New Pub: Tracking students’ progression in developing understanding of energy using AI technologies

New Pub: Tracking students’ progression in developing understanding of energy using AI technologies

Artificial Intelligence, Journal, Publication, School
[caption id="attachment_7553" align="alignright" width="400"] Instructional unit, with pre- and post-test, as well as lesson-set-level assessment[/caption] In physics education, some students fail to have the foundational knowledge of energy concepts needed to engage in societal debates on climate change and energy transformation. A newly published study highlights the potential of AI to identify students with different learning trajectories and to help bridge the knowledge gaps. The researchers used a digital workbook designed to teach energy concepts to collect detailed interaction data from over 500 students. After applying exclusion criteria, data from 172 students were analyzed to identify their productive and unproductive learning curves. [caption id="attachment_7554" align="alignleft" width="400"] Example single choice pretest item[/caption] By using machine learning, specifically random forest models, and natural language processing (NLP), the researchers were able to classify…
Read More
New Pub: Pedagogical Framework for Hybrid Intelligent Feedback

New Pub: Pedagogical Framework for Hybrid Intelligent Feedback

Artificial Intelligence, Feedback, Journal, Publication
[caption id="attachment_7525" align="alignright" width="300"] Principles of hybrid intelligent Feedback[/caption] ChatGPT and other Generative Artificial Intelligence (GenAI) tools have quickly become an active part of everyday academic life. Both teachers and students use them regularly to do research, summarize texts or responses, create exercises or quizzes or explain course content. But GenAI needs to be used in a sensible manner and consistent with sound teaching principles. Otherwise, it could lead to an over-reliance on technology and neglect the important roles of teachers and students. Ideally, GenAI should be used to complement rather than replace human-centered education. When pedagogical practices combine the strengths of humans and AI, this can ultimately lead to enhanced creativity, empathy and academic comprehension of students. A recently published paper explores a promising field of human-AI collaboration in…
Read More
ML2MT at the “AI and the Future of Society” Symposium

ML2MT at the “AI and the Future of Society” Symposium

Artificial Intelligence, Conference, Event
At the final symposium “AI and the Future of Society” on April 23, 2025, the ML2MT project team presented key outcomes from their research on human-machine collaboration. Moving beyond traditional AI, the project explored how machines and humans can mutually benefit and learn from each other in a continuous loop. The results of this interdisciplinary project span multiple domains: In medicine, AI systems were found not only to assist diagnoses but also to promote reflection among professionals, encouraging deeper awareness of their decision-making processes. In education, adaptive AI tools were developed to analyze student feedback and help teachers identify learning gaps more effectively. In human-AI interaction, systems were designed to remember and apply user feedback, improving efficiency and reducing the need for repetitive input. Looking ahead, the project will focus…
Read More
A Warm Welcome to Our Guest Researcher Paola Pavone Salafia

A Warm Welcome to Our Guest Researcher Paola Pavone Salafia

Artificial Intelligence, Team
We are pleased to announce that Paola Pavone Salafia, a doctoral researcher from the University of Macerata (UniMC) and the European University of Rome (UER), will be joining us as a guest researcher from 10.03 – 10.06.205. Paola's work focuses on the use of advanced technologies, particularly Artificial Intelligence (AI), in education to foster inclusive and innovative teaching practices. Her research aligns closely with our ongoing studies on learning disabilities, educational accessibility and teacher agency, particularly in the context of AI-supported teaching methodologies. Paola's research aims to explore how AI can enhance personalized learning for students with special educational needs, as well as investigate the role of AI as a “dual teacher”, which works alongside educators to enrich teaching experiences. Paola will join the HyTea project led by Daniele Di Mitri…
Read More
Legal Assessment of AI and Learning Analytics in Teaching and Learning

Legal Assessment of AI and Learning Analytics in Teaching and Learning

Artificial Intelligence, Learning Analytics, Press, Report
As with any new technology, the laws and regulations relating to them seem to always be one step behind and one can feel somewhat lost in a foggy, legal grey zone. The same is true for the use of AI. Using AI in a legally compliant way depends on its specific application, its range and the technical details. This has to be checked and regulated in accordance with the law in order to be able to use each AI technology safely, for the intended purpose and in compliance with data protection regulations. But how can universities know if they are using Learning Analytics and AI technologies in a legally compliant manner? In a first step in answering this question, the Goethe University has recently published an extensive legal assessment about…
Read More
New Pub: Impact of Artificial Intelligence Based Systems to Improve Mathematics Achievement in Rural Schools

