東京工業大学 環境・社会理工学院 融合理工学系. クロス研究室
Tokyo Institute of Technology, School of Environment and Society
Transdisciplinary Science and Engineering
Meet The Team
教育技术小组
教育技术（Edtech）/人工智能（AI）教育小组的学生研究的课题多种多样，包括虚拟现实（VR）辅助语言学习、个性化在线数学学习、教师培训、面部表情识别和聊天-GPT。我们有兴趣了解教育技术如何与人工智能相结合，特别是如何提高学生的学习效果，并评估这些新方法的有效性。
Luc Gougeon (LUC)
GEDES D3+ student
Luc is a third-year Canadian working adult doctoral student. His research focuses on educational policies and computational thinking. He is interested in understanding if Japanese in-service teachers are ready to teach programming in 2020. Luc has been living in Japan since 2008 and has been working as a university lecturer since 2015. Luc uses technology in his classes on a daily basis and hopes that his research will help him train the new generation of educators.
Promoting University Students and Elementary School Teachers to Become Lifelong Learners Through Play
In 2020, Japanese primary school educators will face the difficult challenge of introducing programming in their classes despite the fact that they never studied programming themselves. Our research aims are mapping the specific contours of the knowledge gap in-service teachers and extend this surveying to current universities students who are also lacking computer literacy skills. Most research in the field of computer literacy places a strong emphasis on children while neglecting the needs of in-service educators and older students. We will tackle this research by both surveying a range of students and teachers while conducting case studies consisting of an education intervention meant to give university students a quick grasp of computational thinking, computer literacy and basic programming concepts. The case study approach intends to offer students essentials skills in an active learning environment, skills which will be transferable to their future workplace or classroom if they intend to become educators. The results of this study are intended to offer stakeholders and policy-makers a clearer picture of the current educational landscape and enlighten their decisions. Below is an illustration of summarizing the issues which will be investigated related to education approaches and students’ knowledge needs.
Robert Anthony Olexa (Tony)
GEDES D3 student
Robert Anthony Olexa is conducting research on Japanese students studying English as a foreign language (EFL) in tertiary educational settings funded by a JSPS Kakenhi grant. The research focuses on how students use iconic gestures and embodied communication to acquire English in virtual environments. The compilation of an ongoing Virtual Reality (VR) Chat language learner corpus cross-referenced with video data and multimodal analysis is used to observe how embodied learning contributes to students’ EFL learning progress.
Embodiment and Iconicity for English as a Foreign Language Learning in Virtual Reality
Iconicity is a term used to describe communicative elements that closely resemble their referents. A degree of iconicity when communicating between caregiver and learner has been recognized as necessary for first language acquisition. Also, the usefulness of iconic gestures has been intuited by educators for second language acquisition as evidenced through the broader educational approach of “Active Learning,” and more concentrated EFL approaches such as Total Physical Response. However, the limitations are known, and the Japanese EFL setting remains situated in the classroom. At current, the learning experience is delivered mainly through passive activities.
Recent advancements in commercial VR technology have allowed for 6 degrees of freedom of movement (see below). Participants can move around in virtual environments with increased space and movement, allowing for embodied communication and iconic gestures. The liberation from a traditional classroom environment can improve EFL teaching and learning in Japan as a whole. Also, the findings may point to needed areas of improvement for software developers and designers of extended reality devices.
Xing Yipeng
GEDES M2 student
Facilitating Personalized Online Learning of Linear Algebra Concepts using Large Language Models
This research investigates the effectiveness of personalized online self-learning facilitated by Large Language Models (LLMs) in the domain of linear algebra at the university level. The objective is to evaluate whether LLM-driven interventions can enhance students’ understanding and performance on abstract mathematical concepts compared to traditional learning methods. The study also explores the characteristics of effective prompts through Natural Language Processing (NLP) analysis of LLM chat histories, aiming to establish a protocol for enhancing personalized learning experiences in mathematical education.
Yuka Matsuno
GEDES M1 student
The Impact of Avatar Appearance in Online English Conversations: Exploring Anxiety and Nervousness among ESL Learners
With the growing interest in learning English, the use of avatars to practice English conversation, especially through virtual reality (VR) environments, has increased. Although a few studies have investigated the relationship between changes in avatar appearance in VR and participants' anxiety levels, there is a lack of research focusing on the psychological effects of avatar changes in online video settings. Hence, research is being conducted to elucidate the characteristics of avatars on online video platforms that foster conversation without causing apprehension or unease among English learners.
Sitchai Rattanakarm
GSEP (undergraduate) B4 student
Emotion-Based Personalized Interactive Online Learning System
Using Facial Expression Recognition (FER) and ChatGPT Prompts:
Evaluating Effectiveness in Reducing Calculus Misconceptions
The expansion of online education highlights the challenges of teaching mathematics to university students, particularly addressing misconceptions in calculus due to the lack of real-time interaction. This research introduces a "Personalized Interactive Online Learning System" using advanced Facial Expression Recognition (FER) and ChatGPT prompts integrated within Moodle to enhance the online learning experience. By employing deep learning models like PAtt-Lite, the system analyzes real-time facial expressions to detect emotional cues, allowing for the categorization of learners into four learner types— active, passive, evaluative, and non-learner. This categorization helps tailor educational content and teaching methods to individual needs, aiming to make online mathematics education, especially Calculus, as effective as traditional settings. Furthermore, the integration of ChatGPT prompts allows the system to offer real-time, context-aware interactions and support, addressing learners' questions and clarifying concepts immediately as confusions arise. The system's effectiveness will be evaluated by its ability to enhance learning outcomes, offering a new approach to personalized and responsive online education.
