Capturing temporal pathways of collaborative roles: A multilayered analytical approach using community of inquiry DOI Creative Commons
Ramy Elmoazen, Mohammed Saqr, Laura Hirsto

и другие.

International Journal of Computer-Supported Collaborative Learning, Год журнала: 2024, Номер unknown

Опубликована: Авг. 14, 2024

Abstract In collaborative learning, students may follow different trajectories that evolve over time. This study used a multilayered approach to map the temporal dynamics of online problem-based learning (PBL) and transition students’ roles across time full year duration. Based on data from 135 dental four consecutive courses throughout academic year, discourses were coded based community inquiry (CoI). A mixture model was identify roles. The identified leaders, social mediators, peripheral explorer roles, they visualized using epistemic network analysis (ENA). Similar sequence process mining. results showed varying activity levels three trajectories. Students in active-constructive trajectory took leadership while interactive mostly free rider predominant role. all returned their initial showing features typical stable dispositions. Both active (active constructive interactive) had very close achievement, whereas riders demonstrated lower grades compared peers. research suggests understanding role evolving can help teachers better design future activities, assign form groups, distribute tasks, and, more importantly, be able support students.

Язык: Английский

Diversity of frontier processes in Amazonian subnational jurisdictions: Frontier metrics reveal major patterns of human–nature interactions DOI Creative Commons
Guido Briceño, Julie Betbeder, Agnès Bégué

и другие.

Ecological Indicators, Год журнала: 2025, Номер 171, С. 113198 - 113198

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

Heterogeneity of early-onset conduct problems: assessing different profiles, predictors and outcomes across childhood DOI Creative Commons
Beatriz Díaz-Vázquez, María Álvarez-Voces, Estrella Romero

и другие.

Child and Adolescent Psychiatry and Mental Health, Год журнала: 2025, Номер 19(1)

Опубликована: Апрель 16, 2025

Язык: Английский

Процитировано

0

A guide to plant morphometrics using Gaussian Mixture Models DOI Creative Commons
Manuel Tiburtini, Luca Scrucca, Lorenzo Peruzzi

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Апрель 22, 2024

Summary Plant morphology is crucial in defining and circumscribing the plant diversity around us. Statistically speaking, study of done using morphometry, that context systematics used to verify hypotheses morphological independence between taxa. Nevertheless, methods currently analyse data do not match with conceptual model behind species circumscription on grounds. Here we 1) provide a step-by-step guide perform linear morphometric analyses 2) develop new conceptual, statistical, probabilistic framework for analyzing Gaussian Mixture Models (GMMs) taxonomy compare alternative taxonomic hypotheses.

Язык: Английский

Процитировано

1

Capturing the Wealth and Diversity of Learning Processes with Learning Analytics Methods DOI Creative Commons
Sonsoles López‐Pernas, Kamila Misiejuk, Rogers Kaliisa

и другие.

Опубликована: Янв. 1, 2024

Abstract The unique position of learning analytics at the intersection education and computer science while reaching out to several other disciplines such as statistics, psychometrics, econometrics, mathematics, linguistics has accelerated growth expansion field. Therefore, it is a crucial endeavor for researchers stay abreast latest methodological computational advances drive their research forward. diversity complexity existing methods can make this task overwhelming both newcomers field experienced researchers. With motivation accompany in challenging journey, book “Learning Analytics Methods Tutorials—A Practical Guide Using R” aims provide guide study, consult, take first steps toward innovation Thanks wealth authors’ backgrounds expertise, which include authors R packages experts applications, offers comprehensive array that are described thoroughly with primer on usage prior education. These sequence analysis, Markov models, factor process mining, network predictive modeling, cluster analysis among others. A step-by-step tutorial using programming language real-life datasets case studies presented each method. In addition, initial chapters devoted getting novice up speed learners basics data analysis. present chapter serves an introduction describing its main aim intended audience. It describes structure covered by chapter. also points readers companion code repositories facilitate following tutorials

Язык: Английский

Процитировано

1

Modeling the Dynamics of Longitudinal Processes in Education. A Tutorial with R for the VaSSTra Method DOI Creative Commons
Sonsoles López‐Pernas, Mohammed Saqr

Опубликована: Янв. 1, 2024

Abstract Modeling a longitudinal process in educational research brings lot of variability over time. The modeling procedure becomes even harder when using multivariate continuous variables, e.g., clicks on learning resources, time spent online, and interactions with peers. In fact, most human behavioral constructs are an amalgam interrelated features complex fluctuations such processes requires method that takes into account the multidimensional nature examined construct as well temporal evolution. this chapter we describe VaSSTra method, which combines person-based methods, sequence analysis life-events methods. Throughout chapter, discuss how to derive states from different variables related students, sequences students’ progression states, identify study distinct trajectories undergo similar We also cover some advanced properties can help us analyze compare trajectories. illustrate through tutorial R programming language.

Язык: Английский

Процитировано

1

Dissimilarity-Based Cluster Analysis of Educational Data: A Comparative Tutorial Using R DOI Creative Commons
Keefe Murphy, Sonsoles López‐Pernas, Mohammed Saqr

и другие.

Опубликована: Янв. 1, 2024

Abstract Clustering is a collective term which refers to broad range of techniques aimed at uncovering patterns and subgroups within data. Interest lies in partitioning heterogeneous data into homogeneous groups, whereby cases group are more similar each other than assigned without foreknowledge the labels. also an important component several exploratory methods, analytical techniques, modelling approaches therefore has been practiced for decades education research. In this context, finding or differences among students enables teachers researchers improve their understanding diversity students—and learning processes—and tailor supports different needs. This chapter introduces theory underpinning dissimilarity-based clustering methods. Then, we focus on some most widely-used heuristic algorithms; namely, K -means, -medoids, agglomerative hierarchical clustering. The -means algorithm described including outline arguments relevant R functions main limitations practical concerns be aware order obtain best performance. We discuss related -medoids its own associated function arguments. later introduce while outlining various choices available practitioners implications. Methods choosing optimal number clusters provided, especially criteria that can guide choice solution multiple competing methodologies—with particular evaluating solutions obtained using dissimilarity measures—and not only given method. All these issues demonstrated detail with tutorial real-life educational set.

Язык: Английский

Процитировано

1

Capturing temporal pathways of collaborative roles: A multilayered analytical approach using community of inquiry DOI Creative Commons
Ramy Elmoazen, Mohammed Saqr, Laura Hirsto

и другие.

International Journal of Computer-Supported Collaborative Learning, Год журнала: 2024, Номер unknown

Опубликована: Авг. 14, 2024

Abstract In collaborative learning, students may follow different trajectories that evolve over time. This study used a multilayered approach to map the temporal dynamics of online problem-based learning (PBL) and transition students’ roles across time full year duration. Based on data from 135 dental four consecutive courses throughout academic year, discourses were coded based community inquiry (CoI). A mixture model was identify roles. The identified leaders, social mediators, peripheral explorer roles, they visualized using epistemic network analysis (ENA). Similar sequence process mining. results showed varying activity levels three trajectories. Students in active-constructive trajectory took leadership while interactive mostly free rider predominant role. all returned their initial showing features typical stable dispositions. Both active (active constructive interactive) had very close achievement, whereas riders demonstrated lower grades compared peers. research suggests understanding role evolving can help teachers better design future activities, assign form groups, distribute tasks, and, more importantly, be able support students.

Язык: Английский

Процитировано

1