Publication Archives - Page 5 of 20

Dec22024 by Prof. Dr. Hendrik DrachslerNo Comments

PhD Defense: A Bridge between Learning Analytics and Learning Design

Book, Event, Higher Education, Learning Analytics, Learning Design, Multimodal Learning Analytics, PhD defense, Publication, School

We warmly congratulate our esteemed associate partner, DR. Marcel Schmitz, on successfully defending his PhD thesis on November 29, 2024. Marcel is a senior lecturer and researcher in Data Intelligence and the Applied Data Science & Artificial Intelligence program at Zuyd University of Applied Sciences. In his dissertation, titled “Towards Learning Analytics-Supported Learning Design”, he focused on how education can be better personalized by incorporating learning analytics already in the design and course planning. His dissertation was supervised by Prof. Dr. Hendrik Drachsler (DIPF | Leibniz Institute & Goethe University Frankfurt), with co-supervisors Prof. Dr. Maren Scheffel (Ruhr University Bochum) and Dr. Roger Bemelmans (Zuyd University of Applied Sciences). Marcel's dissertation provides actionable strategies not only for higher education but also for other educational sectors. His work envisions a future…

Dec22024 by Atezaz AhmadNo Comments

New Pub: Harnessing the Power of Gaming to Influence Policies Addressing Climate Change

Conference, Game, Publication

As part of the GREAT (Games Realising Effective and Affective Transformation) project, co-funded by the European Union and UKRI, the project team has published the following paper at ECGBL which was held at Aarhus University, in October 2024. Harnessing the Power of Gaming to Influence Policies Addressing Climate Change – co-authored by Paul Hollins, Paul Watson, Anchal Garg, Jude Ower, Joost Schuur, David Griffiths, Barbara Kieslinger, Katharina Koller, Jane Yau, pages 403-413 Abstract: In this paper, the authors present the findings of an empirical case study examining the efficacy of the Games Realising Effective & Affective Transformation (GREAT) Case Study design process. The process is underpinned by an established Mixed Methodological Research (MMR) framework for eliciting the preferences of gamers and determining their priorities in climate change policies. Funded by…

Nov182024 by Heather WehnerNo Comments

New Pub: Understanding Learning Engagement in Asynchronous Online Settings

Higher Education, Journal, Learning Analytics, Publication

A newly published study illustrates the complexities of learning engagement (LE) in asynchronous online settings (AOSs) for university students. For university students it can be difficult to learn in such environments since these lack real-time interactions. This also makes it difficult for teachers to measure how engaged students actually are with their study materials. Through trace data, learning analytics can be used as a foundation to analyze students’ learning methods and LE. The study investigates whether LE can be characterized by the sub-dimensions: effort, attention and content interest. The study also explores the question of which trace data from student behavior within AOSs can best represent these factors of LE in self-reports. The research involved 764 university students and utilized best-subset regression analysis to determine which indicators most reliably represent…

Oct232024 by Heather WehnerNo Comments

New Pub: How Can Learning Analytics Dashboards Help Improve Students’ Self-Regulated Learning?

Conference, Empirical Study, Learning Analytics, Publication, School, Self-Regulation

Learning Analytics Dashboards (LADs) are important and widely-used tools used to give feedback to students and to aid them in their self-regulating learning process. Much has been done to investigate the design of LADs, but there is still a lack of knowledge regarding how students interpret the information shown on LADs and how they actually use these tools while learning. In a newly published study, we try to fill this gap. In an experimental study, we compared two groups of students. One group was given personalized self-regulared learning (SRL) feedback on their interactions and learning advances. The control group was only given minimal feedback calculated from the average class scores. After reviewing their feedback, students submitted written reflections on how they would adjust their study behavior. The researchers then analyzed…

Oct142024 by Heather WehnerNo Comments

New Pub: Conceptual Map Assessment Through Structure Classification

Assessment, Conference, Feedback, Publication, School

In educational settings concept maps are often chosen as a tool to help knowledge constructions be visualized. While mapping out concepts and their relationships, students are able to show how well (or not well) they understand certain subjects. A newly published study, which was presented at the AIED 2024 in Recife, Brazil, takes their usage a step further, examining the structural patterns in concept maps and developing an automated system to classify them. The researchers categorized 511 different concept maps into three key structures: spoke, network and chain. Each structure type can provide its own insight about the deepness of students’ understanding. For example, a "spoke" structure may indicate a surface-level understanding, while a "network" might reflect a more complex comprehension. The researchers trained multiclass classification models using statistical data…

