Multimodal Learning Analytics Archives

Sep272023 by Nina MouhammadNo Comments

HyTea Consortium Meeting in Cologne

Artificial Intelligence, Competence development, Higher Education, Learning Analytics, Multimodal Learning Analytics, Project, Project meeting

How can software support presentation skills training? How can AI be used responsibly in this context? What to take from traditional presentation skills training and what to do completely different? In the HyTea consortium meeting, we discussed these questions but also many others and took important decisions on what to focus on in the HyTea project. We started preparing the needed knowledge needed for these critical decisions a few months ago when conducting interviews with presentation training experts. We asked them how they train presentation skills, how students should prepare a presentation and how they think AI or technology in general could support in presentation skills training. Furthermore, we also discussed concerns the experts had regarding AI usage in this context. In preparation of the consortium meeting, we synthesized all…

Sep72023 by Daniele Di MitriNo Comments

New pub: Using Accessible Motion Capture in Educational Games for Sign Language Learning

Conference, Multimodal Learning Analytics

A new publication will be presented at the EC-TEL conference 2023 in Aveiro, Portugal. "Using Accessible Motion Capture in Educational Games for Sign Language Learning" https://link.springer.com/chapter/10.1007/978-3-031-42682-7_74 Abstract Various studies show that multimodal interaction technologies, especially motion capture in educational environments, can significantly improve and support educational purposes such as language learning. In this paper, we introduce a prototype that implements finger tracking and teaches the user different letters of the German fingerspelling alphabet. Since most options for tracking a user’s movements rely on hardware that is not commonly available, a particular focus is laid on the opportunities of new technologies based on computer vision. These achieve accurate tracking with consumer webcams. In this study, the motion capture is based on Google MediaPipe. An evaluation based on user feedback shows that…

Jun162023 by Heather WehnerNo Comments

New pub: Measuring Collaboration Quality Through Audio Data and Learning Analytics

Book chapter, Computer-supported collaborative learning, Learning Analytics, Multimodal Learning Analytics

In the rapidly evolving twenty-first century, collaboration stands as a vital skill. Recognizing its significance, the detection of collaboration quality can play a pivotal role in fostering effective teamwork. This newly published chapter dives into the realm of collaboration quality detection and measurement, aiming to achieve the following objectives: Defining collaboration quality by leveraging audio data and unobtrusive learning analytics measures. Detailing the design of a sensor-based setup specifically tailored for automatic collaboration analytics. Advancing the quantification of collaboration quality through the utilization of this setup and presenting the analysis using insightful visualizations. Moreover, the chapter delves into the challenges and issues at hand while exploring potential solutions that build upon existing research. To elucidate the various objectives, the terminology of "indicators" (i.e., the events) and "indexes" (i.e., the process)…

May312023 by Heather WehnerNo Comments

A Vibrant Week of Exchange Between Brazilian and German LA Researchers

Higher Education, Learning Analytics, Multimodal Learning Analytics, Research Methods, Research topic, Workshop

From May 22 to 25, 2023 five esteemed guest researchers from Brazil visited the EduTec team in Frankfurt in the context of the Humboldt Foundation's Connect Program. This productive exchange not only shed light on the current state of Learning Analytics (LA) research in Brazil and Germany but also paved the way for potential collaborative research activities. Status of LA research in Brazil The week began with a discussion of the role of LA in the global South. Rafael Ferreira Mello from the Federal Rural University of Pernambuco (UFRPE) emphasized the importance of adapting LA methodologies to the specific context and needs of Brazil, ensuring inclusivity and accessibility in educational initiatives. Diego Dermeval from the Universidade Federal de Alagoas (UFAL) highlighted the potential of AI and LA in supporting teachers…

Nov82022 by Daniele Di MitriNo Comments

New CfP: CROSSMMLA @ LAK 2023 Workshop

Multimodal Learning Analytics, Workshop

Call for Papers: CROSSMMLA @ LAK 2023 Workshop: Leveraging Multimodal Data for Generating Meaningful Feedback To be held face-to-face on March 13, 2023, in Arlington, Texas, United States, in conjunction with the LAK 2023 conference. The CROSSMMLA workshop series has focused on collecting and analysing multimodal data across the physical and virtual spaces for understanding and optimising learning processes. (more…)

