Explore the vast range of titles available.

Teachers’ spatial behaviours in the classroom can strongly influence students’ engagement, motivation and other behaviours that shape their learning. However, classroom teaching behaviour is ephemeral, and has largely remained opaque to computational analysis. Inspired by the notion of Spatial Pedagogy, this paper presents a system called ‘Moodoo’ that automatically tracks and models how teachers make use of the classroom space by analysing indoor positioning traces. We illustrate the potential of the system through an authentic study with seven teachers enacting three distinct learning designs with more than 200 undergraduate students in the context of science education. The system automatically extracts spatial metrics (e.g. teacher-student ratios, frequency of visits to students’ personal spaces, presence in classroom spaces of interest, index of dispersion and entropy), mapping from the teachers’ low-level positioning data to higher-order spatial constructs. We illustrate how these spatial metrics can be used to generate a deeper understanding of how the pedagogical commitments embedded in the learning design, and personal teaching strategies, are reflected in the ways teachers use the learning space to provide support to students.

There is a growing interest in creating Learning Analytics (LA) interfaces that support students and teachers directly. Thus far, many of these solutions have been materialised as dashboards and visualisations. However, although a growing number of prototypes and commercial products aimed at supporting students/teachers exist, their limitations are coming under scrutiny. For instance, many visual LA tools are failing to provide meaningful and relevant insights that can support students reflections on their embodied teamwork activity. Moreover, there are additional challenges in visualising and communicating the wide variety of multimodal sensor data captured from physical spaces, in a way that supports educational stakeholders (e.g., teachers or students), who as casual users, have limited training in data analysis and interpretation. Thus, this thesis engages research in Information Visualisation (InfoVis) and specifically the Guidance visualisation paradigm that aims to support casual users, or those users with low analysis expertise, to narrow the gap of data visualisation interpretations. Data Storytelling is one way to provide guidance, as a compression technique to help an audience effectively understand what is important in a visualisation, communicating key messages combining data, visualisations, and narratives. 'Telling stories' with data in these ways should enable the elicitation of deeper reflections in an effective manner. This thesis tackles the above challenges specifically for professional sectors, whose educational and training scenarios can be challenging because they need to develop theory, procedural knowledge and also learn from bodily experiences. This research progresses in by investigating: \"How can salient aspects of embodied team activity be automatically identified, and derived insights be communicated to support timely, productive reflection?\" Four research questions were derived: (1) What modelling techniques can enable identification of salient aspects of multimodal embodied team activity according to the learning design (i.e., teachers' pedagogical intentions)? (2) How can insights be extracted from multimodal sensors and communicated to students and teachers to support teaching and reflection on embodied team activity? (3) To what extent can students and teachers reflect on embodied team activity using MMLA interfaces? and (4) To what extent can MMLA interfaces for students and teachers be automatically generated? This research makes three types of contribution: modelling, prototypes (MMLA interfaces), and implementation. Results from this research point to the potential of creating alternative ways to communicate multimodal data insights to teachers and students, by combining visualisation, narrative and storytelling, driven by teachers' pedagogical intentions and the learning design.

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing dialogue content has been central to advancing team learning theory and informing the design of computer-supported collaborative learning environments, yet this progress has depended on labour-intensive qualitative coding. LLMs offer new possibilities for automating and enhancing the dialogue layer within emerging multimodal learning analytics approaches, with recent studies showing that they can approximate human coding through few-shot prompting. However, prior work has focused on replicating human coding accuracy for research purposes, rather than addressing a more educationally consequential question: how can we design prompts that allow an LLM to label team dialogue accurately and fast enough to be useful in real settings, such as in-person healthcare simulations, where results must be returned quickly and computational cost and sustainability also matter? This paper investigates how prompt design and batching strategies can be optimised to balance coding accuracy, processing time, and environmental impact in team-based healthcare simulation debriefing. Using a dataset of 11,647 utterances coded across 6 dialogue constructs, we compared 4 prompt designs across varying batch sizes, evaluating coding performance, processing time, and energy consumption, as well as the trade-offs between these metrics. Results indicate that increasing batch size improves speed and reduces energy use, but negatively impacts coding performance. Beyond demonstrating the feasibility of LLM-based qualitative analysis, this study offers practical guidance for scaling dialogue analytics in contexts where timeliness, privacy, and sustainability are critical.

Generative artificial intelligence (GenAI) offers promising potential for advancing human-AI collaboration in qualitative research. However, existing works focused on conventional machine-learning and pattern-based AI systems, and little is known about how researchers interact with GenAI in qualitative research. This work delves into researchers' perceptions of their collaboration with GenAI, specifically ChatGPT. Through a user study involving ten qualitative researchers, we found ChatGPT to be a valuable collaborator for thematic analysis, enhancing coding efficiency, aiding initial data exploration, offering granular quantitative insights, and assisting comprehension for non-native speakers and non-experts. Yet, concerns about its trustworthiness and accuracy, reliability and consistency, limited contextual understanding, and broader acceptance within the research community persist. We contribute five actionable design recommendations to foster effective human-AI collaboration. These include incorporating transparent explanatory mechanisms, enhancing interface and integration capabilities, prioritising contextual understanding and customisation, embedding human-AI feedback loops and iterative functionality, and strengthening trust through validation mechanisms.