Oct72024 by Heather WehnerNo Comments

New Pub: Learning At and From a Virtual Conference

Higher Education, Journal, New Pub

In light of the COVID pandemic and the climate crisis, many academic conferences have switched from face-to-face to virtual or hybrid conferences. The advantages of completely virtual conferences are clear. The organizers don’t need to look for physical rooms to book or need to organize food or drinks for participants. For the participants, this form of conferences can also be advantageous because there are no travel expenses and no travel time. Those participating from other countries can even take part in the conference despite being in different time zones or continents. The advantages go hand in hand with the disadvantages of limited personal interaction: no scientific (or leisurely) discussions during a coffee break or a chance to get to know fellow researchers seated nearby before a session begins. With all…

Jul182024 by Heather WehnerNo Comments

New Pub: Revolutionizing Essay Scoring with Hierarchical Rater Models

Artificial Intelligence, Assessment, Higher Education, Journal, New Pub

For a special issue on Natural Language Processing in Psychology we proposed a hierarchical rater model-based approach to address the challenges in automatic essay scoring. Essay writing tests are an integral part of educational systems, essential for assessing students' critical thinking, articulation and understanding. Since the manual scoring process requires significant resources and time, teachers are beginning to use Automated Essay Scoring (AES), which is potentially capable of alleviating the manual effort involved. #AutomatedEssayScoring #NaturalLanguageProcessing #FormativeAssessment #EducationalTechnology #MachineLearning #AIinEducation #HierarchicalRaterModel #EdTech #ScoringAutomation #AI #AssessmentTools #MeasurementInvariance #TransformerModels #EducationResearch #UniversityTesting #AIModels #TechInEducation There are an abundance of available models and each one has its own unique features and scoring methods. Thus, selecting the optimal model is complex and challenging, especially when different aspects of content have to be assessed over a number…

Jul122024 by Prof. Dr. Hendrik DrachslerNo Comments

Advancing Automated Analysis of Concept Maps at AIED24

Artificial Intelligence, Feedback, Higher Education, Learning Analytics, Publication, School, Workshop, Workshop

The 25th International Conference on Artificial Intelligence in Education (AIED 2024), held from July 8-12 in Recife, Brazil, was a significant event for the Highly Informative Learning Analytics Research Programme. This year marked the first Brazilian-German cooperation in this field, supported by the Alexander Humboldt Foundation, the DIPF in Frankfurt and IPN in Kiel under the ALICE project. Two workshop papers presented at the conference showcased innovative approaches to automatically analyze concept maps, promising to automate the way educators assess and understand the student-created context. #AIED24 #LearningAnalytics #ConceptMaps #AIinEducation #EducationalTechnology #MachineLearning #CulturalDiversity #RealTimeFeedback #EdTech #AI #Education #CrossCulturalCollaboration Paper 1: The Influence of Diverse Educational Contexts on Concept Map Structures Authors: Laís P. Van Vossen, Isabela Gasparini, Elaine H. T. Oliveira, Berrit Czinczel, Ute Harms, Lukas Menzel, Sebastian Gombert, Knut Neumann,…

Jul22024 by Heather WehnerNo Comments

New pub: Potentials and Challenges of Generative AI in Instruction and Research on Instruction

Artificial Intelligence, Feedback, General education, Journal, New Pub, School

Artificial Intelligence (AI) is becoming such a part of our daily lives that soon it will be almost impossible to imagine life without it. Especially since the emergence of ChatGPT and other Large Language Models, endless new possibilities have arisen for the usage of AI in many areas, especially in educational settings. Currently, the effective use of AI in education, both in teaching and learning, remains largely undefined, as do its limitations. We are also missing clarity regarding the potential benefits of AI for instructional research and the ethical boundaries of its use in this field. The opportunities and challenges associated with integrating AI into educational practices and research are explored in a newly published article from Hendrik Drachsler, Knut Neumann and Jochen Kuhn. In their paper they identify specific…

Jul12024 by Sebastian GombertNo Comments

New pub: Predicting Item Difficulty and Item Response Time with Scalar-mixed Transformer Encoder Models and Rational Network Regression Heads

Artificial Intelligence, Assessment, Computational Psychometrics, Conference, Higher Education, Publication, Workshop

In a contribution to the BEA 2024 Shared Task, we addressed the challenge of predicting the difficulty and response time of multiple-choice questions from the United States Medical Licensing Examination® (USMLE®). This exam is an important assessment for medical professionals. To predict these variables, we evaluated various BERT-like pre-trained transformer models. We combined these models with Scalar Mixing and two custom 2-layer classification heads, using learnable Rational Activations as the activation function. This multi-task setup allowed us to predict both item difficulty and response time. The results were noteworthy. Our models placed first out of 43 participants in predicting item difficulty and fifth out of 34 participants in predicting item response time. This demonstrates the potential of advanced AI techniques in improving the evaluation processes of critical exams like the…