Moodle Logs Research Articles

Student Behavior Analysis to Predict Learning Styles Based Felder Silverman Model Using Ensemble Tree Method

Learning styles are very important to know so that students can learn effectively. By understanding the learning style, students will learn about their needs in the learning process. One of the famous learning management systems is called Moodle. Moodle can catch student experiences and behaviors while learning and store all student activities in the Moodle Log. There is a fundamental issue in e-learning where not all students have the same degree of comprehension. Therefore, in some cases of learning in E-Learning, students tend to leave the classroom and lack activeness in the classroom. In order to solve these problems, we have to know students' preferences in the learning process by understanding each student's learning style. To find out the appropriate student learning style, it is necessary to analyze student behavior based on the frequency of visits when accessing Moodle E-learning and fill out the Index Learning Style (ILS) questionnaire. The Felder Silverman model's learning style classifies it into four dimensions: Input, Processing, Perception, and Understanding. We propose a learning style prediction model using the Ensemble Tree method, namely Bagging and Boosting-Gradient Boosted Tree. Afterwards, we evaluate the classification results using Stratified Cross Validation and measure the performance using accuracy. The results showed that the Ensemble Tree method's classification efficiency has higher accuracy than a single tree classification model.

Improving the portability of predicting students' performance models by using ontologies.

One of the main current challenges in Educational Data Mining and Learning Analytics is the portability or transferability of predictive models obtained for a particular course so that they can be applied to other different courses. To handle this challenge, one of the foremost problems is the models’ excessive dependence on the low-level attributes used to train them, which reduces the models’ portability. To solve this issue, the use of high-level attributes with more semantic meaning, such as ontologies, may be very useful. Along this line, we propose the utilization of an ontology that uses a taxonomy of actions that summarises students’ interactions with the Moodle learning management system. We compare the results of this proposed approach against our previous results when we used low-level raw attributes obtained directly from Moodle logs. The results indicate that the use of the proposed ontology improves the portability of the models in terms of predictive accuracy. The main contribution of this paper is to show that the ontological models obtained in one source course can be applied to other different target courses with similar usage levels without losing prediction accuracy.

Towards Portability of Models for Predicting Students’ Final Performance in University Courses Starting from Moodle Logs

Predicting students’ academic performance is one of the older challenges faced by the educational scientific community. However, most of the research carried out in this area has focused on obtaining the best accuracy models for their specific single courses and only a few works have tried to discover under which circumstances a prediction model built on a source course can be used in other different but similar courses. Our motivation in this work is to study the portability of models obtained directly from Moodle logs of 24 university courses. The proposed method intends to check if grouping similar courses by the degree or the similar level of usage of activities provided by the Moodle logs, and if the use of numerical or categorical attributes affect in the portability of the prediction models. We have carried out two experiments by executing the well-known classification algorithm over all the datasets of the courses in order to obtain decision tree models and to test their portability to the other courses by comparing the obtained accuracy and loss of accuracy evaluation measures. The results obtained show that it is only feasible to directly transfer predictive models or apply them to different courses with an acceptable accuracy and without losing portability under some circumstances.

Comparison Clustering Performance Based on Moodle Log Mining

The use of digital data now saves a lot of information, but still raw and not in the form of knowledge that can be directly seen, therefore we need a data processing to get useful particular understanding from raw data. Data Mining has an important role to process and find useful information from data. This process is also called Knowledge Discovery. Educational Data Mining is a Knowledge Discovery process in the world of education using data mining techniques. One method used in data mining is clustering. By using clustering analysis techniques, data can be grouped into groups without the need for prior knowledge (previous knowledge), so that the data is grouped based on similarity of patterns. This paper compares the K-means, Hierarchical and Louvain clustering methods to see the most appropriate clustering technique in analyzing log activity data in Moodle Learning Management System (LMS). The results of clustering are measured using the Silhouette Coefficient, and then we compare the values and distribution between clusters. In conclusion, Hierarchical clustering produces the highest Silhouette Coefficient value and also this algorithm can detect outlier data as new cluster. Louvain clustering perform very well to find cluster groups in new dataset as the algorithm does not required the number of clusters to be specified before. Louvain clustering can divide more evenly and precision compare to K-means and hierarchical cluster techniques.

