Pre-conference Schedule

Learning analytics offers tremendous potential to improve educational outcomes, but new measures and metrics often remain isolated within institutions or companies. This half-day workshop at the 2024 Learning Analytics and Knowledge Conference aims to collaboratively advance the development and dissemination of innovative analytic measures in education. Submissions of new and innovative metrics will be compiled on a website and presented at the event. Through mini-presentations, structured discussions, and breakout sessions, participants will exchange insights about creating, validating, and distributing novel metrics. The workshop will conclude by voting on the most promising measure and awarding a prize. By synthesizing diverse viewpoints, the workshop intends to catalyze the evolution and adoption of impactful new techniques in learning analytics. Outcomes will be shared through a public website, potential publications, and continued online community dialogue. This interactive workshop provides an exciting opportunity to collectively spur progress in developing the next generation of learning metrics. Organizers: Charles Lang, Geraldine Gray, Christopher Brooks Yoav Bergner Website: https://charles-lang.github.io/measures-metrics-LAK24/

The increasing complexity and potential for disruption of recent artificial intelligence (AI) advances (including their applications to education, like learning analytics – LA) make the issue of aligning those technologies with human stakeholders’ goals and values more relevant than ever. Further, the global reach of many of these educational applications puts into question whether LA designed for one setting and its local culture can be unproblematically transferred to another culture/setting. The fields of cross-cultural psychology and human-computer interaction have developed frameworks and methods to explicitly and systematically look at such problems of value alignment in the design of technology (e.g., under the label “value-sensitive design”), but there are still few examples of applying them in the LA domain. In the present workshop, participants will learn about and apply different value-sensitive design methods and value frameworks, to the design (or re- design) of specific LA innovations proposed by the facilitators and participants themselves. Organizers: Ioana Jivet, Olga Viberg, María Jesús Rodríguez-Triana, Luis Pablo Prieto, Bodong Chen, Maren Scheffel Website: https://sites.google.com/view/carla-workshop

The resurgence of interest in social network analysis (SNA) in educational contexts, spurred on by the proliferation of social networking sites and the integration of digital resources in education, is the focal point of this one-day course. Aimed at education researchers unfamiliar with SNA, the course offers an immersion into social network theory, showcases diverse applications of network analysis in educational settings, and affords hands-on experience with analyzing actual data sets. By weaving theoretical instruction with applied experiences, the course seeks to foster a deep-seated understanding of SNA’s dual role as a theoretical lens and a method of analysis, enabling scholars to harness its potential in understanding and enhancing learning environments and outcomes. This endeavor champions the belief that SNA can be a powerful tool in the continuous effort to improve student learning and the atmospheres in which this learning takes place

Organizers:

Shaun Kellogg, Jeanne McClure, Shiyan Jiang, Susan Hibbard and Doreen Mushi

Website:

https://laser-institute.github.io/LAK24-kyoto-SNA/

The 9th Annual DesignLAK workshop (DesignLAK24) will build on the outcomes of the 2023 workshop to explore how a map of key elements derived from research in the field on Learning Design (LD) and Learning Analytics (LA) can help operationalise the LD/LA connection for research and practice. Over the past year, the team have taken on board feedback received through previous workshops and further analysed the literature to update and refine the map. The workshop will be delivered as a half-day, face-to-face event and enable participants to apply the LDLA Map to authentic LDLA projects, receive feedback, and build collaboration networks. Participants will be asked to bring a project idea to the workshop and work in groups to apply the map to their individual projects. Throughout the activities, participants will discuss challenges and provide feedback on the map's utility. The workshop will close with a group reflection on next steps for their projects, and further recommendations for future development and dissemination of the LDLA Map. The expected outcomes include exposure to the LDLA Map for current and future use, new collaborations, and a series of case reports on the application of the map in different scenarios of LDLA connection.

