Banca de QUALIFICAÇÃO: RAIMUNDO NONATO BEZERRA NETO

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : RAIMUNDO NONATO BEZERRA NETO
DATE: 27/01/2026
TIME: 09:00
LOCAL: Google Meet
TITLE:

An Intelligent Tutoring System to Assist in Writing Game Designs Based on Prompt Engineering

KEY WORDS:

Generative Artificial Intelligence. Prompt Engineering. Game Design Document. Digital Education. Intelligent Tutoring System.

PAGES: 123
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SPECIALTY: Engenharia de Software
SUMMARY:

The use of digital games in an educational settings faces significant challenges, especially regarding the production of Game Design Documents (GDDs), which require clarity, organization, and digital skills often overlooked by traditional teaching methodologies. Generative Artificial Intelligence (GenAI), combined with prompt engineering, emerges as an innovative alternative to support students and teachers in producing more structured GDDs aligned with pedagogical objectives. However, the adoption of these technologies in the classroom demands solutions that foster autonomy, creativity, and curricular integration, while also addressing issues of usability and pedagogical validation. In this context, this study proposes the development and evaluation of the intelligent tutoring system Vocalis, designed to assist the GDD writing process by integrating GenAI, prompt engineering, and pedagogical principles. Vocalis allows data entry via text or audio, processes the
information using advanced language models, and provides automatic evolution reports, promoting iterative cycles of revision and enhancement of the documents by students. The research is characterized as applied and explanatory in nature, employing the hypothetical-deductive method and a mixed approach (qualitative and quantitative), with planned case studies in public schools and the participation of lower and upper secondary education classes. The initial evaluation was conducted in a simulated environment, comparing the system’s automated analyses with expert human assessments. The simulated results indicate significant convergence in the identification of structural gaps and progression in GDDs, although some divergences are observed at  intermediate levels, highlighting the importance of teacher supervision. Vocalis demonstrated operational stability and potential to support pedagogical mediation, standing out as a promising tool for the development of digital competencies and the improvement of document quality in educational contexts.

COMMITTEE MEMBERS:
Presidente - 1671962 - EDUARDO HENRIQUE DA SILVA ARANHA
Externo à Instituição - FRANCISCO DANTAS DE MEDEIROS NETO - UERN
Externo à Instituição - KLEBER TAVARES FERNANDES - UFERSA