home

2025년 2분기 교육 연구에서의 시선추적 인사이트

시선추적 기술은 학생과 학습 자료의 상호작용에 대한 상세한 인사이트를 제공함으로써 교육 연구를 크게 향상시켰습니다. 2025년 2분기에는 피드백의 효과, 교과서의 시각적 주의력, 학습 시 행동 패턴을 탐구하기 위해 시선추적을 활용한 연구가 진행되었습니다. 이러한 연구 결과는 시선추적이 어떻게 교육 설계에 정보를 제공하고, 학습 전략을 최적화하며, 주의 할당과 상호작용 패턴을 분석하여 교육 성과를 개선할 수 있는지를 보여줍니다.

The Human Condition: Modal and Interactive Advantages of Teacher over AI Feedback on Childrens Mathematical Performance

Jacqueline Anton, Giulia Cosentino, Kshitij Sharma, Mirko Gelsomini, Micah Mok, Michail Giannakos & Dor Abrahamson

Artificial intelligence (AI) offers promising opportunities in providing educational feedback. However, AI agents often lack the nuanced, multimodal interactions of human teachers. Twenty-seven elementary school students participated in a 45-minute individual activity targeting integer arithmetic (e.g., “-2 + -3 = _”) to assess the comparative effectiveness of feedback provided by human teachers (n=15) and AI agents (n=12). Audio, video, and eye-tracking data were collected. Pre- to post-assessment scores revealed double the gains in the human condition....

EyeUnderstand: Dashboard for Gaze and Deep-Learning Driven Comprehension Estimation in Online Lectures

Ko Watanabe, Gitesh Gund, Jayasankar Santhosh, Haruka Sakagami, Yuki Matsuda, Andreas Dengel & Shoya IshimaruLecture Notes in Information Systems and Organisation Technology Driven Transformation

Online videos are a potent tool for educators to disseminate knowledge widely to diverse student audiences. However, collecting student feedback remains a significant challenge for lecturers, particularly in the absence of feedback. Understanding students’ subjective comprehension levels during online video lectures with sensor technology is yet to be thoroughly researched. This study uses eye-tracking technology to predict self-reported comprehension levels during video lectures. We recruited 20 participants from Germany and Japan who were invited to wa...

    Decoding Visual Attention: Eye-Tracking Insights Into Students’ Interaction with Images in Physics Textbooks

    Martina Kekule & Alžběta Krejčí

    We used the eye-tracking method to observe students’ strategies when they read a text from a physics textbook supplemented by both pictures and questions. In this paper we focused on students’ interaction with pictures that can contain different amounts of information; information ranging from purely decorative pictures (no information) to being important for understanding the text (according to Pozzer and Roth, Journal of Research in Science Teaching, 40(10), 1089–1114, 2003). Thirty-three high school students participated in the study. We observed diff...

    Once Upon a Time… Acquisition of Second Language Vocabulary Through Robotic Storytelling in Classroom Settings

    Anne-Lise Jouen, Reiko Matsunaka & Kazuo Hiraki

    Given their embodied social nature, robots have the potential to facilitate educational processes. As childhood is an opportune age to introduce a new language, robots could be particularly useful in the area of second language (L2) learning for children. This study assessed whether a social robot could provide efficient teaching to young children and how social cues of joint attention (pointing and gazing) can influence L2 learning. 82 children participated in an experiment with the Nao robot telling a story in French, adding -or not- joint attention ge...

    Investigating behavioral patterns of high- and low-performers in learning by teaching with educational videos

    Yan Zheng, Xin Zhao, Yuan Yang, Jiayu Wang, Zhongling Pi & Xiying Li

    Learning by teaching is an increasingly popular strategy in educational videos, designed to foster active learning. However, the relationship between instructional behaviors and learners’ performance in this context remains underexplored. This study employed a combination of eye-tracking and screen recording techniques to examine how learners’ behaviors while preparing for teaching through video viewing and engaging in subsequent teaching are associated with their own learning performance. The participants were 100 undergraduate students (86 females and ...

    Designing the HMI for a DC Motor Toolkit for Control Engineering Education

    Vivek Kant, Pramod Mhaske & P. S. V. Nataraj

    The aim of this article is to design a Human Machine Interface (HMI) for a direct current (DC) motor toolkit. This toolkit is designed to teach the concepts of control engineering to undergraduate engineering students. The kit itself has been developed over the course of a decade by several refinements from in‐class engagement and feedback from several batches of undergraduate learners. The kit can be connected to a computer through a USB port and can be provided inputs through it. The key challenge is to design a suitable HMI to support the operation of...

    Unraveling Coherence: The Impact of Image‐Relatedness in Concept Learning

    Tristan H. S. de Jonge, Anna Berti, Sanne van Schijndel, Margot van Wermeskerken & Ellen Kok

    The coherence principle suggests removing unnecessary—or seductive—content from educational texts to reduce cognitive load. However, the binary proposition that all seductive details should be excluded neglects images' potential to prime semantically related concepts, which makes texts easier to process. It was hypothesized that this priming would cause at least tangentially related images to enhance processing and recall of concepts. Participants learned 24 concepts under four conditions: direct depictions, tangentially related and unrelated images, and...

    MultiScaleAnalyzer for Spatiotemporal Learning Data Analysis: A Case Study of Eye-Tracking and Mouse Movement

    Shuang Wei, Chen Guo, Qingli Lei, Yingjie Chen & Yan Ping Xin

    With the development of high-performance computers, cloud storage, and advanced sensors, people’s ability to gather complex learning data has greatly improved. However, analyzing these data remains a significant challenge. Especially for spatiotemporal learning data such as eye-tracking and mouse movement, understanding and analyzing these data to identify the learning insights behind them is a difficult task. We propose a visualization platform called “MultiScaleAnalyzer”, which employs hierarchical structure to illustrate spatiotemporal learning data i...

    Multimodal Effort Profiles and Childrens Performance: Cognitive, Physiological and Physical Dimensions

    Kshitij Sharma, Serena Lee‐Cultura, Sofia Papavlasopoulou & Michail Giannakos

    Background: Effort measurement is essential for adaptation to interactive learning technologies. Most contemporary technologies measure effort through the log data (reaction time and correctness). Some adaptive technologies use facial expressions and attention to adapt. Objectives: We present a novel, complementary, and multimodal definition of effort that can be used to adapt not only the content but also the interaction in learning technologies for children. Methods: We propose a 3D view of an effort measurement, that is, cognitive, physiological, an...

    Investigating the impact of explanation type and peer relationship closeness on multimedia learning

    Qiuchen Yu, Caixia Liu, Zhongling Pi & Jiumin YangJournal of Eye Movement Research

    Writing explanations is widely recognized as an effective strategy to promote meaningful learning outcomes. However, most research focused on writing explanations for fictitious peers, with limited investigation into the benefits of writing for actual peers, particularly considering the influence of peer relationship closeness. To address this gap, the present study examined how explanation type (writing explanations vs. viewing explanations) and peer relationship closeness (close peer vs. distant peer) affect student’s perceived learning experience, att...

    • Tobii Pro X60 / X120 / T60 / T120
    교육 연구 분야의 최신 논문 탐색
    모든 발행물 보기

    교육 연구 강화하기

    최첨단 시선추적 연구를 통해 학생의 행동과 학습 전략에 대한 인사이트를 확보하세요.