Organizers:

Linda Corrin, Nancy Law, Daisy Chen, Aneesha Bakharia and Xiao Hu

Website: https://sites.google.com/view/designlak24

As the adoption of digital learning materials in modern education systems is increasing, the analysis of reading behavior and their effect on student performance gains attention. The main motivation of this workshop is to foster research into the analysis of students’ interaction with digital textbooks, and find new ways in which it can be used to inform and provide meaningful feedback to stakeholders: teachers, students and researchers. The previous years workshops at LAK19 and LAK20 focused on reading behavior in higher education, and LAK21, LAK22 and LAK23 on secondary school reading behavior and pre/post COVID-19 pandemic changes. Participants of this year’s workshop will be given the opportunity to analyze several different datasets, including secondary school prediction of academic performance for more than one subject. As with previous years, additional information on lecture schedules and syllabus will also enable the analysis of learning context for further insights into the preview, in-class, and review reading strategies that learners employ. In addition, this workshop will accept a wide range of reaserch topics on learning analytics, educational technology, and learning support systems in the post COVID-19 era, including applications of AI in education, proposals for new educational systems, new evaluation methods, and so on.

Organizers:

Brendan Flanagan, Atsushi Shimada, Fumiya Okubo and Hiroaki Ogata, Hsiao-Ting Tseng, Albert C.M. Yang, Owen H.T. Lu

Website:

https://sites.google.com/view/lak24datachallenge

Last year's LAK conference featured a workshop dedicated to introducing an innovative concept of learning design (LD) and the utilization of a complimentary software tool for creating and analyzing LD. This year's workshop will turn its focus towards the evolving challenges intertwined with AI's role in LD. Participation in last year's workshop is not a prerequisite for this year's session. The objectives for this year's workshop are twofold: To provide a platform for exchanging experiences, showcasing research findings, and deliberating on the challenges that lie at the intersection of learning analytics (LA) and LD. This encompasses the ethical and impactful integration of AI in the educational paradigm. To introduce attendees to an innovative, free LD tool (learning-design.eu) and its capabilities. Attendees will be immersed in exploring advanced LD analytics using this tool. Participants are invited to collaboratively refine the LD of their courses, programs, or quality assurance endeavours while examining the LA data generated by the tool. This interactive session will empower participants to enhance their courses further, understand the role of design analytics in quality assurance, and harness the potential of AI-driven LD. This half-day, in-person workshop is a collaborative effort by three universities from Europe and Australia.

Organizers:

Blazenka Divjak, Barbi Svetec, Dragan Gašević, Mladen Raković and Bart Rienties

Website:

https://learning-design.eu/en/lak-2024

This submission is for a half-day workshop. There is a growing call for ethical and equitable learning analytics (LA), from educators, designers, researchers and policy makers. Numerous frameworks and tool-based strategies have been produced for education. However, there has been limited focus on how these frameworks, tools and resources are identified, adopted and employed by those developing and implementing LA; the extent to which they find them valuable and meaningful in translating them into practice; the extent to which such frameworks and tools are effective in varied contexts and situations; what other kinds of resources are needed; and how the experiences of those doing this ‘knowledge translation’ are captured and disseminated in ways that can support the further development of responsible LA. This interactive workshop aims to address some of these challenges, through a combination of small group breakout sessions, guided discussion and the sharing of practice across the LA community. Organizers: Rebecca Eynon, Olga Viberg, Simon Knight and Alyssa Wise Website: https://edtech.oii.ox.ac.uk/workshops/fostering-ethical-and-equitable-learning-analytics/

In this current era where digital access to knowledge is cheap and user attention is expensive, a number of online applications have been developed for learning. These platforms collect a massive amount of data over various profiles, that can be used to improve learning experience: intelligent tutoring systems can infer what activities worked for different types of students in the past, and apply this knowledge to instruct new students. In order to learn effectively and efficiently, the experience should be adaptive: the sequence of activities should be tailored to the abilities and needs of each learner, in order to keep them stimulated and avoid boredom, confusion and dropout. In the context of reinforcement learning, we want to learn a policy to administer exercises or resources to individual students. Educational research communities have proposed models that predict mistakes and dropout, in order to detect students that need further instruction. Such models are usually calibrated on data collected in an offline scenario, and may not generalize well to new students. There is now a need to design online systems that continuously learn as data flows, and self-assess their strategies when interacting with new learners. These models have been already deployed in online commercial applications (ex. streaming, advertising, social networks) for optimizing interaction, click-through-rate, or profit. Can we use similar methods to enhance the performance of teaching in order to promote lifetime success? When optimizing human learning, which metrics should be optimized? Learner progress? Learner retention? User addiction? The diversity or coverage of the proposed activities? What are the issues inherent to adapting the learning process in online settings, in terms of privacy, fairness (disparate impact, inadvertent discrimination), and robustness to adversaries trying to game the system? Student modeling for optimizing human learning is a rich and complex task that gathers methods from machine learning, cognitive science, educational data mining and psychometrics. This workshop welcomes researchers and practitioners in the following topics (this list is not exhaustive):

