Artificial Intelligence Archives - Page 2 of 5

Jun292023 by Sebastian GombertNo Comments

Workshop: Large Language Models for Feedback Generation @ JTEL Summer School 2023

Artificial Intelligence, Feedback, Summer School, Workshop

At the seventeenth JTEL Summer School, Lukas Menzel and I had the pleasure of giving a workshop on the potentials and pitfalls of large language models for generating learner feedback. We kicked the event off with a general presentation on large language models. We explained the technical properties of well-known language models such as BERT or GPT. Following this, we went into different setups that can be used for feedback generation. On the one hand, this can involve training a BERT-based model to predict codes for input responses that trigger OnTask-style feedback rules. While this approach is stable regarding what feedback students receive, it is also inflexible, as such feedback cannot necessarily mirror all detailed intricacies that might occur in a student's response. For this reason, it can feel kind…

Jun212023 by Sebastian WollnyNo Comments

Advancing Education with “AI in the Loop” Interfaces @ #JTELSS23

Artificial Intelligence, Summer School, Workshop

From June 3rd to 10th, the city of La Manga in Spain hosted an exciting event, the Seventeenth EATEL Summer School on Technology Enhanced Learning (JTELSS 2023). Among the talented researchers organizing this renowned summer school for young TEL researchers in Europe, Sebastian Wollny contributed with a workshop focused on the speed design challenge. The challenge this year was to design an "AI in the Loop" interface specifically aimed at helping teachers analyze Exit Slips. These short reflection tasks, given at the end of a lesson, offer valuable insights into student comprehension and learning. However, teachers often struggle with limited time to thoroughly analyze these Exit Slips. Sebastian encouraged participants to place the human at the center of their design while incorporating artificial intelligence, embracing the concept of "AI in…

Jun62023 by Heather WehnerNo Comments

New pub: Lernpfade in adaptiven und künstlich-intelligenten Lernprogramme

Artificial Intelligence, Book chapter, Learning Analytics, Research Methods

In this newly published book chapter, the authors delve into the comparison between interactive, adaptive and artificially intelligent learning programs. While adaptive and AI-based applications offer promising potential, they face greater complexity in their development and have yet to fully establish themselves. To evaluate the prospects of these technologies, their respective capabilities are explored. Adaptive learning programs prove effective in skill acquisition, while AI-based solutions shine in cases where an explicit expertise model is challenging to articulate. The didactic and pedagogical challenges that lie ahead for AI-based learning applications are also highlight. By examining these factors, valuable insights are gained into the landscape of advanced learning technologies and their future implications. Reference: Kerres, M., Buntins, K., Buchner, J., Drachsler, H., & Zawacki-Richter, O.. (In Press). Lernpfade in adaptiven und künstlich-intelligenten…

May152023 by Prof. Dr. Hendrik DrachslerNo Comments

New research program: Towards Highly Informative Learning Analytics

Artificial Intelligence, Assessment, Book, Computational Psychometrics, Computer-supported collaborative learning, Feedback, Further Education, Higher Education, Keynote, Learning Analytics, Learning Design, Research Methods, School

On May 12, 2023, the Highly Informative Learning Analytics (HILA) research program of the EduTec@DIPF, studiumdigitale@Goethe University Frankfurt and the Open Learning and Instruction group@Open Universiteit was presented by Hendrik Drachsler at the main campus of the Open University of the Netherlands. The release of the HILA research program marks a significant milestone for the collaboration in the field of learning analytics between of the Dutch-German research collective. The HILA research program is focused on developing new tools and methods to collect, analyze, and interpret data that can help educational institutions to understand the learning process better. As part of the program's launch, a keynote by Ioana Jivet on student-facing learning analytics was provided. Ioana reported on two empirical studies investigating the effect of data-driven feedback on students. [pdf-embedder url="https://edutec.science/wp-content/uploads/2023/05/2023_05-Keynote-Symposium-Hendrik.pdf"…

Feb222023 by Jane YauNo Comments

HIKOF – Evaluation Study Completed

Artificial Intelligence, Assessment, Feedback, Learning Analytics, Project

In HIKOF (highly informative feedback for digital learning) project, the evaluation study has been successfully completed, where feedback was provided for about 1000 students in a Teacher Education Course (from Psychology department). Students' feedback on the feedback that was given to them was also collected to determine how comprehensive our feedback was, if it motivated them, and was helpful for them, and enhanced their learning progress. Specifically, the evaluation study focuses on the use of machine learning for the creation of personalized feedback that is both formative and summative. Data from a pilot study serves as a starting point for the evaluation to further optimize the AI technology for generating feedback. The evaluation study aims to investigate the effect of Highly Informative Automated Feedback (HIAF) on student performance and perception…

