Skripsi
MPLEMENTASI OPENAI API UNTUK PEMBANGKITAN SOAL KUIS PADA QUIZ GAME SEJARAH
Quiz games serve not only as entertainment but also as educational media. However, manually creating varied questions, especially for production-level digital quiz games, requires significant resources. This research attempts to address this challenge by implementing GPT-3.5, through the OpenAI API, as a question generation system for quiz game question banks within the domain of history. The system is designed to generate three categories of history questions: international history, Indonesian history, and South Sumatra history. A total of 300 questions were tested, with an even distribution of 100 questions for each category. Test results showed that the GPT-3.5 model achieved the highest validity rate in the international history category (80%), followed by Indonesian history (48%) and South Sumatra history (30%). From these results, it can be concluded that GPT-3.5 shows potential in automating history quiz question generation, but its effectiveness remains limited when used to generate questions about specific historical topics. This indicates limitations in the model's training data, particularly regarding historical content, suggesting that further development is needed to improve the quality and accuracy of the generated output.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407007112 | T163287 | T1632872024 | Faculty of Economics (REFERENS) | Available |
No other version available