• abstract representations of learning
• additive/conjunctive factor models
• adversarial learning
• causal models
• cognitive diagnostic models
• deep generative models such as deep knowledge tracing
• item response theory
• models of learning and forgetting (spaced repetition)
• multi-armed bandits
• multi-task learning
• reinforcement learning

Organizers:

Samuel Girard, Inria, France

Hisashi Kashima, Kyoto University, Japan

Fabrice Popineau, CentraleSupélec & LRI, France

Jill-Jênn Vie, Inria, France

Yong Zheng, Illinois Institute of Technology, USA

Website:

https://jilljenn.github.io/humanlearn/

The first three editions of the Workshop on Learning Analytics and Assessment were successfully organized at LAK21-23 conferences, resulting in multiple post-workshop collaborations and a special issue in a journal. In this workshop, we intend to address some of the key open challenges in learning analytics that are related to use of learning analytics in formative and summative assessment; measurement of learning progression; reliability and validity of data collection and analysis; and assurance of assessment trustworthiness, in particular given the emergence of the generative artificial intelligence (AI) methods. An open call for contributions will be distributed to solicit brief descriptions of current research and practice projects for roundtable-style discussions with workshop participants. Expected outcomes are the further formation of a community of practice and possible follow-up publications and special issues in journals.

Organizers:

Dragan Gasevic, Mladen Rakovic, Blazenka Divjak, Yoon Jeon Kim, Naif Aljohani and Abhinava Barthakur

Website:

https://sites.google.com/monash.edu/lakassess23/about

Our international, multidisciplinary research Centre X organises this interactive workshop on how to use multiple data streams to measure and support students’ self- regulated learning (SRL) through human-AI collaboration. Prior research has shown that supporting SRL through learning analytics (LA) fosters life-long learning skills. However, there are still major challenges for the LA community conducting research in this area: i) identifying useful data streams to measure different SRL processes in an unobtrusive, valid, and reliable manner; and ii) supporting SRL with LA backed interventions. Therefore, this full-day workshop facilitates a program of research integrating different types of SRL trace data into LA-based supports by i) presenting empirical and theoretical studies; ii) initiating multidisciplinary dialogue (e.g., computer science, learning sciences) to foster cross-team collaborations and promote transdisciplinary perspectives on human-AI collaborations for SRL; and iii) providing workshop participants with hands-on opportunities to collect multi-trace data and investigate different personalized support types (e.g. dashboard, scaffolding, NLP generated prompts) based on human-AI collaboration. Expected outcomes are forming a community of research and practice within the field LA; identifying potential areas for collaborative projects; and promoting future collaborations for joint publications and grant submissions.

Organizers:

Joni Lämsä, Susanne de Mooij, Daryn Dever, Lyn Lim, Mladen Rakovic, Megan Wiedbusch, Roger Azevedo, Maria Bannert, Dragan Gasevic, Inge Molenaar and Sanna Järvelä

 

Website:

https://sites.google.com/edu.oulu.fi/cellalak24

This full day event is for those students selected to the LAK24 Doctoral Consortium. 

 

Generative artificial intelligence (GenAI) presents a transformative opportunity to advance the field of learning analytics (LA). Its capabilities extend from automating the analysis of unstructured data and crafting adaptive educational resources to enhancing the presentation of LA outcomes through rich narratives and detailed explanations. This first GenAI-LA workshop is conceived as a catalyst for dialogue and partnership, spotlighting the potential of GenAI in LA. By assembling a diverse group of learning scientists, LA practitioners, software engineers, and AI specialists, we aim to foster a comprehensive exploration and envisioning of GenAI's pivotal role in advancing LA research and practices.