Multimodal Learning Analytics (MMLA) innovations make use of rapidly evolving sensing and artificial intelligence algorithms to collect rich data about learning activities that unfold in physical learning spaces. The analysis of these data is opening exciting new avenues for both studying and supporting learning. Yet, practical and logistical challenges commonly appear while deploying MMLA innovations \"in-the-wild\". These can span from technical issues related to enhancing the learning space with sensing capabilities, to the increased complexity of teachers' tasks and informed consent. These practicalities have been rarely discussed. This paper addresses this gap by presenting a set of lessons learnt from a 2-year human-centred MMLA in-the-wild study conducted with 399 students and 17 educators. The lessons learnt were synthesised into topics related to i) technological/physical aspects of the deployment; ii) multimodal data and interfaces; iii) the design process; iv) participation, ethics and privacy; and v) the sustainability of the deployment.

Knowledge Management is crucial for capturing and transferring expertise within universities, especially in high staff turnover contexts where expertise loss disrupts teaching. Documenting teachers' workflows is time-intensive and diverts experts from core responsibilities. Sequential Pattern Mining (SPM) leverages log data to identify expert workflows, offering an automated alternative to represent workflows but requiring transformation into intuitive formats for novice educators. This paper introduces Visual Process Representations (VPR), a design approach combining SPM, Knowledge Management processes, and storytelling techniques to convert expert log data into clear visualisations. We detail the design phases and report a study evaluating visual affordances (text lists vs. pictorial-style) and teachers' perceptions of four versions of the VPR with 160 higher teachers on Prolific. Results indicate improved task performance, usability, and engagement, particularly with enriched visuals, though process memorability and task time improvements were limited. The findings highlight VPR's potential to visualise workflows and support novice educators.

Designing Knowledge Management Systems (KMSs) for higher education requires addressing complex human-technology interactions, especially where staff turnover and changing roles create ongoing challenges for reusing knowledge. While advances in process mining and Generative AI enable new ways of designing features to support knowledge management, existing KMSs often overlook the realities of educators' workflows, leading to low adoption and limited impact. This paper presents findings from a two-year human-centred design study with 108 higher education teachers, focused on the iterative co-design and evaluation of GoldMind, a KMS supporting in-the-flow knowledge management during digital teaching tasks. Through three design-evaluation cycles, we examined how teachers interacted with the system and how their feedback informed successive refinements. Insights are synthesised across three themes: (1) Technology Lessons from user interaction data, (2) Design Considerations shaped by co-design and usability testing, and (3) Human Factors, including cognitive load and knowledge behaviours, analysed using Epistemic Network Analysis.

The objective of this study was to develop and validate a questionnaire, through a Delphi consensus, to be used by allergists in their routine clinical practice to assess the preferences of patients starting allergen immunotherapy (AIT) treatment using an objective approach. A Delphi consensus-driven process was used. The scientific committee, composed of 15 allergists, led the study and participated in the preparation of the questionnaire. Two-hundred panelists from different Spanish regions were invited to complete a 16-item questionnaire on a nine-point Likert scale covering six topic blocks. Consensus was achieved if ≥66.6% of panelists reached agreement or disagreement. Of the 200 experts invited to participate in the Delphi process, a total of 195 (97.5%) answered the questionnaire. The panel experts reached a consensus on \"agreement\" on a total of 12 of the 16 (75.0%) items, covering a total of six categories: (a) patient knowledge (2 questions), (b) barriers to patient adherence (3 questions), (c) patient behavior (4 questions), (d) future actions (3 questions), (e) treatment costs (2 questions), and (f) final patient preferences (2 questions). This Delphi consensus study validated a set of twelve recommended questions for patients objectively assessing their preferences and suitability for the most common AIT options available. The questionnaire intends to assist allergists in making an objective, unconditioned decision regarding the best AIT option for each patient, after informing them about the different routes.

Purpose: The objective of this study was to develop and validate a questionnaire, through a Delphi consensus, to be used by allergists in their routine clinical practice to assess the preferences of patients starting allergen immunotherapy (AIT) treatment using an objective approach. Patients and Methods: A Delphi consensus-driven process was used. The scientific committee, composed of 15 allergists, led the study and participated in the preparation of the questionnaire. Two-hundred panelists from different Spanish regions were invited to complete a 16-item questionnaire on a nine-point Likert scale covering six topic blocks. Consensus was achieved if [greater than or equal to]66.6% of panelists reached agreement or disagreement. Results: Of the 200 experts invited to participate in the Delphi process, a total of 195 (97.5%) answered the questionnaire. The panel experts reached a consensus on \"agreement\" on a total of 12 of the 16 (75.0%) items, covering a total of six categories: (a) patient knowledge (2 questions), (b) barriers to patient adherence (3 questions), (c) patient behavior (4 questions), (d) future actions (3 questions), (e) treatment costs (2 questions), and (f) final patient preferences (2 questions). Conclusion: This Delphi consensus study validated a set of twelve recommended questions for patients objectively assessing their preferences and suitability for the most common AIT options available. The questionnaire intends to assist allergists in making an objective, unconditioned decision regarding the best AIT option for each patient, after informing them about the different routes. Keywords: allergen immunotherapy, Delphi consensus, shared decision-making, questionnaire