TIDE-UPF will present four papers at European Conference on Technology-Enhanced Learning next September:

Ishari Amarasinghe, Francielle Marques, Ariel Ortiz-Beltran and Davinia Hernández-Leo,  Generative Pre-trained Transformers for Coding Text Data? An Analysis with Classroom Orchestration Data, European Conference on Technology-Enhanced Learning, Portugal, September 2023.

Abstract. Video content analysis is of importance for researchers in technology-enhanced learning. A common starting point typically involves transcribing video into textual transcripts that enable the application of a coding scheme to group the text into key themes. However, manual coding is demanding and requires time and effort of human annotators. Therefore, this study explores the possibility of using Generative Pre-trained Transformer 3 (GPT-3) models for automating the text data coding compared to baseline classical machine learning approaches using a dataset manually coded for the orchestration actions of six teachers in classroom collaborative learning sessions. The findings of our study showed that a fine-tuned GPT-3 (curie) model outperformed classical approaches (F1 score of 0.87) and reached a 0.77 Cohen’s kappa, which indicated a moderate agreement between manual and machine coding. The study also brings out the limitations of our text transcripts and highlights the importance of multimodal observations that capture the context of orchestration actions.

Marc Beardsley, Laia Albó and Davinia Hernández-Leo, A teacher professional development tool for creating and sharing research lessons on evidence-based teaching strategies, European Conference on Technology-Enhanced Learning, Portugal, September 2023.

Abstract. This demo paper presents a teacher professional development (PD) tool aimed at increasing educator adoption of evidence-based teaching and learning strategies such as retrieval practice, distributed practice, spaced learning, and reframing. The tool, evolving from Learning Design and online communities of teachers’ technologies, is an online platform centered on a teacher-led inquiry design template. The template, developed to scaffold teacher creation of research lessons (i.e., case studies) based on their use of the strategies, presents a 5-step teacher inquiry process: (1) lesson planning, (2) data planning, (3) activity and materials, (4) sense-making, and (5) communication. In addition to enabling teachers to create their own research lessons, document the lesson effects, and share their work with other teachers; the tool provides teachers with content and resources to deepen their understanding of the strategies and to support their usage. Furthermore, exemplar research lessons that teachers can duplicate and adapt to their contexts are offered to facilitate teacher learning and creation of case studies. The tool was co-designed with teachers as part of a European project that ran a series of workshops for teachers in four countries during the academic year 2021-2022 – and has been integrated into a 20-hour teacher PD program.

Emily Theophilou, Francesco Lomonaco, Gregor Donabauer, Dimitri Ognibene, J. Roberto Sánchez Reina and Davinia Hernandez-Leo. AI and Narrative Scripts to educate adolescents about Social Media Algorithms: Insights about AI overdependence, trust and awareness, European Conference on Technology-Enhanced Learning, Portugal, September 2023.

Abstract. Social Media Artificial Intelligence algorithms provide users with engaging and personalized content. Yet, the personalization of algorithms may have a negative impact on users who lack AI literacy. The limited understanding of SM algorithms among the population suggest that adolescents are more likely to place blind trust in the information they consume, exposing them to negative consequences (misinformation, filter bubbles and echo chambers). We therefore propose an intervention with a narrative scripts approach to raise awareness of AI algorithms in SM. To foster an authentic learning experience and question adolescents’ trust in AI, we deploy a low-accuracy AI image classifier. A quasi-experimental study was conducted among 144 high-school students in Barcelona, Spain. The results show that the narrative scripts intervention improved students’ awareness of SM algorithms and shaped more critical attitudes towards them. A comparison of students’ choices between human predictions and those produced by a low-accuracy AI classifier shows a lack of AI overdependence. Information about predictions’ source did not affect students’ trust or learning about AI. These findings contribute towards SM algorithms education and share insight into the effect of deploying low-accuracy detectors in learning technology interventions.

Laia Albó and Marc Beardsley, Teacher professional development to help students manage stress: barriers and enablers, European Conference on Technology-Enhanced Learning, Portugal, September 2023.

Abstract. This research work seeks to better understand barriers and enablers in addressing student stress in school settings using a continuing professional development (CPD) approach informed by research on teacher needs in the post- pandemic educational ecosystem. A survey study was conducted in which 91 teachers from 3 countries (Spain, Denmark, and Cyprus) participated. Preliminary results indicate that teachers hold negative stress mindsets – which presents a barrier the CPD must address across regions. Secondly, an emphasis on stress management techniques emerges as a focal point for the program. Thirdly, among elements that comprise the CPD approach, Learning Design and Digital Technologies for teaching and learning are topics generating the most interest from teachers whereas Open Educational Resources and Universal Design for Learning the least. Results are to inform the design and evaluation of a CDP approach and contribute to our understanding of teacher needs in the post- pandemic educational ecosystem.

Feel free to ask for copy of the manuscript to the autors, for personal use, at [email protected]!