Li Chen

• PhD
• Assistant Professor at Kyushu University

We explore the use of Large Language Models (LLMs) for automated assessment of open-text student reflections and prediction of academic performance. Traditional methods for evaluating reflections are time-consuming and may not scale effectively in educational settings. In this work, we employ LLMs to transform student reflections into quantitative...

Concept maps have been widely used in education to organize and represent information hierarchically. However, traditional methods for constructing concept maps often depend on human experts, which can be costly and time-consuming. The emergence of large language models (LLMs), such as GPT-4, has transformed concept construction and reasoning tasks...

This paper proposes a three-step approach to develop knowledge graphs that integrate textbook-based target knowledge graph with student dialogue-based knowledge graphs. The study was conducted in seventh-grade STEM classes, following a collaborative problem solving process. First, the proposed approach generates a comprehensive target knowledge gra...

Generative artificial intelligence (AI) tools like ChatGPT are becoming increasingly common in educational settings, especially in programming education. However, the impact of these tools on the learning process, student performance, and best practices for their integration remains underexplored. This study examines student experiences and interac...

In this study, a collaborative problem solving-based STEM course was implemented in a seventh-grade class. This study aimed to examine the effects of students’ prior knowledge on their CPS-based STEM learning processes by using a mixed-methods approach. First, a lag sequential analysis was used to investigate individual cognitive and metacognitive...

This study explores the effectiveness of Large Language Models (LLMs) for Automatic Question Generation in educational settings. Three LLMs are compared in their ability to create questions from university slide text without fine-tuning. Questions were obtained in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-C...

Despite the growing emphasis on integrating collaborative problem-solving (CPS) into science, technology, engineering, and mathematics (STEM) education, a comprehensive understanding of the critical factors that affect the effectiveness of this educational approach remains a challenge. This study aims to identify effective strategic and behavioral...

With the advent of generative artificial intelligence (AI), the scope of data analysis, prediction of performances, real-time feedback, etc. in learning analytics has widened. The purpose of this study is to explore the possibility of using generative AI to analyze educational data. Moreover, the performances of two large language models (LLMs): GP...

The integration of ChatGPT as a supportive tool in education, notably in programming courses, addresses the unique challenges of programming education by providing assistance with debugging, code generation, and explanations. Despite existing research validating ChatGPT's effectiveness, its application in university-level programming education and...

本研究では，ChatGPTを教育に応用する際，情報検索と判断方略を支援するためのワークシートをデザインし，ワークシートの利用状況を評価した．このワークシートでは，出典の確認，専門知識による判断，および合意評価の3段階を通じて，情報の信頼性を評価することが求められる．また，ワークシートを通じて学生がどのような情報判断方略を採ったかを評価できるようにデザインされており，これらの方略に関連するメタ認知の要因を特定した．今後は，ワークシートのデザインを改善し，ChatGPTとワークシートが学修成果への影響を探求し，教育におけるChatGPTのより効果的な使い方を提案していく．

Traditional textbooks are progressively being replaced by e-book systems, which are also being utilized more commonly in K-12 education. The study investigated learning behavioral patterns in a seven-week high school mathematics course using an e-book system. In this study, learning data from the BookRoll system was analyzed with lag sequential ana...

As the utilization of digital learning materials continues to rise in higher education, the accumulated operational log data provide a unique opportunity to analyze student reading behaviors. Previous works on reading behaviors for e-books have identified jump-back as frequent student behavior, which refers to students returning to previous pages t...

This study introduces a worksheet to support students using ChatGPT for information retrieval and understanding. ChatGPT is a powerful tool; however, its value in education largely depends on how it is used. Therefore, this study aims to provide a design of a worksheet to help students assess the credibility of information through source checks, ex...

Developed to maximize learning performance, learning analytics dashboards (LAD) are becoming increasingly commonplace in education. An LAD’s effectiveness depends on how it is used and varies according to users’ academic levels. In this study, two LADs and a learning support system were used in a higher education course to support students’ cogniti...

Self-regulated learning (SRL) is a very important factor in students' learning process and in theirlearning environment. However, even with a well-developed learning plan, it is difficult to achieve learning goals without good time management. Previous research indicates that time management skills have a positive effect on learning performance. Th...

The aim of this study was to examine the effects of Content and Language Integrated Learning (CLIL) designed according to the First Principles of Instruction (FPI). A 15-h Japanese CLIL course was implemented. A total of 16 university students attended the course and data were collected from multiple sources, including learning tests, questionnaire...

The aim of this study was to examine the effects of content and language integrated learning (CLIL) designed according to the First Principle of Instruction (FPI). Fifteen hours Japanese CLIL course was implemented. A total of 16 university students attended the course and multiple data sources, including learning tests, questionnaire feedback, and...

Learning skills include abilities, habits, understanding, and attitudes that are utilized to achieve learning. Students will not achieve good grades unless they manage their limited study time properly. However, it is not easy for them to organize their own study time and use it efficiently. Previous research on time management has not examined the...