New Pub: Impact of Artificial Intelligence Based Systems to Improve Mathematics Achievement in Rural Schools

Artificial Intelligence, Journal, New Pub, School
Poor mathematics achievement, especially in rural areas, remains a persistent challenge. Schools in rural areas often struggle to attract and retain highly qualified mathematics teachers, and the teacher shortage across the United States further amplifies this issue. Numerous studies indicate that AI-based systems can enhance mathematics achievement and improve test scores on both standardized and non-standardized tests in K-12 and higher education. These systems offer adaptive and personalized education tailored to the unique needs of each student. By creating learning pathways based on students' current knowledge and offering real-time feedback and support, AI-based systems have the potential to improve learning outcomes across the P-20 educational spectrum. Despite the increasing adoption of AI-based tools, there is limited research on its impact on K-12 classrooms within rural contexts, especially among socioeconomically disadvantaged…
Read More
Girls and Women in STEM Forum of the European Institute for Innovation and Technology (EIT)

Girls and Women in STEM Forum of the European Institute for Innovation and Technology (EIT)

Artificial Intelligence, Award, Conference, Digitalisation, Event, Transfer Activity
Our Co-Worker Dana Kube was selected to be a jury member of this year's Girls and Women in STEM Award of the European Institute for Innovation and Technology (EIT) in Budapest. Read her report: I'm still buzzing with the energy from the Women and Girls in STEM Forum 2024! It was an inspiring day filled with conversations on AI, inclusion, and the future of STEM with girls and women from all over Europe. The keynote speakers, Pia Ahrenkilde Hansen and Ilaria Tagliavini, emphasised the urgent need for more women to lead the next generation of scientists in Europe, highlighting the European Commission’s commitment to this mission through strategic plans for STEM education. Ilaria celebrated Girls Go Circular’s expansion to 32 countries, recognising the need for a mindset shift towards greater…
Read More
HILA goes to school – Keynote at ISDT24, Linnaeus University, Sweden

HILA goes to school – Keynote at ISDT24, Linnaeus University, Sweden

Artificial Intelligence, Conference, Feedback, Keynote, Learning Analytics, School
What happens when Highly-Informative Learning Analytics (HILA) goes to school? That’s exactly what Hendrik Drachsler explored during his keynote at the 3rd International Symposium on Digital Transformation (ISDT24) in Linnaeus University Växjö, Sweden. His talk highlighted the impact of the AFLEK project, a transformative initiative under the HILA research program, which focuses on improving learning outcomes in secondary schools through actionable data and AI-driven tools. The keynote wasn't just about theoretical advances; it presented real-world applications that are actively shaping how secondary education functions today. Through three key publications, Drachsler demonstrated how the integration of Data-Enriched Learning Activities (DeLA), teacher dashboards, and empirical research has paved the way for improved teaching practices and measurable student success. Let’s dive into what happens when HILA meets the classroom. Key Highlights from Hendrik…
Read More
Keynote at #LearningAID24, Bochum Germany

Keynote at #LearningAID24, Bochum Germany

Artificial Intelligence, Conference, Event, Higher Education, Keynote, Learning Analytics, Learning Design
At the recent #LearningAID24 conference in Bochum, Germany, Hendrik Drachsler delivered a keynote that challenged conventional perspectives on Learning Analytics and AI in education. He opened the discussion by examining the often ambiguous boundary between Learning Analytics and AI in education, posing a thought-provoking question: are these two areas truly distinct, or do they converge into one shared domain? Beyond theoretical discussions, Hendrik presented early empirical findings from the research program on Highly-Informative Learning Analytics (HILA), advocating for a more evidence-based approach to integrating Learning Analytics and AI into education. The goal, he argued, should be to ensure that these technologies effectively meet the informational needs of learners, providing meaningful and actionable insights. He framed the 2nd conference day around the theme: INFORMED PRECISION -  This concept captures the need…
Read More
New Pub: Revolutionizing Essay Scoring with Hierarchical Rater Models

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…
Read More