Early Detection of Drop Outs in E-Learning Systems

After the popularity of Learning Management Systems, Data Mining and Learning Analytics have become emerging topics. Learning Management Systems such as Moodle, provide big amount of data to be used in analyzing students’ online behavior. This paper represents a method for early detection of drop outs from a Bachelor degree course using data mining methods. Data is collected through Moodle logs. For early detection, event logs till the first exam is taken into consideration. Decision Tree (DT) and Bayesian Network (BN) algorithms are used for the prediction. In the end it is shown that DT algorithm gives a higher over-all accuracy but BN is better for discovering fail cases as it has higher specificity.

Prediction of student academic performance using Moodle data from a Further Education setting.

Increasingly educational providers are being challenged to use their data stores to improve teaching and learning outcomes for their students. A common source of such data is learning management systems which enable providers to manage a virtual platform or space where learning materials and activities can be provided for students to engage with. This study investigated whether data from the learning management system Moodle can be used to predict academic performance of students in a blended learning further education setting. This was achieved by constructing measures of student activity from Moodle logs of further education courses. These were used to predict alphabetic student grade and whether a student would pass or fail the course. A key focus was classifiers that could predict likelihood of failure from data available early in the term. The results showed that classifiers built on all course data predicted student grade moderately well (accuracy= 60.5%, kappa = 0.43) and whether a student would pass or fail very well (accuracy= 92.2%, kappa=0.79). However, classifiers built on the first six weeks of data did not predict failing students well. Classifiers trained on the first ten weeks of data improved significantly on a no-information rate (p<0.008) though more than half of failing students were still misclassified. The evidence indicates that measures of Moodle activity on further education courses could be useful as part of on an early-warning system at ten weeks.

Activity Based Students’ Performance Measure Using Moodle Log Files

Activity Based Students’ Performance Measure Using Moodle Log Files

P.1.j.033 - Early recognition and treatment of delirium using the confusion assessment method for the intensive care unit in cardiac surgical intensive care unit

Two core courses have been given for several years to senior chemical engineering undergraduate students in flipped format, combining pre-class online preparation by the students, “class meetings” with the lecturer, and “active tutorials,” in which groups of students solve exercises. In 2020/21, the COVID-19 lockdown imposed online teaching of these courses to the 54 enrolled students. The objective of work presented in this paper is to explore the impact of the remote flipped classroom design on students' learning experience and achievements, in comparison to the regular flipped class in which only the first preparation phase was online. Because the course was taught completely online, a plethora of data was for the first time made available to support a thorough study of the course teaching protocol, including data from Panopto Analytics®, Zoom and Moodle logs, extensive self-report surveys, as well as actual learning outcomes (exam results). Statistical analyses including multivariate regression were performed to determine which factors most affect learning outcomes. The student surveys indicate that of the three class steps, the “active tutorial” gives students the most confidence in their mastery. Furthermore, analysis indicates that active students think that they benefit more than do passive students, as reflected by both self-reporting and final exam performances. The importance of underlying ability, as indicated by the GPA is a principal conclusion from the regression model, which also identifies attendance of “active tutorials” as a dominant positive effect on exam grades. Two important conclusions of our work are that the online and face-to-face versions of our flipped approach achieve indistinguishable learning outcomes and that students’ perceived confidence in their mastery is highest after the active tutorial.

A case study exploring video access by students

Every click made by a student is being captured by our learning platforms and integrated web-based tools. This store of data acts as, in its simplest form, part of an individual's digital behaviour with measurable points of interest. But how can this data give teachers an indication that our energy, time and potentially money spent making educational videos is worth the investment? Do-It-Yourself (DIY) videos are more commonly being made by teachers to replace written or face-to-face spoken content, provide an alternative instruction format or provide assessment feedback, to name just a few. This paper explores how we can help answer the most common question asked by teachers who undertake DIY video creation: are DIY educational videos being accessed by students? To answer this question, usage data generated by Moodle (student access point) and YouTube (video host) was collected. Simple analysis tools were employed to make sense of the typical log points generated by each system. Using a first year nursing subject as a case study, this project compared student access behaviour of pre-recorded one hour weekly video lectures. The results indicated an overall declining trend in viewing the video content online throughout the semester yet an increased video access when videos are presented in small segments assembled in YouTube playlists. An additional important outcome of this study was learning and sharing how to wrangle Moodle logs and YouTube Analytics data by non-statistical experts to quickly visualise video access. This information may ultimately support video creators to evaluate their videos, spend their time more efficiently when initially making videos, support decisions to change content or update curriculum, and to ultimately re-evaluate the role videos play in learning and teaching online environments.

