Nonverbal communication is essential for effective oral presentations, shaping audience engagement and conveying confidence beyond spoken words. Multimodal Learning Analytics (MmLA) research has advanced the automatic detection of presenters’ behaviors—such as posture, gestures, and eye contact—but continues to explore how to provide actionable feedback that fosters reflection and skill development. Recent advances in Generative Artificial Intelligence (GenAI) offer new opportunities to automate the analysis of nonverbal cues and generate narrative evaluations that go beyond raw metrics. This study investigates the integration of a Learning Analytics Dashboard (LAD) with a Large Language Model (LLM) to deliver both numerical and narrative feedback across five dimensions of nonverbal communication: body posture, eye contact, hand gestures, facial expression, and use of space. Twenty-two undergraduate students participated in the study, receiving numerical feedback through a LAD and narrative feedback from either a human expert or an LLM. Findings revealed no significant differences in students’ perceptions of human- and LLM-generated feedback, while also highlighting the potential of LLM-based feedback to support reflection despite certain technical limitations. These results suggest that LLMs can meaningfully enhance learning analytics dashboards by delivering actionable, human-like feedback that supports the development of nonverbal communication skills.

Recent literature in automated creativity measurement explores the use of large language models to measure creative tasks at scale, for example using text-based large language models to score text-based brainstorming activities or neural nets to rate images from a creative drawing task. Prior research has shown that educators of all levels want to gauge and support students' ability to be creative, but are often limited due to the time-consuming nature of existing creativity measurements, as well as a disconnect between validated instruments and class-based activities. This paper expands creativity measurement in several important ways. We leverage state-of-the-art multimodal large language models (MLLMs), trained on text, image, and other data, to not only model creativity tasks in a unitask approach (one model per task), but also in a multitask approach (one model for several tasks). We connect multimodal large language models to benchmarks established in psychological creativity research, and demonstrate that some MLLMs (notably native multimodal Llama 3.2 and Qwen 3-VL models) surpass the best scoring measurements by up to 5%, while other MLLMs (notably Llama 4-109B) need additional training procedures to accommodate limited fine-tuning data. We offer evidence of the ability of MLLMs to measure creativity based on human ratings, and explore future opportunities to advance multimodal creativity assessment within complex, real-world learning environments.

This case study examines an interactive, low barrier process, termed instructor-in-the-loop, by which an instructor defines and makes meaning from exploratory metrics and visualizations, and uses this multimodal information to improve a course iteratively. We present potentials for course improvement based on automated learning analytics insights related to students’ participation in small active learning sessions associated with a large lecture course. Automated analytics processes are essential for larger courses where engaging smaller groups is important to ensure participation and understanding, but monitoring a large total number of groups throughout an instructional experience becomes untenable for the instructor. Of interest is providing instructors with easy-to-digest summaries of group performance that do not require complex set up and knowledge of more advanced algorithmic approaches. We explore synthesizing metrics and visualizations as ways to engage instructors in meaning making of complex learning environments, but in a low barrier manner that provides insights quickly.

Collaborative Learning Analytics (CLA) tools have recently emerged as a potential solution to address the onerous process of monitoring and providing timely feedback on collaboration skills in higher education students. However, prior studies on the efficacy of such tools have mainly been carried out in small, controlled settings. This study aims to measure the impact of a specific CLA tool that can be easily deployed on a larger scale with minimal instructor effort in real-world online group work activities. Additionally, this research examines the potential influence that the characteristics of the collaborative activity may have on the tool's effectiveness. The CLA tool under investigation displays speaking participation time and peer evaluation scores from students engaged in online collaborative activities as part of their regular courses. The tool was evaluated with five instructors and 156 students over the course of one semester. The effects of the tool on students' speaking participation and peer evaluation scores were quantitatively measured and tested. A qualitative analysis of reflections from both students and instructors provided supplementary information on the quantitative results. The main finding of this study indicates that the tool has an overall small positive impact. The effectiveness of the CLA tool is primarily modulated by the synchronous or asynchronous presence of the instructor, as students tend to interact more naturally and feel less scrutinized in the absence of instructor evaluation. Based on the discussion of the findings, this research suggests design insights to enhance future CLA tools at scale for the purpose of supporting the development of online collaboration skills.

