Learning Log Data Research Articles

Student's Behavior Clustering based on Ubiquitous Learning Log Data using Unsupervised Machine Learning

Online learning is the source of data generation related to learner's learning behaviors, which is valuable for knowledge discovery. Existing research emphasized more on an understanding of student's performance and achievement from learning log data. In this study, we presented data-driven learning behavior clustering in authentic learning context to understand students' behavior while participating in the learning process. The objective of the study is to distinguish students according to their learning behavior characteristics and identify clusters of students at risk of unsuccessful learning achievement. Learning log data were collected from ubiquitous learning applications before conducting Exploratory Data Analysis (EDA) and cluster analysis. We used partitional clustering using K-means algorithm and hierarchical clustering based on the agglomerative method to improve clustering strategies. The result of this study revealed three different clusters of students supported by data visualization techniques. Cluster 1 comprised more students with active learning behavior based on the total logs, total problems posed, and the total attempts in fraction operation and simplification. Students in clusters 2 and 3 had a higher attempt at problem-solving instead of problem-posing. Both clusters also focused on fraction's conceptual understanding. Knowledge discovery of this study used real data generated from ubiquitous learning application namely U-Fraction. We combined two different types of clustering method for delivering more accurate portrait of a student's hidden learning behaviors. The outcome of this study can be a basis for educational stakeholders to provide preventive learning strategies tailored to a different cluster of students.

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

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.

Prediction of In-Class Performance Based on MFO-ATTENTION-LSTM

In this paper, we present a novel approach to predicting in-class performance using log data from course learning, which is important in the field of personalized education and classroom management. Specifically, a set of fine-grained features is extracted from unit learning log data to train a prediction model based on long short-term memory (LSTM). However, to enhance the accuracy of the model, we introduce moth flame optimization-attention-LSTM (MFO-Attention-LSTM) as an improvement to the conventional LSTM-attention model. The MFO algorithm is utilized instead of the traditional backward propagation method to calculate attention layer parameters, thereby allowing the model to jump out of local optima. The proposed model outperforms the SVM, CNN, RNN, LSTM, and LSTM-Attention models in terms of the F1 score. Empirical results demonstrate that the optimization of the MFO algorithm contributes significantly to the improved performance of the prediction model. In conclusion, the proposed MFO-Attention-LSTM model offers a promising solution for predicting in-class performance using log data from course learning and could provide valuable insights for personalized education and classroom management.

Students' Learning Behaviour in Programming Education Analysis: Insights from Entropy and Community Detection.

The high dropout rates in programming courses emphasise the need for monitoring and understanding student engagement, enabling early interventions. This activity can be supported by insights into students' learning behaviours and their relationship with academic performance, derived from student learning log data in learning management systems. However, the high dimensionality of such data, along with their numerous features, pose challenges to their analysis and interpretability. In this study, we introduce entropy-based metrics as a novel manner to represent students' learning behaviours. Employing these metrics, in conjunction with a proven community detection method, we undertake an analysis of learning behaviours across higher- and lower-performing student communities. Furthermore, we examine the impact of the COVID-19 pandemic on these behaviours. The study is grounded in the analysis of empirical data from 391 Software Engineering students over three academic years. Our findings reveal that students in higher-performing communities typically tend to have lower volatility in entropy values and reach stable learning states earlier than their lower-performing counterparts. Importantly, this study provides evidence of the use of entropy as a simple yet insightful metric for educators to monitor study progress, enhance understanding of student engagement, and enable timely interventions.

Exploring jump back behavior patterns and reasons in e-book system

With the increasing use of digital learning materials in higher education, the accumulated operational log data provide a unique opportunity to analyzing student learning behaviors and their effects on student learning performance to understand how students learn with e-books. Among the students’ reading behaviors interacting with e-book systems, we find that jump-back is a frequent and informative behavior type. In this paper, we aim to understand the student’s intention for a jump-back using user learning log data on the e-book materials of a course in our university. We at first formally define the “jump-back” behaviors that can be detected from the click event stream of slide reading and then systematically study the behaviors from different perspectives on the e-book event stream data. Finally, by sampling 22 learning materials, we identify six reading activity patterns that can explain jump backs. Our analysis provides an approach to enriching the understanding of e-book learning behaviors and informs design implications for e-book systems.