The concept map has a positive effect on the enhancement of self-regulated learning (SRL) and learning performance in terms of cognitive learning tools, according to previous research. However, the relationships between knowledge construction state, learning behaviors, psychological state, and learning performance have not been clearly investigated...

本稿では，中学校における協調問題解決型STEM 授業において，生徒の学習動機と学習成果との関係性を調査した. その結果，「知的好奇心」，「達成」，「内的因果律」と「楽しさ」の学習動機要因と学習成果との間に有意な正の相関が示された. この結果より, 協調問題解決型STEM 授業をデザインする際，これらの要因を検討することが望ましいことが示唆された.

Mastering self-regulated learning (SRL) can help learners achieve their academic goals. In this paper, we discuss the designs and development of a learning analytics dashboard (LAD) we created to support learners’ metacognition, the Metaboard. We tested the Metaboard with four student participants, then surveyed their perceptions of the LAD and its...

This study aims to identify the types of learning logs that can measure learning skills. By using the learning analytics approach, the learning process can be analyzed. Identifying learning skills from the behavioral level can be linked to students' learning behaviors and how they support their own learning. However, the skills identified from thos...

In this study, a collaborative problem solving (CPS) based science, technology, engineering, and mathematics (STEM) course was designed, following CPS processes and the important factors of STEM education. The course was divided into three learning phases based on the contents and teaching approach. The purpose of the study was to identify the lear...

In this study, we used a learning analytics dashboard (LAD) in a higher education course to support students' metacognition and evaluated the effects of its use. The LAD displays students' reading path and specific behaviors when viewing digital learning materials. The study was conducted on 53 university students to identify the factors that affec...

Learning skills include abilities, habits, understanding, and attitudes which are utilized to achieve learning. Students will not achieve good grades unless they properly manage their limited study time. However, it is not easy for them to organize their own study time and learn how to use it efficiently. Notably, learning analytics has not been us...

近年，科学技術に関する知識習得とその知識を活用した問題解決能力の育成を目的として，協調的問題解決型STEM 教育が世界的に広まっている. 本研究では，ラーニングアナリティクスのアプローチを用いて，学習行動の視点から，協調的問題解決プロセスをどのようにデザインし，どのようなSTEM学習の要因をSTEM授業に取り入れるのかを検討した.

The existing researches and developments of dashboard visualizing results from learning analytics mainly serve the instructors instead of learners in a direct manner. Effective visualizations extracted from learning log data can help the students to reflect and compare studying activities and access their metacognition to improve their self-regulat...

Summer vacation is considered a cause of loss in students' learning performance. In this study, we investigated the differences in learning behaviors in reading learning materials and time-related behavior patterns regarding summer assignments among three classes under different instructional styles. The results showed that students' learning behav...

Previous research has established that motivation has a positive impact on the learning processes and behaviors [1][2]. Learning analytics (LA) can play an important role in addressing the issue of collecting learning behaviors. In this study, we observed the teaching activities of three classes and examined the relationships among learning motivat...

本稿では高等学校におけるラーニングアナリティクスに基づいた教育実践研究について、その知見を紹介し、授業デザインや改善への可能性について説明する。

This study designed a science course following collaborative problem solving (CPS) processes, and examined the effect on students’ CPS awareness. The Limnic Eruption CPS course was implemented using a Moodle system in a tenth-grade class. Considering the complex and coordinated nature of CPS, in order to improve CPS skills, it is important to ident...

This poster presents an initial prototype design and development of a learning analytics dashboard supporting self-regulated learning, from which the students can benefit from LA more directly. The current stage of the development focuses on providing visualizations of learning processes and behaviors extracted from operation log data of an e-book...

This study was designed to investigate effects of different learning behaviors in and out of class on students' learning performance and self-regulated learning (SRL) awareness improvement. The study was conducted at an eight-week information technology course for 70 university students. Results revealed that during in-class activities, using funct...

This paper introduces a practice to incorporate a learning analytics dashboard that analyzes and visualizes learning logs using digital textbooks for high school students. Based on the knowledge gained through the practice over the past six months, an important model for incorporating learning analytics in high schools is proposed. In the future, w...

Learning behaviors are associated with learning performance. Using the "BookRoll" digital learning material readers to collect log data, researchers can analyze logs and teachers can provide feedback to learners. The marker functions in BookRoll help students focus on learning content for future tests based on cognitive and metacognitive strategies...

This study examined the factors of learning behaviors that predict university students' learning outcomes including learning performance and self-regulated learning awareness improvement in a higher education institution in Japan. Stepwise multiple regression analyses were conducted with a sample of 70 freshman university students. The results reve...

Abstract The purpose of this study was to explore the factors that might affect learning performance and collaborative problem solving (CPS) awareness in science, technology, engineering, and mathematics (STEM) education. We collected and analyzed data on important factors in STEM education, including learning strategy and learning behaviors, and e...

Metacognition is an aspect in self-regulated learning and is necessary to achieve such learning in an effective and efficient manner. However, it is not always easy and accurate for learners to monitor or assess their own metacognition. In this study, we designed a learning analytics dashboard to improve self-regulated learning in online environmen...