This paper proposes an overarching framework for automated collaboration feedback that bridges theory and tool as well as technology and pedagogy. This pragmatic and theory-driven framework guides our thinking by outlining the components involved in converting theoretical collaboration constructs into features that can be automatically extracted and then converted into actionable feedback. Focusing on the pedagogical components of the framework, the constructs are validated by mapping them onto a selection of multi-disciplinary collaboration frameworks. The resulting behavioral indicators are then applied to measure collaboration in a sample scenario and those measurements are then used to exemplify how feedback analytics could be calculated. The paper concludes with a discussion on how those analytics could be converted into feedback for students and the next steps needed to advance the technological part of the framework.

Providing formative feedback to foster collaboration and improve students’ practice has been an emerging topic in CSCL and LA research communities. However, this pedagogical practice could be unrealistic in authentic classrooms, as observing and annotating improvements for every student and group exceeds the teacher’s capabilities. In the research area of group work and collaborative learning, current learning analytics solutions have reported accurate computational models to understand collaboration processes, yet evaluating formative collaboration feedback, where the final user is the student, is an under-explored research area. This paper reports an exploratory evaluation to understand the effects a collaboration feedback report through an authentic study conducted in regular classes. Fifty students from a Computer Science undergraduate program participated in the study. We followed an user-centered design approach to define six collaboration aspects that are relevant to students. These aspects were part of initial prototypes for the feedback report. From the exploratory intervention, we did not find effects between students who received the feedback (experimental condition) report and those who did not (control condition). Finally, this paper discusses design implications for further feedback report designs and interventions.

This study aims to identify the conceptual structure and the thematic progress in Learning Analytics (evolution) and to elaborate on backbone/emerging topics in the field (maturity) from 2011 to September 2019. To address this objective, this paper employs hierarchical clustering, strategic diagrams and network analysis to construct the intellectual map of the Learning Analytics community and to visualize the thematic landscape in this field, using co-word analysis. Overall, a total of 459 papers from the proceedings of the Learning Analytics and Knowledge (LAK) conference and 168 articles published in the Journal of Learning Analytics (JLA), and the respective 3092 author-assigned keywords and 4051 machine-extracted key-phrases, were included in the analyses. The results indicate that the community has significantly focused in areas like Massive Open Online Courses and visualizations; Learning Management Systems, assessment and self-regulated learning are also basic topics, yet topics like natural language processing and orchestration are emerging. The analysis highlights the shift of the research interest throughout the past decade, and the rise of new topics, comprising evidence that the field is expanding. Limitations of the approach and future work plans conclude the paper.

Learning analytics dashboards are at the core of the LAK vision to involve the human into the decision-making process. The key focus of these dashboards is to support better human sense-making and decision-making by visualising data about learners to a variety of stakeholders. Early research on learning analytics dashboards focused on the use of visualisation and prediction techniques and demonstrates the rich potential of dashboards in a variety of learning settings. Present research increasingly uses participatory design methods to tailor dashboards to the needs of stakeholders, employs multimodal data acquisition techniques, and starts to research theoretical underpinnings of dashboards. In this paper, we present these past and present research efforts as well as the results of the VISLA19 workshop on "Visual approaches to Learning Analytics" that was held at LAK19 with experts in the domain to identify and articulate common practices and challenges for the domain. Based on an analysis of the results, we present a research agenda to help shape the future of learning analytics dashboards.

Several Learning Analytics applications are limited by the cost of generating a computer understandable description of the course domain, what is called an Intelligent Curriculum. The following work contributes a novel approach to (semi-)automatically generate Intelligent Curriculum through ontologies extracted from existing learning materials such as digital books or web content. Through a series of natural language processing steps, the semi-structured information present in existing content is transformed into a concept-graph. This work also evaluates the proposed methodology by applying it to learning content for two different courses and measuring the quality of the extracted ontologies against manually generated ones. The results obtained suggest that the technique can be readily used to provide domain information to other Learning Analytics tools.

The present work describes the challenges faced during the development of a countrywide Learning Analytics tool focused on tracking the trajectories of Uruguayan students during their first three years of secondary education. Due to the large-scale of the project, which covers an entire national educational system, several challenges and constraints (both technical and legal) were faced during its conception and development. This paper presents the design decisions and solutions found to address or mitigate the problems found, with the current state of the project. Early results point out the feasibility of finding meaningful patterns in the available data (using data mining techniques) which can be embedded into a prototype for tracking the students scholar trajectory.

