Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent
Rainer Winkler, Sebastian Hobert, Antti Salovaara, Matthias Söllner, Jan Marco Leimeister
Abstract
Enrollment in online courses has sharply increased in higher education. Although online education can be scaled to large audiences, the lack of interaction between educators and learners is difficult to replace and remains a primary challenge in the field. Conversational agents may alleviate this problem by engaging in natural interaction and by scaffolding learners' understanding similarly to educators. However, whether this approach can also be used to enrich online video lectures has largely remained unknown. We developed Sara, a conversational agent that appears during an online video lecture. She provides scaffolds by voice and text when needed and includes a voice-based input mode. An evaluation with 182 learners in a 2 x 2 lab experiment demonstrated that Sara, compared to more traditional conversational agents, significantly improved learning in a programming task. This study highlights the importance of including scaffolding and voice-based conversational agents in online videos to improve meaningful learning.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 7e874005-af6e-4a6f-ae1a-2cf57fe3f6cfCited by top-tier papers18
- ArgueTutor: An Adaptive Dialog-Based Learning System for Argumentation SkillsThiemo Wambsganss, Tobias Kueng, Matthias Söllner, Jan Marco LeimeisterCHI 2021 · 126 citations
- Towards Mutual Theory of Mind in Human-AI Interaction: How Language Reflects What Students Perceive About a Virtual Teaching AssistantQiaosi Wang, Koustuv Saha, Eric Gregori, David A. Joyner et al.CHI 2021 · 115 citations
- Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo ChatJohn Chen, Xi Lu, Yuzhou Du, Michael Rejtig et al.CHI 2024 · 47 citations
- Promptiverse: Scalable Generation of Scaffolding Prompts Through Human-AI Hybrid Knowledge Graph AnnotationYoonjoo Lee, John Joon Young Chung, Tae Soo Kim, Jean Y. Song et al.CHI 2022 · 32 citations
- Exploring the Effects of Incorporating Human Experts to Deliver Journaling Guidance through a ChatbotYi-Chieh Lee, Naomi Yamashita, Yun HuangCSCW 2021 · 28 citations
Related papers
- Designing Conversational Evaluation Tools: A Comparison of Text and Voice Modalities to Improve Response Quality in Course EvaluationsThiemo Wambsganss, Naim Zierau, Matthias Söllner, Tanja Käser et al.CSCW 2022 · 17 citations
- Perceive, Adapt, and Interact: An Intelligent Virtual Agent for Education in Mixed RealityNaveed Ahmed, Zulaiha Afrah Sadakathullah Shaduly, Mohammed Lataifeh, Imad AfyouniIEEE VR 2026
- Who You Explain To Matters: Learning by Explaining to Conversational Agents with Different Pedagogical RolesZhengtao Xu, Junti Zhang, Anthony Tang, Yi-Chieh LeeCHI 2026 · 2 citations
- "Elinor's Talking to Me!": Integrating Conversational AI into Children's Narrative Science ProgrammingYing Xu, Valery Vigil, Andres S. Bustamante, Mark WarschauerCHI 2022 · 39 citations
- Visual StoryCoder: A Multimodal Programming Environment for Children's Creation of StoriesGriffin Dietz, Nadin Tamer, Carina Ly, Jimmy K. Le et al.CHI 2023 · 21 citations