Dec122022 by Dana KubeNo Comments

Podcast “FutureSchool”: Child reporter talks with Scientist about Educational Technologies

Artificial Intelligence, Augmented Reality, Competence development, Computer-supported collaborative learning, Digitalisation, Event, Feedback, Invited talk, Promotion activity, Robots in Education, School, Transfer Activity

The German podcast "FutureSchool" looks at the classroom of the future and which technical aids for learning could be conceivable, but are also already being developed. Luis and DIPF education expert and our colleague Dana Kube consider together where technology is superior to teachers and when, in turn, teachers are unbeatable as real people with real experiences: https://blog.bildungsserver.de/klassenzimmer-der-zukunft/ The three-part podcast "FutureSchool" was created as part of the BMBF project "enorM - Lernen von (ÜBER)MORGEN". In the project, which is part of the "Science Year 2022 - Inquired about!", pupils and researchers have exchanged ideas in numerous formats, for example about new subjects and digital learning support.

Nov92022 by Onur KarademirNo Comments

BR Radio: Roboter statt Lehrerinnen und Lehrer? Wie sollte die Schule der Zukunft aussehen?

Artificial Intelligence, Invited talk, Learning Analytics, Learning Design, Robots in Education, School

Ist es denkbar, dass wir irgendwann keine echten Lehrer*innen mehr haben? Stattdessen fahren Roboter durch das Klassenzimmer und erklären alles? Wäre das überhaupt gut – wenn ja wie? Lasst uns gemeinsam darüber reden. Diese Sendung funktioniert in zwei Richtungen – ihr könnt natürlich alle Fragen stellen über Roboter in der Schule. UND: Ihr könnt einem Forscher sagen, bei was ihr wirklich gerne einen Roboter hättet. Denn das ist der Beruf von unserem Gast Onur Karademir – er promoviert im Bereich der Educational Technologies und findet raus, wann Lerntechnologien helfen und wann nicht. Die Sendung "RadioMikro" hier anhören

Nov22022 by Atezaz AhmadNo Comments

Presentation: Atezaz participated in the ICDLE conference and presented a new publication

Artificial Intelligence, Conference, Conference, Feedback, Further Education, Learning Analytics, Lifelong Learning, Open access, Publication, Self-Regulation

Our paper titled "Caught in the Lifelong Learning Maze: Helping People with Learning Analytics and Chatbots to Find Personal Career Paths" was accepted at the 13th International Conference on Distance Learning and Education (ICDLE 2022) held at the University of Barcelona, Spain. Atezaz Ahmad participated in the conference and presented their publication. The article will be published (open access) in the International Journal of Information and Education Technology. Abstract: Current lifelong learning platforms offer users a query option to select a wide variety of courses. However, finding a suitable course among the seemingly endless catalogs of options presented by the platforms is not straightforward. We argue that digital counseling can enhance this process. In this paper, we present a set of three formative studies where we explored the main aspects…

Oct272022 by Sebastian WollnyNo Comments

Shaping AI and the Future of Society @ Herrenhausen Conference and elf Annual Conference

Artificial Intelligence, Conference, Digitalisation

The journey from an initial idea to a finished product is generally known to be a long one. At least, this also seems to be the case with the implementation of AI systems that are intended to support various areas of everyday life. With regard to the automated understanding of language and images, AI models have made great progress in recent years and are being used in more and more applications, such as chatbots (see GUDI at Goethe University). The Educational Technologies team is therefore researching AI implementations in the education sector to support teachers and students, as well as to develop autodidactic learning environments. [caption id="attachment_4583" align="alignright" width="300"] Herrenhausen Conference "AI and the Future of Societies" 2022[/caption] The fact that the development of AI technologies continues to advance and…

Sep152022 by Sebastian GombertNo Comments

Sebastian Gombert @ EC-TEL 2022 Doctoral Consortium

Artificial Intelligence, Conference, Event, Learning Analytics, Research topic

At EC-TEL 2022, Sebastian Gombert presented his doctoral project "Methods and perspectives for the automated analytic assessment of free-text responses in formative scenarios". The goal behind this project is to build free-text assessment systems which can code constructed responses analytically. While much of the past work in response scoring focused on predicting holistic scores, analytic scoring allows to code free-text responses for multiple different aspects. The goal behind these efforts is to provide learners and teachers with useful feedback on each of them. A more detailed project overview will be released as part of the EC-TEL 2022 doctoral consortium proceedings soon.