Counting Clicks is Not Enough

Fincham, Ed; Whitelock‐Wainwright, Alexander; Kovanović, Vitomir; Joksimovíc, Srécko; Staalduinen, Jan-Paul van; Gašević, Dragan

doi:10.1145/3303772.3303775

Cited by 35 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, a research focus on explaining variability, accounting for heterogeneity, expanding modelling or using within‐person methods is timely. Furthermore, the validity of measurement methods in learning analytics—while it has been emphasized before—remains an issue that requires more research and experimentation (Fincham et al, 2019; Winne, 2020; Yarkoni, 2020). In addition, the search for contextual variations, what works for who and when should also be prioritized.…”

Section: Discussionmentioning

confidence: 99%

Modelling within‐person idiographic variance could help explain and individualize learning

Saqr

2023

Brit J Educational Tech

View full text Add to dashboard Cite

Learning analytics is a fast‐growing discipline. Institutions and countries alike are racing to harness the power of using data to support students, teachers and stakeholders. Research in the field has proven that predicting and supporting underachieving students is worthwhile. Nonetheless, challenges remain unresolved, for example, lack of generalizability, portability and failure to advance our understanding of students' behaviour. Recently, interest has grown in modelling individual or within‐person behaviour, that is, understanding the person‐specific changes. This study applies a novel method that combines within‐person with between‐person variance to better understand how changes unfolding at the individual level can explain students' final grades. By modelling the within‐person variance, we directly model where the process takes place, that is the student. Our study finds that combining within‐ and between‐person variance offers a better explanatory power and a better guidance of the variables that could be targeted for intervention at the personal and group levels. Furthermore, using within‐person variance opens the door for person‐specific idiographic models that work on individual student data and offer students support based on their own insights. Practitioner notesWhat is already known about this topic Predicting students' performance has commonly been implemented using cross‐sectional data at the group level. Predictive models help predict and explain student performance in individual courses but are hard to generalize. Heterogeneity has been a major factor in hindering cross‐course or context generalization. What this paper adds Intra‐individual (within‐person) variations can be modelled using repeated measures data. Hybrid between–within‐person models offer more explanatory and predictive power of students' performance. Intra‐individual variations do not mirror interindividual variations, and thus, generalization is not warranted. Regularity is a robust predictor of student performance at both the individual and the group levels. Implications for practice The study offers a method for teachers to better understand and predict students' performance. The study offers a method of identifying what works on a group or personal level. Intervention at the personal level can be more effective when using within‐person predictors and at the group level when using between‐person predictors.

show abstract

Section: Discussionmentioning

confidence: 99%

Modelling within‐person idiographic variance could help explain and individualize learning

Saqr

2023

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…As described in section (a) and (b), it has been proven that learner's click patterns can be considered as an indicator to predict the learner's performance and behavior. However, according to the study of [9], clicks are not enough to evaluate specific learner behavior through any online learning system. Besides that, other studies have also examined various factors of learner behavior, such as logging history and timely completion of assignments.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, due to its dynamic and numerous interpretation, data schema that contains meaningful learner interaction data based on click and time centered server log needs to be further investigated in terms of novel methods of extraction, triangulation, and visualization [8]. According to the study of [9], clicks are not enough to evaluate the learner's behavior through any online learning system. Besides, clickstream data schema that has been addressed in the literature section was limited to click patterns focusing on event-based click patterns and time in the logging history.…”

Section: Introductionmentioning

confidence: 99%

Clickstream Data Schema for Learning Analytics to Understand Learner Behaviour

2020

IJATCSE

View full text Add to dashboard Cite

Learning analytics has caught numerous researchers' attention in the last decade due to its ability to analyze, report, and process information produced by learners. Several research studies have examined learning analytics in terms of learner behavior to provide quality and efficient reporting for educators and higher learning institutions. In particular, the click pattern of the learner has been examined in terms of its significant impact on determining learner performance. Yet, the clickstream data schema that has been addressed in the literature was limited to click patterns focusing on event-based click patterns and time in the logging history. However, learner interaction logging history available in clickstream data schema for major online learning management systems holds great potential to reveal diverse and complex learner behavior patterns based on various significant learner behavior elements that are waiting to be discovered. The literature has shown that great interest has been given in understanding specific behavior produced by the learner through an online learning management system. Thus, this study aims to review previous related studies that could reveal possible learner click patterns, which could be considered as an indicator to predict the learner's performance and behavior. Potential learner interaction data that could be applied to produce a clickstream data stream has been outlined. As an implication, the contribution of the study could open up new frontiers that trigger the development of a learning analytics dashboard for various online learning platforms.

show abstract

“…Researchers in AIED, as in EDM, use more artificial intelligence algorithms (data mining, machine learning or deep learning) to analyze data from LMS, in order to establish the best possible predictions (Liu & Tan, 2020;Mao et al, 2018). However, in So-LAR, modeling, relationship exploration and data visualization (in the form of LADs) are transferred to the main actors of the LMS (Fincham et al, 2019;Millecamp et al, 2018). In the first approach, the aim is to design automatic monitoring, adaptation and personalization systems that do not require the intervention of a teacher or a student.…”

Section: Literature Reviewmentioning

confidence: 99%

TaBAT: Design and Experimentation of a Learning Analysis Dashboard for Teachers and Learners

Safsouf

Mansouri²,

Poirier

2021

JITE:Research

View full text Add to dashboard Cite

Aim/Purpose: Since the beginning of the COVID-19 pandemic, many countries have adopted online education as an alternative to face-to-face courses. This has increased awareness of the importance of analyzing learning data left by students to improve and evaluate the learning process. This article presents a new tool, named TaBAT, created to work with different LMSs in the form of dashboards accessible online and allowing teachers to monitor the progress of their learners and at the same time allow learners to visualize their learning process. Background: TaBAT is designed based on the results of our previous research on factors that can influence the success of online learners, where we proposed and statistically validated a model for assessing the success of online learners called e-LSAM (e-Learner Success Assessment Model). Methodology: Two studies are presented in this article. The first one is conducted on a group of students from two classes (each composed of two groups) of a higher institute in Morocco, who participated in courses organized in blended learning on the Moodle platform. For each class, one of the two groups had access to the experiment to use the TaBAT tool (exposed group) to analyze the learning traces, while the second group did not have access to the dashboard (control group). The second study aimed to understand the impact of the usage of the TaBAT tool on the two exposed groups. Contribution: The purpose of this article is to present a new analysis tool as well as to test this tool and to evaluate its impact on self-regulation and the prediction of academic success and, finally, to see how these students evaluate this tool. Findings: The results of the TaBAT usage demonstrate the effectiveness of the success algorithm, based on our theoretical model e-LSAM. The results also prove that this tool was able to increase the performance of the students of both groups exposed. The general evaluations of the participants also confirmed these results. Impact on Society: The article proposes a tool for institutions to facilitate the monitoring and control of students’ learning process. The tool provides visual information for teachers to study and react to in the educational context and gives students visualizations to promote their self-reflection and increase their performance and academic success. Future Research: Generalize the use of the TaBAT tool, incorporating both private and public institutions, in order to confirm the results obtained in this article and at the same time improve the self-regulation and academic success of learners.

show abstract

Counting Clicks is Not Enough

Cited by 35 publications

References 47 publications

Modelling within‐person idiographic variance could help explain and individualize learning

Modelling within‐person idiographic variance could help explain and individualize learning

Clickstream Data Schema for Learning Analytics to Understand Learner Behaviour

TaBAT: Design and Experimentation of a Learning Analysis Dashboard for Teachers and Learners

Contact Info

Product

Resources

About