Sep142022 by Daniele Di MitriNo Comments

New Pub: Actionable Components of a Model for Augmented Feedback

Feedback, Higher Education, Multimodal Learning Analytics, Workshop

A new workshop paper was presented at the MILeS 2022 workshop written by Daniele Di Mitri, Sebastian Gombert, Onur Karademir entitled: Reflecting on the Actionable Components of a Model for Augmented Feedback. The MILeS 2022 – Multimodal Immersive Learning Systems workshop took place on the 13th of September at EC-TEL 2022 conference taking place in Toulouse, France. The paper will appear in the CEUR proceedings. Abstract. In this paper, we introduce the concept of "Augmented feedback'' as an enhanced version of traditional educational feedback enriched by digital data and artificial intelligence. To provide an operational definition of augmented feedback, we acknowledge previous research in the fields of technology-enhanced learning and learning analytics. We argue why augmented feedback constitutes a promising research direction for the future of learning. We define the…

Sep142022 by Daniele Di MitriNo Comments

New Pub: Privacy-Preserving and Scalable Affect Detection in Online Synchronous Learning

Artificial Intelligence, Conference, Multimodal Learning Analytics, Publication, Research topic

A full research paper entitled "Privacy-Preserving and Scalable Affect Detection in Online Synchronous Learning" written by Felix Böttger, Ufuk Cetinkaya, Daniele Di Mitri, Sebastian Gombert, Krist Shingjergji, Deniz Iren & Roland Klemke was accepted at the Seventeenth European Conference on Technology Enhanced Learning (EC-TEL 2022) Educating for a new future: Making sense of technology-enhanced learning adoption - Toulouse, France, 12-16 September 2022 The paper reports on a research prototype which stems from the cooperation between DIPF and the Open University of the Netherlands. Abstract The recent pandemic has forced most educational institutions to shift to distance learning. Teachers can perceive various non-verbal cues in face-to-face classrooms and thus notice when students are distracted, confused, or tired. However, the students’ non-verbal cues are not observable in online classrooms. The lack of…

Sep112022 by Daniele Di MitriNo Comments

New pub: The Rise of Multimodal Tutors in Education

Artificial Intelligence, Book chapter, Further Education, Higher Education, Multimodal Learning Analytics, Open access, Publication

A book chapter entitled "The Rise of Multimodal Tutors in Education" written by Daniele Di Mitri, Jan Schneider & Hendrik Drachsler was published open access in the "Handbook of Open, Distance and Digital Education" edited by Olaf Zawacki-Richter and Insung Jung. Abstract This chapter describes the insights derived from the design and development of the Multimodal Tutor, a system that uses artificial intelligence to provide digital feedback and support psychomotor skills acquisition. In this chapter, we discuss the insights which we gained from eight studies: (1) an exploratory study combining physiological data and learning performance (Learning Pulse); (2) a literature survey on multimodal data for learning and a conceptual model (the Multimodal Learning Analytics Model); (3) an analysis of the technical challenges of Multimodal Learning Analytics (the Big Five Challenges);…

Jun52022 by Fernando P. Cardenas-HernandezNo Comments

Workshop – Learning Psychomotor Skills with AI & AR/VR considering Technical and Mental Aspects

Artificial Intelligence, Augmented Reality, Event, Multimodal Learning Analytics, Project, Research topic, Summer School, Workshop

From May 21 to 28, the 16th version of the EATEL Summer School on Technology-Enhanced Learning (JTELSS 2022) was held in the city of Halkidiki, Greece, whose purpose is to promote the dissemination of research in the area of Technology Enhanced Learning and encourage international cooperation between researchers, students and people interested in this topic. As members of the MILKI-PSY project, Dr. Daniele Di Mitri, Fernando P. Cardenas Hernandez, Gianluca Romano and Dr. Jan Schneider attended JTELSS 2022. Additionally, Fernando P. Cardenas Hernandez and Gianluca Romano, as active participants in the summer school, presented the workshop entitled "Learning Psychomotor Skills with AI & AR/VR considering Technical and Mental Aspects". This workshop started with a theoretical introduction given by both exponents where the participants were able to identify some of the…

Mar232022 by Prof. Dr. Hendrik DrachslerNo Comments

New Pub: Towards Collaborative Convergence: Quantifying Collaboration Quality with Automated Co-located Collaboration Analytics

Conference, Conference, Event, Higher Education, Learning Design, Multimodal Learning Analytics, Publication

Collaboration is one of the four important 21st-century skills. With the pervasive use of sensors, interest on co-located collaboration (CC) has increased lately. Most related literature used the audio modality to detect indicators of collaboration (such as total speaking time and turn taking). CC takes place in physical spaces where group members share their social (i.e., non-verbal audio indicators like speaking time, gestures) and epistemic space (i.e., verbal audio indicators like the content of the conversation). Past literature has mostly focused on the social space to detect the quality of collaboration. In this study, we focus on both social and epistemic space with an emphasis on the epistemic space to understand different evolving collaboration patterns and collaborative convergence and quantify collaboration quality. We conduct field trials by collecting audio recordings…