Analysis of Student’s Learning Log Data in Fill-in-the-Blank Programming Questions

Analysis of Student’s Learning Log Data in Fill-in-the-Blank Programming Questions

Learning log-based automatic group formation: system design and classroom implementation study

Collaborative learning in the form of group work is becoming increasingly significant in education since interpersonal skills count in modern society. However, teachers often get overwhelmed by the logistics involved in conducting any group work. Valid support for executing and managing such activities in a timely and informed manner becomes imperative. This research introduces an intelligent system focusing on group formation which consists of a parameter setting module and the group member visualization panel where the results of the created group are shown to the user and can be graded. The system supports teachers by applying algorithms to actual learning log data thereby simplifying the group formation process and saving time for them. A pilot study in a primary school mathematics class proved to have a positive effect on students’ engagement and affections while participating in group activities based on the system-generated groups, thus providing empirical evidence to the practice of Computer-Supported Collaborative Learning (CSCL) systems.

How Learner Support Services Affect Student Engagement in Online Learning Environments

Learning is challenging, especially in the self-paced online learning environment. Not all the students start online learning with the skills to manage their learning plans, balance work-study, and find learning resources. Therefore, as an online educational institution, providing learner support services are essential to improving learning outcomes and student satisfaction. The existing studies have analyzed the impact of learner support services on student satisfaction, learning outcomes, and course retention. However, the relationship between these services and student engagement in the long-term learning process has not been fully examined. To address this issue, this paper investigates students' usage of two online learner support (OLS) services and their impact on student engagement. We examined four student groups categorized by their usage of two OLS services and analyzed student engagement with an online course using learning log data and visual analytics techniques. The findings indicate that the use of services and how many times the services are used are highly relevant to the pattern and level of student engagement, which suggests that the use of OLS services can be added to the indicators that reflect student learning status.

A Study on Analysing Speaking-pen Learning Log Data Considering Interests for Improvement of Primary School Children’s English Ability

As globalization advances, early English education for children in non-English speaking countries has been regarded as important. Many studies have proposed effective learning methods; however, few of these have analysed the relationship between learning processes and their effects with respect to detailed, classified interes ts. This study investigated and proposed detailed learners’ interests in primary school children’s English learning as variables from log data obtained through learning with a speaking-pen, and analysed the relation ship between features of learners’ interests and their improvements. Children were classified into four types based on their initial abilities, and an effective learning method was hypothesized for each type. The relationship between the features of children’s interests and variables related to self-regulated learning and English education , and their improvement of English skills, were then analysed . As a result, the validity of using variables of interests for understanding factors in English skill improvement was shown . https://doi.org/10.26803/ijlter.17.1.7

An Online Interaction Mode for International Trade Practice Course under Network Environment

In this study, behavior sequence analysis was applied to analyze behavior transformation pattern of students’ online study after the introduction of animation design in the course of International Trade Practice. As an effective method to study online study behavior, behavior sequence analysis can be used to track learners’ online learning path and describe their behavior sequence so as to explore their learning habits. Based on the analysis of 240 students’ online learning log data, it is found that multiple behavior sequences are significantly related to learning effect. In this paper, the theory of behavior sequence analysis was adopted to analyze the learning effect of International Trade Practice after the introduction of animation design. The result shows that the introduction of animation design can enhance students’ learning initiative.

Developing a source code reading tutorial system and analyzing its learning log data with multiple classification analysis

To efficiently support novice programming learners who are feeling the programming difficult, clarifying the cause of preventing programming comprehension, and developing a new instruction method appropriate for their comprehension would be necessary. The objective of this paper is to develop a learning support system to facilitate the programming instruction through source code reading, which is also available for self-study and mini-examination. In addition, this paper aims to discover the unit of knowledge (knowledge module) which will obstruct an understanding for programming beginners. The developed system can automatically generate a source code of C programming language in which there is no particular meaning because the source codes as learning materials are generated randomly. The developed system was utilized in a programming class for novices. This paper obtained student answer log, after the students had completed one semester of the instruction, and analyzed the data. From the analysis result, the description which may make program reading comprehension difficult for a beginner was clarified.

Speaking Practice Support System for Japanese Learners of English and Investigation of Learning Strategies and Patterns through Learning Log Data

This paper constructs the system to support Japanese English learners to speak fluently and accurately with the use of Text-to-Speech (TTS) technology. In addition, this paper analyzes how the learners’ learning behavior is changed according to the difficulty of the materials and investigates the relationship between their learning strategies and learning behaviors on the basis of learning log data. This paper concludes that the system affected their learning strategies according to the difficulty of the materials and their learning attitudes became more flexible and adaptive due to the use of the system.