In this paper, we introduce the BookRoll dataset that was provided for analysis in the joint acti... more In this paper, we introduce the BookRoll dataset that was provided for analysis in the joint activity on learning performance prediction in the Learning Analytics workshop at ICCE2018. Firstly, we provide a definition of the task, the dataset, how the data was collected, and briefly introduce previous work that has analyzed similar data from the BookRoll system. We also give an overview of the various approaches that were adopted by the participating authors for learner performance prediction using BookRoll reading behavior logs.
In recent years, learning analytics has become a hot topic with many institutes deploying learnin... more In recent years, learning analytics has become a hot topic with many institutes deploying learning management systems and learning analytics tools. In this paper, we introduce learning analytics platforms that have been established in two top national Japanese universities. These initiatives are part of a broader research project into creating wide-reaching learning analytics frameworks. The aim of the project is to support education and learning through research into educational big data accumulated on these platforms. We also discuss the future direction of our research into learning analytics platforms. This includes introducing a model in which learning analytics tools and the results of research can be shared between different education institutes.
As the adoption of digital learning materials in modern education systems is increasing, the anal... more As the adoption of digital learning materials in modern education systems is increasing, the analysis of reading behavior and their effect on student performance gains attention. The main motivation of this workshop is to foster research into the analysis of students' interaction with digital textbooks, and find new ways in which it can be used to inform and provide meaningful feedback to stakeholders, such as: teachers, students and researchers. In this workshop, participants analyzed the event logs from three different universities datasets with information on over 1000 students reading behaviors. Additional information on lecture schedules were also provided to enable the analysis of learning context for further insights into the preview, in-class, and review reading strategies that learners employ. Finally, workshop contributors were encouraged to implement their research results as a feature of an open LA dashboard.
There has been much research that demonstrates the effectiveness of using ontology to support the... more There has been much research that demonstrates the effectiveness of using ontology to support the construction of knowledge during the learning process. However, the widespread adoption in classrooms of such methods are impeded by the amount of time and effort that is required to create and maintain an ontology by a domain expert. In this paper, we propose a system that supports the creation, management and use of knowledge maps at a learning analytics infrastructure level, integrating with existing systems to provide modeling of learning behaviors based on knowledge structures. Preliminary evaluation of the proposed text mining method to automatically create knowledge maps from digital learning materials is also reported. The process helps retain links between the nodes of the knowledge map and the original learning materials, which is fundamental to the proposed system. Links from concept nodes to other digital learning systems, such as LMS and testing systems also enable users to monitor and access lecture and test items that are relevant to concepts shown in the knowledge map portal.
To enable students to engage in lifelong learning, it would require developing self-direction ski... more To enable students to engage in lifelong learning, it would require developing self-direction skills (SDS). The use of technology in education is common, however, the available software still offers poor support from a self-direction point of view. From the theories of self-directed learning (SDL) and evidence-based practice (EBP), we proposed a framework to track self-directed actions and represent strategies of practice by the learner. This framework is one of main components of the GOAL (Goal Oriented Active Learner) system. The GOAL system is built to support for acquisition of SDS in the context of learning and health. In this paper we describe how learner interactions in the GOAL system are captured as eXperience API statements and later visualized to enable learners reflect on their strategies.
The increasing volume of student reading logs from virtual learning environment (VLE) provides op... more The increasing volume of student reading logs from virtual learning environment (VLE) provides opportunities for mining student' engagement pattern in digital textbook reading. In order to mine and measure students' engagement pattern, in this paper, we extract several students' reading interaction variables from the digital textbook as metrics for the measurement of reading engagement. Moreover, in order to explore the presence of subpopulation of students that can be differentiated based on their engagement patterns and academic performances, we cluster students into different groups. Students are clustered based on their reading interactions such as total session of reading, total notes adding, etc. Accordingly, we identify students' engagement patterns from different groups based on the clustering analysis results. Several student subpopulations such as low engagement high academic performances and low engagement low academic performances are identified based on students' reading interaction characteristics by clustering analysis. The obtained results can be used to provide researchers with opportunities to intervene in the specific group of students and also an optimal choice for student grouping.
There has been much research that demonstrates the effectiveness of using ontology to support the... more There has been much research that demonstrates the effectiveness of using ontology to support the construction of knowledge during the learning process. However, the widespread adoption in classrooms of such methods are impeded by the amount of time and effort that is required to create and maintain an ontology by a domain expert. In this paper, we propose a method to automatically generate a contents model by analyzing learning materials with the aim of supporting the construction of knowledge structures. A map of the keyword nodes is constructed by applying text mining techniques to find the important words and phrases and their relations contained within the learning materials. The process retains links between the nodes and the original learning materials, and it is therefore possible to recommend and rank sections that cover a concept contained within the contents model map.
2012 IEEE/ACIS 11th International Conference on Computer and Information Science, 2012
ABSTRACT Various viewpoints are required to make a survey and a trend analysis on related researc... more ABSTRACT Various viewpoints are required to make a survey and a trend analysis on related research. In order to find important problems, especially in unfamiliar field, simple search and clustering is not enough. We have to read most of the articles carefully. The work requires a lot of time and effort. This paper analyzes the sentences that describe the problem using SVM. It turned out the negative words are more effective in discernment than manually selected clue words or the positive words.