The abilities of Augmented Reality to overlay learning materials with contextual dynamic information and of software simulations to allow rapid and safe exploration of complex engineering concepts have already been established as beneficial in education. Access to both technologies in the classroom has been rather limited due to costs and hardware requirements. With the intention to bring these two technologies closer to engineering students, we created Virtual Circuits: a low-cost simulator app of electrical circuits designed for the classroom and autonomous study. Virtual Circuits requires only a smart-phone and a set of plastic tokens and, with the help of Augmented Reality and a simulation engine, it allows electrical engineering students to quickly explore complex concepts in their field. In this article we present the Virtual Circuits app and the results of our first field test in a real electrical engineering classroom at our university. The collected feedback from students was overwhelmingly positive hinting at tangible educational benefits and improvements in future versions of our app.

Developing communication skills in higher education students could be a challenge to professors due to the time needed to provide formative feedback. This work presents RAP, a scalable system to provide automatic feedback to entry-level students to develop basic oral presentation skills. The system improves the state-of-the-art by analyzing posture, gaze, volume, filled pauses and the slides of the presenters through data captured by very low-cost sensors. The system also provides an off-line feedback report with multimodal recordings of their performance. An initial evaluation of the system indicates that the system's feedback highly agrees with human feedback and that students considered that feedback useful to develop their oral presentation skills.

Multimodal Learning Analytics (MMLA) captures, integrates and analyzes learning traces from different sources in order to obtain a more holistic understanding of the learning process, wherever it happens. MMLA leverages the increasingly widespread availability of diverse sensors, high-frequency data collection technologies and sophisticated machine learning and artificial intelligence techniques. The aim of this workshop is twofold: first, to expose participants to, and develop, different multimodal datasets that reflect how MMLA can bring new insights and opportunities to investigate complex learning processes and environments; second, to collaboratively identify a set of grand challenges for further MMLA research, built upon the foundations of previous workshops on the topic.

This workshop on Learning Analytics for Curriculum and Program Quality Improvement investigates how LAK can drive improvements in teaching practices, instructional and curricular design, and academic program delivery. This workshop brings forward research and examples of how LAK can help build the case for instructional, curricular, or programmatic change and further how LAK can be used to foster acceptance of change processes by teachers, administrators, and other stakeholders in the educational enterprise.

This is a proposal for organizing a Multimodal Learning Analytics (MLA) data challenge as part of the workshop offering of the Learning Analytics and Knowledge (LAK) conference. It explains the motivation of the event, its objectives, target groups, expected format, organization, dissemination strategy and schedule.

The traditional recording of student interaction in classrooms has raised privacy concerns in both students and academics. However, the same students are happy to share their daily lives through social media. Perception of data ownership is the key factor in this paradox. This article proposes the design of a personal Multimodal Recording Device (MRD) that could capture the actions of its owner during lectures. The MRD would be able to capture close-range video, audio, writing, and other environmental signals. Differently from traditional centralized recording systems, students would have control over their own recorded data. They could decide to share their information in exchange of access to the recordings of the instructor, notes form their classmates, and analysis of, for example, their attention performance. By sharing their data, students participate in the co-creation of enhanced and synchronized course notes that will benefit all the participating students. This work presents details about how such a device could be build from available components. This work also discusses and evaluates the design of such device, including its foreseeable costs, scalability, flexibility, intrusiveness and recording quality.

Multimodality is an integral part of teaching and learning. Over the past few decades researchers have been designing, creating and analyzing novel environments that enable students to experience and demonstrate learning through a variety of modalities. The recent availability of low cost multimodal sensors, advances in artificial intelligence and improved techniques for large scale data analysis have enabled researchers and practitioners to push the boundaries on multimodal learning and multimodal learning analytics. In an effort to continue these developments, the 2015 Multimodal Learning and Analytics Grand Challenge includes a combined focus on new techniques to capture multimodal learning data, as well as the development of rich, multimodal learning applications.

In this paper, we briefly describe the goal and activities of the LAK15 workshop on Visual Aspects of Learning analytics.

This paper summarizes the third Multimodal Learning Analytics Workshop and Grand Challenges (MLA'14). This subfield of Learning Analytics focuses on the interpretation of the multimodal interactions that occurs in learning environments, both digital and physical. This is a hybrid event that includes presentations about methods and techniques to analyze and merge the different signals captured from these environments (workshop session) and more concrete results from the application of Multimodal Learning Analytics techniques to predict the performance of students while solving math problems or presenting in the classroom (challenges sessions). A total of eight articles will be presented in this event. The main conclusion from this event is that Multimodal Learning Analytics is a desirable research endeavour that could produce results that can be currently applied to improve the learning process.

