• Title/Summary/Keyword: conversational tutoring system

Search Result 2, Processing Time 0.02 seconds

INTERFACE DEVELOPMENT ENVIRONMENT BASED ON CHARACTER AGENT

  • Park, Young-Mee;Choo, Moon-Won
    • Journal of Korea Multimedia Society
    • /
    • v.6 no.4
    • /
    • pp.650-657
    • /
    • 2003
  • We describe a scheme for developing character-based interface within the context of an agent-based tutoring system in the Web environment. The ideas in this paper stem from original work representing aspects of human emotion in tutoring computer models, where may provide mote natural ways for students to communicate with digital learning materials. The proposed system model is a set of software services that enable developers to incorporate interactive animated characters into their Web pages designed for on-line lectures. The prototypical application is developed and shown for validating the applicability and the effectiveness of this model in real tutoring settings.

  • PDF

Development and mathematical performance analysis of custom GPTs-Based chatbots (GPTs 기반 문제해결 맞춤형 챗봇 제작 및 수학적 성능 분석)

  • Kwon, Misun
    • Education of Primary School Mathematics
    • /
    • v.27 no.3
    • /
    • pp.303-320
    • /
    • 2024
  • This study presents the development and performance evaluation of a custom GPT-based chatbot tailored to provide solutions following Polya's problem-solving stages. A beta version of the chatbot was initially deployed to assess its mathematical capabilities, followed by iterative error identification and correction, leading to the final version. The completed chatbot demonstrated an accuracy rate of approximately 89.0%, correctly solving an average of 57.8 out of 65 image-based problems from a 6th-grade elementary mathematics textbook, reflecting a 4 percentage point improvement over the beta version. For a subset of 50 problems, where images were not critical for problem resolution, the chatbot achieved an accuracy rate of approximately 91.0%, solving an average of 45.5 problems correctly. Predominant errors included problem recognition issues, particularly with complex or poorly recognizable images, along with concept confusion and comprehension errors. The custom chatbot exhibited superior mathematical performance compared to the general-purpose ChatGPT. Additionally, its solution process can be adapted to various grade levels, facilitating personalized student instruction. The ease of chatbot creation and customization underscores its potential for diverse applications in mathematics education, such as individualized teacher support and personalized student guidance.