In this paper, we introduce the BookRoll dataset that was provided for analysis in the joint acti... more In this paper, we introduce the BookRoll dataset that was provided for analysis in the joint activity on learning performance prediction in the Learning Analytics workshop at ICCE2018. Firstly, we provide a definition of the task, the dataset, how the data was collected, and briefly introduce previous work that has analyzed similar data from the BookRoll system. We also give an overview of the various approaches that were adopted by the participating authors for learner performance prediction using BookRoll reading behavior logs.
In recent years, learning analytics has become a hot topic with many institutes deploying learnin... more In recent years, learning analytics has become a hot topic with many institutes deploying learning management systems and learning analytics tools. In this paper, we introduce learning analytics platforms that have been established in two top national Japanese universities. These initiatives are part of a broader research project into creating wide-reaching learning analytics frameworks. The aim of the project is to support education and learning through research into educational big data accumulated on these platforms. We also discuss the future direction of our research into learning analytics platforms. This includes introducing a model in which learning analytics tools and the results of research can be shared between different education institutes.
As the adoption of digital learning materials in modern education systems is increasing, the anal... more As the adoption of digital learning materials in modern education systems is increasing, the analysis of reading behavior and their effect on student performance gains attention. The main motivation of this workshop is to foster research into the analysis of students' interaction with digital textbooks, and find new ways in which it can be used to inform and provide meaningful feedback to stakeholders, such as: teachers, students and researchers. In this workshop, participants analyzed the event logs from three different universities datasets with information on over 1000 students reading behaviors. Additional information on lecture schedules were also provided to enable the analysis of learning context for further insights into the preview, in-class, and review reading strategies that learners employ. Finally, workshop contributors were encouraged to implement their research results as a feature of an open LA dashboard.
There has been much research that demonstrates the effectiveness of using ontology to support the... more There has been much research that demonstrates the effectiveness of using ontology to support the construction of knowledge during the learning process. However, the widespread adoption in classrooms of such methods are impeded by the amount of time and effort that is required to create and maintain an ontology by a domain expert. In this paper, we propose a system that supports the creation, management and use of knowledge maps at a learning analytics infrastructure level, integrating with existing systems to provide modeling of learning behaviors based on knowledge structures. Preliminary evaluation of the proposed text mining method to automatically create knowledge maps from digital learning materials is also reported. The process helps retain links between the nodes of the knowledge map and the original learning materials, which is fundamental to the proposed system. Links from concept nodes to other digital learning systems, such as LMS and testing systems also enable users to monitor and access lecture and test items that are relevant to concepts shown in the knowledge map portal.
To enable students to engage in lifelong learning, it would require developing self-direction ski... more To enable students to engage in lifelong learning, it would require developing self-direction skills (SDS). The use of technology in education is common, however, the available software still offers poor support from a self-direction point of view. From the theories of self-directed learning (SDL) and evidence-based practice (EBP), we proposed a framework to track self-directed actions and represent strategies of practice by the learner. This framework is one of main components of the GOAL (Goal Oriented Active Learner) system. The GOAL system is built to support for acquisition of SDS in the context of learning and health. In this paper we describe how learner interactions in the GOAL system are captured as eXperience API statements and later visualized to enable learners reflect on their strategies.
The increasing volume of student reading logs from virtual learning environment (VLE) provides op... more The increasing volume of student reading logs from virtual learning environment (VLE) provides opportunities for mining student' engagement pattern in digital textbook reading. In order to mine and measure students' engagement pattern, in this paper, we extract several students' reading interaction variables from the digital textbook as metrics for the measurement of reading engagement. Moreover, in order to explore the presence of subpopulation of students that can be differentiated based on their engagement patterns and academic performances, we cluster students into different groups. Students are clustered based on their reading interactions such as total session of reading, total notes adding, etc. Accordingly, we identify students' engagement patterns from different groups based on the clustering analysis results. Several student subpopulations such as low engagement high academic performances and low engagement low academic performances are identified based on students' reading interaction characteristics by clustering analysis. The obtained results can be used to provide researchers with opportunities to intervene in the specific group of students and also an optimal choice for student grouping.
There has been much research that demonstrates the effectiveness of using ontology to support the... more There has been much research that demonstrates the effectiveness of using ontology to support the construction of knowledge during the learning process. However, the widespread adoption in classrooms of such methods are impeded by the amount of time and effort that is required to create and maintain an ontology by a domain expert. In this paper, we propose a method to automatically generate a contents model by analyzing learning materials with the aim of supporting the construction of knowledge structures. A map of the keyword nodes is constructed by applying text mining techniques to find the important words and phrases and their relations contained within the learning materials. The process retains links between the nodes and the original learning materials, and it is therefore possible to recommend and rank sections that cover a concept contained within the contents model map.
2012 IEEE/ACIS 11th International Conference on Computer and Information Science, 2012
ABSTRACT Various viewpoints are required to make a survey and a trend analysis on related researc... more ABSTRACT Various viewpoints are required to make a survey and a trend analysis on related research. In order to find important problems, especially in unfamiliar field, simple search and clustering is not enough. We have to read most of the articles carefully. The work requires a lot of time and effort. This paper analyzes the sentences that describe the problem using SVM. It turned out the negative words are more effective in discernment than manually selected clue words or the positive words.
Uploads