Are computer information technology majors different than computer science majors in personality, learning style, or academic performance?

An increasing number of Computer Science (CS) departments include a Computer Information Technology (CIT) major into their programs to satisfy the increasing needs in the computing industry. Personality and learning styles have shown to have an effect on students' learning. We measured the personality and learning styles among CS and CIT students and analyzed their learning activities with Moodle logs at one regional comprehensive university. The results showed that CIT students have a slightly different personality compared to CS students but did not specify differences in learning styles and online activities. Both CS and CIT students' learning styles, and personalities correlated significantly with their performance, regardless of major. This study provides further understanding of CIT students, promotes an awareness of personalized class design, and contributes to the computer science education by enriching the literature and offering recommendations for pedagogy and research.

Students' LMS interaction patterns and their relationship with achievement: A case study in higher education

The use of Learning Management Systems has grown exponentially in the last several years and has come to have a strong effect on the teaching-learning process, particularly in higher education. The present study intends to examine students' asynchronous learning processes via an Educational Data Mining approach using data extracted from the Moodle logs of students who were grouped according to similar behaviors regarding effort, time spent working, and procrastination. The behaviors were then matched with different levels of achievement.First, the different patterns of students' involvement in the learning process in a Learning Management System were clustered. Second, the different variables selected from the Moodle records were studied to see if they were equally suitable for the configuration of student clusters. Third, the relationships between those patterns to students' final marks were examined.After analyzing the log data gathered from a Moodle 2.0 course in which 140 undergraduate students were enrolled, four different patterns of learning with different final marks were found. Additional results showed that there are variables more related to achievement and more suitable to group the students on the basis of which the different groups were characterized, namely, two Task Oriented Groups (socially or individually focused) and two Non Task Oriented Groups (procrastinators or non-procrastinators). These results have implications in the design of interventions for improving students' learning processes and achievement in LMSs.

Optimizing the Access Records of Students in the Moodle Virtual Learning Environment Database

Moodle is a freeware solution for Learning Management System (LMS) applied to Virtual Learning Environments (VLS). Despite the several features to support online courses, some desirable information is not easily provided, for instance, the amount of time the user spent in the system or in a specific course. A custom implementation can measure the time spent on the user's searches into the internal Moodle log and the distance between the records through the session time. However, for a large number of recorded logs, searching a single record passing through the other records requires a large time processing. As a consequence, the generation of custom reports is also costly. This work proposes a realtime plugin for Moodle to count the time spent by a student logged into the system retrieving the information from a pre-computed central table. The objective of the solution is to improve the counting precision and allow a faster retrieval of data. Our proposed plugin is validated using real data from the National School of Public Administration (Enap) in Brazil.

Using Fourier coefficients in time series analysis for student performance prediction in blended learning environments

AbstractIn this work, it is shown that student access time series generated from Moodle log files contain information sufficient for successful prediction of student final results in blended learning courses. It is also shown that if time series is transformed into frequency domain, using discrete Fourier transforms (DFT), the information contained in it will be preserved. Hence, resulting periodogram and its DFT coefficients can be used for generating student performance models with the algorithms commonly used for that purposes. The amount of data extracted from log files, especially for lengthy courses, can be huge. Nevertheless, by using DFT, drastic compression of data is possible. It is experimentally shown, by means of several commonly used modelling algorithms, that if in average all but 5–10% of most intensive and most frequently used DFT coefficients are removed from datasets, the modelling with the remained data will result with the increase of the model accuracy. Resulting accuracy of the calculated models is in accordance with results for student performance models calculated for different dataset types reported in literature. The advantage of this approach is its applicability because the data are automatically collected in Moodle logs.

E-COURSE MANAGEMENT WITHIN MOODLE IN HIGHER EDUCATION: TECHNOLOGICAL AND PEDAGOGICAL ISSUES

E-course management could be reflected both pedagogically, which implies analysis of teacher’s role as course manager, and administratively, making course activities traceable for estimation and institutional control. The article presents the results of Moodle log data analysis at higher education institutions in Latvia. Analysis is made in order to reveal Moodle log data opportunities and restrictions as an instrument, which could be purposefully used for course management both in administrative and pedagogical sense. Moodle log data analysis, which is showing time, activities and additional information about Moodle interactive tools usage, has been compared to teachers’ self-report survey results about their e-course management activities within Moodle. The study shows that teachers are tended to overestimate their course management activities’ frequency within Moodle comparing to lag data. Possibility to analyse Moodle log data by teachers and higher education institution administration could help to improve e-courses management, which is significant factor for improving learning outcomes.

