang beragam tanpa mengorbankan keselarasan dengan tujuan asesmen merupakan tantangan utama dalam pengembangan Game-Based Assessment (GBA). Penelitian ini mengusulkan metode untuk mengestimasi kinerja pemain melalui pembangkitan level permainan puzzle yang secara otomatis menyesuaikan tingkat kesulitan berdasarkan pencapaian pemain. Metode ini mengintegrasikan Procedural Content Generation (PCG) dengan pendekatan Dynamic Difficulty Adjustment (DDA) dan model pemain untuk menetapkan parameter konten yang adaptif sekaligus melacak kinerja pemain secara berkelanjutan. Pendekatan ini mengombinasikan indikator pembelajaran (konten aritmatika) dan teknis (parameter puzzle) untuk memastikan bahwa tingkat kesulitan permainan tetap relevan secara kognitif maupun mekanis. Hasil pengujian terhadap 1.379 data log permainan menunjukkan penyesuaian tingkat kesulitan yang konsisten dengan kinerja pemain (r = 0.73, p < 0.001; RMSE = 0.031). Validasi eksternal ini memperkuat efektivitas metode PCG adaptif berbasis model pemain dalam mengestimasi kemampuan peserta. Evaluasi lanjutan terhadap 94 siswa sekolah menengah menunjukkan bahwa Perceived Usability (β = 0.417, p < 0.01) dan Perceived Usefulness (β = 0.547, p < 0.01) berpengaruh signifikan terhadap kepuasan pengguna, sedangkan Confirmation dan Satisfaction bersama-sama memengaruhi niat penggunaan berkelanjutan (r = 0.694, p < 0.05). Temuan ini menegaskan bahwa sistem penilaian berbasis permainan adaptif tidak hanya efektif dalam mengestimasi kemampuan pemain, tetapi juga meningkatkan kepuasan dan keberlanjutan penggunaan melalui pengalaman belajar yang interaktif, personal, dan selaras dengan tujuan asesmen.
=====================================================================================================================================
Estimating diverse player abilities without compromising alignment with assessment objectives remains a key challenge in developing Game-Based Assessment (GBA). This study proposes a method to estimate player performance through the procedural generation of puzzle game levels that automatically adjust difficulty according to player achievement. The method integrates Procedural Content Generation (PCG) with Dynamic Difficulty Adjustment (DDA) and a player model to define adaptive content parameters while continuously tracking player performance. The approach combines learning indicators (arithmetic content) and technical indicators (puzzle parameters) to ensure that difficulty levels remain both cognitively and mechanically relevant. Evaluation of 1,379 gameplay records demonstrated consistent difficulty adjustment aligned with player performance (r = 0.73, p < 0.001; RMSE = 0.031). This external validation confirms the effectiveness of the adaptive PCG method with a player model in estimating player ability. A subsequent evaluation involving 94 junior high school students revealed that Perceived Usability (β = 0.417, p < 0.01) and Perceived Usefulness (β = 0.547, p < 0.01) significantly influenced user satisfaction, while Confirmation and Satisfaction jointly affected continuance usage intention (r = 0.694, p < 0.05). These findings indicate that adaptive game-based assessment systems are not only effective in estimating player performance but also enhance satisfaction and sustainable engagement through interactive, personalized, and assessment-aligned learning experiences.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Uncontrolled Keywords: | kepuasan pengguna, model pemain, pembangkit konten prosedural, penilaian berbasis permainan, tingkat kesulitan adaptif, adaptive difficulty, game-based assessment, player model, procedural content generation, user satisfaction |
| Subjects: | L Education > LB Theory and practice of education > LB1029.S53 Educational games. Simulation methods |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20001-(S3) PhD Thesis |
| Depositing User: | Lailatul Husniah |
| Date Deposited: | 20 Jan 2026 02:46 |
| Last Modified: | 20 Jan 2026 02:46 |
| URI: | http://repository.its.ac.id/id/eprint/129770 |
Actions (login required)
 |
View Item |