Learning and Evidence Analytics Framework (LEAF): Research and Practice in International Collaboration

Ogata, Hiroaki; Majumdar, Rwitajit; Yang, Stephen J.H.; Warriem, Jayakrishnan Madathil

doi:10.12937/itel.2.1.inv.p001

Cited by 10 publications

(8 citation statements)

References 22 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this problem, we plan to conduct the experiment in other schools. As we have a large-scale research network including other countries that use the LEAF platform (Ogata et al, 2022), using the dashboard in other schools would increase the generalizability of the results.…”

Section: Limitationsmentioning

confidence: 99%

Learning analytics for student homework activities during a long break: Evidence from K-12 education in Japan

Kuromiya,

Majumdar,

Horikoshi

et al. 2024

RPTEL

View full text Add to dashboard Cite

Learning Analytics (LA) is an emergent field that aims to better understand students and provide intelligence to learners, teachers, and administrators using learning log data. Although the use of technology in class is increasing in the K-12 sector and tertiary education, cases of effective implementation of LA in secondary schools have rarely been reported. This study offers an example of LA implemented in a junior high Math class during long vacations in Japan. This paper comprises two studies: first, we analyzed 121 students’ answer logs and their exam performance after vacation by the K-means clustering method. We found that students’ progress patterns were categorized into four types of engagement—early, late, high, and low—and the early and high-engagement groups obtained significantly higher scores than the low-engagement group. In the second study, we implemented a real-time dashboard that visualizes students’ progress patterns and gives students insights about their progress during the vacation period. We found that the dashboard significantly increased students’ interactions with the assignment, and the questionnaire survey determined that the LA dashboard motivated students to learn during the long vacation period. Considering the previous studies of LA, we estimate that LA-based interventions enhance students’ self-regulation skills, which is crucial for learning during long vacation periods. Our study offers a novel approach to implementing LA in K-12 education.

show abstract

Section: Limitationsmentioning

confidence: 99%

Learning analytics for student homework activities during a long break: Evidence from K-12 education in Japan

Kuromiya,

Majumdar,

Horikoshi

et al. 2024

RPTEL

View full text Add to dashboard Cite

show abstract

“…Firstly, a system using genetic algorithms is designed and implemented to form groups using learning log data from various data sources. In terms of data synthesis, the presented group formation system enables student models from different data sources underpinned by genetic algorithms and LEAF infrastructure that aggregates multiple learning logs [76]. These logs cover online reading logs for engagement and annotation behaviors, quiz scores from the LMS, uploaded offline test scores (performance data), survey responses (perception data), and so on.…”

Section: Optimized Group Formationmentioning

confidence: 99%

Data-Driven Support Infrastructure for Iterative Team-Based Learning

Liang,

Majumdar,

Horikoshi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Iterative team-based learning (TBL) is a common educational strategy for collaborative learning that involves sequential phases of individual and group learning activities. The advent of digital learning platforms, with the accumulation of learning log data, presents an opportunity to leverage datadriven techniques to enhance TBL practices. However, applying data-driven approaches in iterative TBL scenarios has received limited exploration in existing literature. Through a review of initial studies in this domain, data-driven iterative TBL emerges as a promising area. To explore this topic, we introduce a novel framework, drawing from the GLOBE framework for group learning, aimed at integrating datadriven designs into iterative TBL settings. This framework is proposed to guide data and activity design within iterative TBL, comprising four phases of group learning activity workflow and three essential steps of data flow. Additionally, we present two authentic instances supported by empirical evidence, offering insights into how educators can implement data-driven designs across different phases of TBL. Within the data-driven environment, we also uncover potential impacts and challenges of data-driven iterative TBL, to identify avenues for future research that can further expand our understanding of the possibilities in this domain.

show abstract

“…In Japan, an evidence-based LA framework called the Learning and Evidence Analytics Framework (LEAF) has been proposed to integrate learning analytics and evidence-based education [6], [7] . They defined the concept "teaching-learning cases (TLCs)," as a brief description of the intervention and the results captured from a single teaching-learning scenario.…”

Section: Regular Papermentioning

confidence: 99%

“…In previous studies, we proposed LEAF, an LA infrastructure [6], [7] . The LEAF aims to store TLCs that describe the results of the interventions and student learning logs.…”

Section: Novelty Of Our Systemmentioning

confidence: 99%

Supporting Reflective Teaching Workflow with Real-World Data and Learning Analytics

Kuromiya,

Nakanishi,

Horikoshi

et al. 2023

ITEL

Self Cite

View full text Add to dashboard Cite

Evidence-based practice stems from medicine. It involves the concept of Real-World Evidence (RWE), which involves the analysis of routinely collected patient data to extract evidence of practice. In this paper, we propose a learning-analytics (LA) based reflective teaching workflow that analyzes data from daily teaching and learning environments. This reflective teaching workflow uses a Learning and Evidence Analytics Framework (LEAF), a specific learning platform that is currently used in multiple Japanese and international educational institutions. This workflow provides a bottom-up approach for producing evidence from routinely collected data on the LA platform. We illustrate a case study in a Japanese high school math class to demonstrate the practical use of this reflective teaching workflow. We draw implications from this reflective workflow towards producing rich and robust evidence in the LEAF system, which should lead to the democratization of evidence-based practice in the classroom.

show abstract

Learning and Evidence Analytics Framework (LEAF): Research and Practice in International Collaboration

Cited by 10 publications

References 22 publications

Learning analytics for student homework activities during a long break: Evidence from K-12 education in Japan

Learning analytics for student homework activities during a long break: Evidence from K-12 education in Japan

Data-Driven Support Infrastructure for Iterative Team-Based Learning

Supporting Reflective Teaching Workflow with Real-World Data and Learning Analytics

Contact Info

Product

Resources

About