Logo des Repositoriums

Auflistung nach Autor:in "Ito, Takayuki"

1 - 2 von 2
  • Konferenzbeitrag
    Comparative analysis of AI facilitator impact in online discussions: A cross-cultural study
    (INFORMATIK 2024, 2024) Sahab, Sofia; Haqbeen, Jawad A.; Ito, Takayuki
    AI chatbots are helpful in facilitating group discussions in online forums while enhancing users’ engagement and interaction. However, whether the AI chatbot as a facilitator influences users to express their opinions may depend on factors such as users' social presence, knowledge on discussion topics, and their desire to express their opinions. The effectiveness of social qualities of agents in collecting various opinions across different cultural contexts in online discussions needs further research. This paper investigates the effect of facilitation chatbots in collecting various opinions in two countries with distinct socio-cultural and economic backgrounds, Afghanistan and Japan. In an experimental study (n=32), we found that chatbots significantly impact discussion development with groups knowledgeable about the discussion topic (vs. less knowledgeable individuals). Additionally, self-disclosure, influenced by specific social contexts, encourages users to post their opinions more freely, affecting levels of social presence and opinion expression in chatbot-assisted online forums. Our findings provide a basis for designing tools that enhance idea development in online communities with distinct socio-cultural and economic backgrounds.
  • Konferenzbeitrag
    Facilitation chatbots enhance student confidence in learning platforms
    (INFORMATIK 2024, 2024) Haqbeen, Jawad A.; Sahab, Sofia; Ito, Takayuki
    The recent development of Large Language Models (LLMs) in the last two years has enhanced the potential of creating facilitation chatbots that enhance creativity and productivity in the online community. However, the impact of facilitation chatbots on learning confidence is yet to be clearly articulated. In this study, we introduce facilitation agents that implement understanding and content-generation capabilities on learning platforms with the participation of undergraduate students. It explores the potential of LLMs to enrich pre- and post-lecture discussions by providing diverse viewpoints and stimulating engagement with lecture contents among participants. In this paper, we investigated the effect of facilitation chatbots on students' learning confidence during synchronous e-learning courses. In the control experimental study (n=80), we found that chatbots induced learning confidence most effectively, making students experience strong confidence in the learning platform, likely due to the chatbot's contextual knowledge and human touch. Our study provides insight into creating effective chatbots to enhance students' confidence, skills, benefits, and involvement in the pre- and post-learning processes.