One of the key promises of Learning Analytics research is to create tools that could help educational institutions to gain a better insight of the inner workings of their programs, in order to tune or correct them. This work presents a set of simple techniques that applied to readily available historical academic data could provide such insights. The techniques described are real course difficulty estimation, dependance estimation, curriculum coherence, dropout paths and load/performance graph. The description of these techniques is accompanied by its application to real academic data from a Computer Science program. The results of the analysis are used to obtain recommendations for curriculum re-design.

Multimodal Learning Analytics is a field that studies how to process learning data from dissimilar sources in order to automatically find useful information to give feedback to the learning process. This work processes video, audio and pen strokes information included in the Math Data Corpus, a set of multimodal resources provided to the participants of the Second International Workshop on Multimodal Learning Analytics. The result of this processing is a set of simple features that could discriminate between experts and non-experts in groups of students solving mathematical problems. The main finding is that several of those simple features, namely the percentage of time that the students use the calculator, the speed at which the student writes or draws and the percentage of time that the student mentions numbers or mathematical terms, are good discriminators be- tween experts and non-experts students. Precision levels of 63% are obtained for individual problems and up to 80% when full sessions (aggregation of 16 problems) are analyzed. While the results are specific for the recorded settings, the methodology used to obtain and analyze the features could be used to create discriminations models for other contexts.

A large number of curated digital collections containing learning resources of a various kind has emerged in the last year. These include referatories containing descriptions for resources in the Web (as MERLOT), aggregated collections (as Organic.Edunet), concrete initiatives as Khan Academy, repositories hosting and versioning modular content (as Connexions) and meta-aggregators (as Globe and Learning Registry). Also, OpenCourseware and other OER initiatives have contributed to making this ecosystem of resources richer. Very interesting insights can be extracted when studying the usage and social data that are produced within the learning collections, repositories and federations. At the same time, concerns for the quality and sustainability of these collections have been raised, which has lead to research on quality measurement and metrics. The Workshop attempts to bring studies and demonstrations for any kind of analysis done on learning resource collections, from an interdisciplinary perspective. We consider digital collections not as merely IT deployments but as social systems with contributors, owners, evaluators and users forming patterns of interactions on top of portals or through search systems embedded in other learning technology components. This is in coherence of considering these social systems under a Web Science approach (http://webscience.org/).

The field of Technology Enhanced Learning (TEL) in general, has the potential to solve one of the most important challenges of our time: enable everyone to learn anything, anytime, anywhere. However, if we look back at more than 50 years of research in TEL, it is not clear where we are in terms of reaching our goal and whether we are, indeed, moving forward. The pace at which technology and new ideas evolve have created a rapid, even exponential, rate of change. This rapid change, together with the natural difficulty to measure the impact of technology in something as complex as learning, has lead to a field with abundance of new, good ideas and scarcity of evaluation studies. This lack of evaluation has resulted into the duplication of efforts and a sense of no "ground truth" or "basic theory' of TEL. This article is an attempt to stop, look back and measure, if not the impact, at least the status of a small fraction of TEL, Learning Object Technologies, in the real world. The measured apparent inexistence of the reuse paradox, the two phase linear growth of repositories or the ineffective metadata quality assessment of humans are clear reminders that even bright theoretical discussions do not compensate the lack of experimentation and measurement. Both theoretical and empirical studies should go hand in hand in order to advance the status of the field. This article is an invitation to other researchers in the field to apply Informetric techniques to measure, understand and apply in their tools the vast amount of information generated by the usage of Technology Enhanced Learning systems.

Qualifying a subscriber loop for xDSL transmission can be done in many ways. Amongst all ways, methods that don't require an expensive truck-roll to the customer are preferred. In this paper we provide a method for an intelligent automated interpretation of reflectometric 1-port measurements at the central office. First, we focus on how reflectograms can be characterised. Next, we build up intelligence in the system to deal with the uncertainty on the characteristics and to infer the topology by means of a belief network. Eventually, we combine in an artificial intelligent way, by means of a rule-based expert system all available knowledge and derive the basic loop properties i.e. the topology and the delays of the individual line sections.