JST CREST (2022-2027)
Technologies and Apps for Reliable Learning Analytics
Immediacy
Early prediction
Pattern matching
Persuasiveness
Reasoning for decision
Context analysis
Adaptability
Generalization
Personalized support
Early Prediction of Student Performance
This study helps improve the early prediction of student performance by RNN-FitNets, which applies knowledge distillation (KD) to the time series direction of the recurrent neural network (RNN) model. The RNN-FitNets replaces the teacher model in KD with “an RNN model with a long-term time-series in which the features during the entire course are inputted” and the student model in KD with “an RNN model with a short-term time-series in which only the features during the early stages are inputted.” As a result, the RNN model in the early stage was trained to output the same results as the more accurate RNN model in the later stages. The experiment compared RNNFitNets with a normal RNN model on a dataset of 296 university students in total. The results showed that RNN-FitNets can improve early prediction. Moreover, the SHAP value was employed to explain the contribution of the input features to the prediction results by RNN-FitNets. It was shown that RNN-FitNets can consider the future effects of the input features from the early stages of the course.
Image Segmentation Model for Handwritten Notebook Analytics
The main objective of this paper is to improve the image segmentation model for handwritten notebook analytics. We conducted a considerable amount of research in this area to increase the accuracy and efficiency of segmentation. To address the issues with traditional methods, we introduced attention mechanism and recursive residual convolutional neural network in the multi-task U-Net model. Through training and testing the model on handwritten notebook dataset and compared it with other existing technologies, we demonstrated the effectiveness of this method. The results showed that the model had a significant improvement in accuracy. Therefore, the research findings in this paper are important for improving the technology of handwritten notebook analytics.
Analytics of Student Handwritten Notes by GPT-4
Handwritten notes by students are a critical data source reflecting their learning status. Traditionally, educators have had to review these notes individually to gauge students' comprehension and mastery of course material. However, this method is time-consuming, inefficient, and often fails to capture and quantify students' learning progress and challenges comprehensively. With advancements in technology, especially in text recognition and machine learning, new avenues have opened up for automating this review process. This allows for a more efficient and systematic analysis of students' learning situations. This study aims to explore how these technologies can be utilized to automatically identify and analyze key information in students' handwritten notes. The goal is to assess students' learning outcomes and understanding more effectively. By automating the recognition and analysis of handwritten notes, the study seeks to provide educators with a powerful tool to monitor students' learning progress more accurately, identify learning obstacles, and offer personalized feedback and support based on individual needs. This paper introduces a technology integrating Attention Multi-task U-Net and GPT-4 for extracting data from handwritten notes. The method facilitates better understanding and analysis of student notes, offering teachers precise learning data and aiding students in receiving personalized learning support. The study underscores its potential in educational technology, particularly in improving teaching quality and student learning outcomes.
JST AIP Acceleration Research (2019-2021)
Sustainable Learning Analytics Cycle
Teaching & learning support
On-site/online education
Live sharing learning status
New learning environment
Learning repository
Sharing learning articles
Grow-up support for learners
Data analytics skills
Reflection via data
Real-time Learning Analytics Dashboard
While positive effects of imitating other learners have been reported, the recent increases in the number of online classes have seriously limited opportunities to learn how others are learning. Providing information about others’ learning activities through dashboards could be a solution, but few studies have targeted learning activities on e-textbook systems; it remains unclear what information representations would be useful and how they would affect learning. We developed a dashboard system that enables live sharing of students’ learning activities on e-textbooks. An experiment was conducted applying the dashboard in an online class to evaluate its impact. The results of questionnaires and quizzes were analyzed along with learning activities on the e-textbook system. From the questionnaire results, the most useful feedback types were identified. Regarding the impact on learning, the study found that a higher percentage of students who used the dashboard followed the progress of the class than those who did not. The study also found that students who used the dashboard were more likely to achieve higher quiz scores than those who did not. This study is the first to reveal what specific feedback is useful and to successfully investigate the impact of its use on learning.
Automatic Recommendation of Personalized Review Materials
In this study, we propose an integrated system to support learners' reviews. In the proposed system, the review dashboard is used to recommend review contents that are adaptive to the individual learner's level of understanding and to present other information that is useful for review. The pages of the digital learning materials that are estimated to be insufficiently understood by each learner and the webpages related to those pages are recommended. As a method for estimating such pages, we consider extracting the pages related to the questions that were answered incorrectly. We examined the accuracy of matching each question with the pages of the learning materials. We also conducted an experiment to verify the usefulness of the system and its effect on learning using a review dashboard. In the experiment, the evaluation of the review dashboard indicated that at least half of the participants found it useful for most types of feedback. In addition, the rate of change in quiz scores was significantly higher in the group using the review dashboard, which indicates that using the review dashboard has the effect of improving learning.
Teaching and Learning Among Learners Through Sharing Learning-Articles
Teaching and learning from one another is one of the most effective ways for learners to acquire proactive learning attitudes. In this study, we propose a new learning support system that encourages mutual teaching and learning by introducing a mechanism that guarantees sustainability. Learners submit articles called “learning-articles” that summarize their own learning and knowledge. The proposed system not only accumulates and publishes these articles but also has a mechanism to encourage the submission of necessary topics. The proposed system has been in operation since the academic year 2020, and it has collected learning-articles across our university’s nine academic disciplines from more than 300 learners. To investigate the effects of sharing learning-articles on education from the learners’ perspectives, a questionnaire was distributed among 25 students.
JST PRESTO (2015‐2018)
Real-Time Learning Analytics
Lecture support
Visualization of learning activities in classroom
Sharing learning status with each other
Learning support
Materials for catchup
Important keywords
Real-time learning analytics system
The purpose of this study is to propose a real-time lecture supporting system. The target of this study is on-site classrooms where teachers give lectures and a lot of students listen to teachers’ explanations, conduct exercises, etc. The proposed system uses an e-learning system and an e-book system to collect teaching and learning activities from a teacher and students in real time. The collected data are immediately analyzed to provide feedback to the teacher just before the lecture starts and during the lecture. For example, the teacher can check which pages were well previewed and which pages were not previewed by students using the preview achievement graph. During the lecture, real-time analytics graphs are shown on the teacher’s PC. The teacher can easily grasp students’ status and whether or not students are following the teacher’s explanation. Through the case study, the authors first confirmed the effectiveness of each tool developed in this study. Then, the authors conducted a large-scale experiment using a real-time analytics graph and investigated whether the proposed system could improve the teaching and learning in on-site classrooms. The results indicated that teachers could adjust the speed of their lecture based on the real-time feedback system, which also resulted in encouraging students to put bookmarks and highlights on keywords and sentences.
Automatic Summarization of Lecture Slides
We propose a novel method for summarizing lecture slides to enhance students’ preview efficiency and understanding of the content. Students are often asked to prepare for a class by reading lecture materials. However, because the attention span of students is limited, this is not always beneficial.We surveyed 326 students regarding the preview of lecture materials, revealing a preference for summarized materials to preview. Therefore, we developed an automatic summarization method for condensing original lecture materials into a summarized set. Our proposed approach utilizes image and text processing to extract important pages from lecture materials, optimizing selection of pages in accordance with a specified preview time. We applied the proposed summarization method to a set of lecture slides. In an experiment with 372 students, we compared the effectiveness of the summarized slides and the original materials in terms of quiz scores, preview achievement ratio, and time spent previewing. We found that students who previewed the summarized slides achieved better scores on pre-lecture quizzes, even though they spent less time previewing the material.