Learning Style Classification Based on Student's Behavior in Moodle Learning Management System

In learning field, each student has his own learning style that affects his way of get, process, understand and percept information. Determining the learning style of students enhances the performance of learning process. Two methods are commonly used to acquire student's learning style: static by questionnaire and dynamic by tracing student's navigation on e-learning environment. In this paper, a new approach to classify students dynamically depending on their learning style was proposed. This approach was experimented on 35 students for Data Structure online course created using Moodle. By extracting students' behavior, data from Moodle log, the learning style for each student was identified according to Felder and Silverman model. Also, learning style based on the behavior have been compared with a quiz results conducted at the end of the course. Receiver operating characteristic (ROC) curve have been used to evaluate the quality of classification results comparing with quiz results. Good results with average accuracy of 76% are achieved. Students' data have been divided into four training and testing sets with different splitting ratio. Different testing accuracy values are obtained for the different ratios using each dimension of Felder-Silverman learning style model (FSLSM).

Understanding collaborative learning behavior from Moodle log data

Although course management systems (CMSs) were originally designed for teachers to manage their teaching, little interest has been directed at students' learning. Moodle is usually regarded as a CMS. However, how to make full use of its powerful features and design them into learning tools has rarely been investigated. This study investigates two features, embedded in the Moodle system, wiki and assessment tools, to find out how they are designed to support project-based learning. The theory and rationale for using these two features in learning activities are elaborated. The effects of wiki-supported collaboration, peer grading, and feedback on junior secondary students' enquiries in liberal studies are analyzed using hierarchical multiple regression. One hundred and eighty-six students participated in the study. Working on their own wikis, commenting on the work of peers, and previous performance on the humanities course were found to be significant predictors of liberal study project performance.

Of Conflict in Virtual Learning Communities in the Context of a Democratic Pedagogy

Conflict is a dynamic and complex concept which takes a crucial part in students' learning experiences, especially in learning communities underpinned with democratic pedagogy. Democratic pedagogies provide a base for emancipatory education by enabling students to participate in governance of their learning processes and so take responsibility for their own learning. In VLCs underpinned with democratic pedagogy, the method and content of the learning programme are not tightly structured in order to fulfil the community members' wishes, interests, ideas and so on, throughout the learning process. Within this framework, emergence of conflict among the community members is inevitable, given the diverse and sometimes clashing individual differences in participation in the negotiation process; in the loose structure of the programme which brings about uncertainty; and in the nature of the technological environments in which learning takes place. Once conflict emerges, it may lead to either an enjoyable or an unpleasant learning experience for students.Although in the literature it is identified as a negative or positive concept, in this research a neutral approach is taken to explore this concept holistically and openly.To surface the conflict in the learning process, a case study was conducted with third-year undergraduate students enrolled in a Computer Education and Instructional Technology programme in Turkey, during one academic term. In order to investigate students' experience with conflict in the context of democratic pedagogy, two learning groups were chosen: while the first group members did not perceive conflict, the second group members did experience severe conflict. By presenting these two contrasting groups' cases, it is aimed to exhibit the members' learning with and without conflict, and thereby to surface the importance of conflict in learning. Throughout the study, data was collected via interviews, focus group meetings, pre & post questionnaires, Moodle logs, and field notes. Data analysis was informed by grounded theory. Drawing on the findings, the dynamics and the roles of conflict in learning were discussed.We show how small groups of students in the community experienced different conflict pathways during the course of study. The findings demonstrate the importance of taking a holistic, processual view of the emergence of conflict in a learning community.

Do IT And Medicine Students E-Collaborate In The Same Way: Comparison Regarding Forums And Wikis

This study reveals comparison of behaviour patterns between students of medicine and IT students, regarding their use of forums and wiki. Olap techniques is used with in order to determine possible differences. The research was conducted based on the Moodle logs for learning management at Technical Faculty in Cacak, and Medical Faculty in Belgrade. Obtained results point towards the significant differences between these two groups, and the need for content adjustments in courses according to characteristics of different student sets.