Organizers:

Lixiang Yan, Andy Nguyen, Lele Sha, Jionghao Lin, Mutlu Cukurova, Kshitij Sharma, Roberto Martinez-Maldonado, Linxuan Zhao, Yuheng Li and Dragan Gasevic

Website:

https://sites.google.com/monash.edu/genai-la-workshop-lak24

The successful application of Learning Analytics (LA) can improve student learning outcomes, student support and teaching. The key-challenges for LA adoption (i.e., Ethics, Leadership, Analytics culture, Analytics capabilities, Stakeholder involvement, and Technology) have been investigated. However, large-scale adoption remains lacking as does research into it. This half-day workshop organized in cooperation of several European universities has the aim to provide support to researchers and practitioners for realizing large scale adoption of practicable LA within higher education and the essential research thereon. Research and insights from the varied European contexts will be presented in this workshop for comparison with researchers from other non-European and other European contexts. The idea is that this exchange will provide insights to learn from the differences and overcome global challenges for successful adoption of LA at scale.

Organizers:

Ludo W. van Meeuwen, Bart Rienties, Hendrik Drachsler, Olga Viberg, Rianne Conijn, Caroline Vonk, Jan Willem Brijan and Marcus Specht

Website:

https://sites.google.com/view/lak24adoptionworkshop/home

Organizers:

Lukas Menzel, Ioana Jivet, Sebastian Gombert, Hendrik Drachsler, Tornike Giorgashvili and Marcel Schmitz

Website:

https://hila.edutec.science/

The pursuit of actionability in learning analytics has long been a central aim, yet the knowledge base related to improving it has remained relatively sparse and disconnected. This workshop aims to initiate unifying discussions on how “actionability” can be conceptualized for the learning analytics community. During the workshop, we will define and refine actionability from various stakeholder perspectives: technical (for tech developers), design (for designers), self-regulated learning (for learners), and classroom orchestration (for teachers); and then explore how these perspectives can be used to inform the development of analytics tools, learning designs, and impact measurement. Through diverse discussions and consolidation efforts, this workshop seeks to develop a comprehensive framework with tangible implications and foster a network of interested researchers and practitioners in actionable learning analytics

Organizers:

Yeonji Jung, Alyssa Wise, Yannis Dimitriadis, yannis@tel.uva.es, Ishari Amarasinghe

Website:

https://sites.google.com/view/actionablela-lak24/

Data Storytelling (DS) in Learning Analytics (LA) has proven as an effective approach to communicating insights to non-data experts (e.g., students and teachers). DS brings the promise to incorporate narratives into LA interfaces (e.g., dashboards) to facilitate the provision of direct feedback and pedagogical explanations. The LA community has researched Data Storytelling principles and techniques to support educational stakeholders in interpreting their teaching and learning progress. However, given the relevance of the story narrative, challenges arise to provide unbiased, fair, and meaningful stories without misleading the communication of insights. This workshop aims to explore the formal and practical challenges and opportunities of DS by engaging in discussions with the LA community. In this workshop, we expect to spark discussion on these main topics: What methods and methodologies of DS from other domains are suitable for LA? How to evaluate the impact of DS in LA? How can we automate the process of generating fair and unbiased data stories to facilitate sense-making and effectively communicate insights? This workshop will bring together storytelling researchers and practitioners, whose data storytelling in LA is a special case, to clarify and converge on the future of DS in LA related to their challenges and opportunities.

Organizers:

Gloria Milena Fernandez-Nieto, Vanessa Echeverria, Roberto Martinez-Maldonado, Yi-shan Tsai, Lu Lawrence, Shaveen Singh, Stanislav Pozdniakov, Lujie Karen Chen, Jiaqi Gong and Louise Yarnall

Website:

https://datastorytelling-education.github.io/

This workshop proposal explores how learning analytics can reconcile deficit- and asset-based approaches. Deficit-based models, which focus on identifying and remedying learner shortcomings, have been effective but may neglect students' existing strengths. Conversely, asset-based approaches emphasize recognizing learners' identities as assets to their learning. We advocate for a combination of both. We ground our discussion in the data feminism framework, which scrutinizes power structures in data design and interpretation. We will delve into three core data feminism principles: examine power, challenge power, and rethink binaries and hierarchies, to construct narratives affirming students' diverse identities. Through presentations, discussions, and interactive activities, we aim to develop a set of questions that allow researchers to reflect on their data and create cohesive narratives aligning asset and deficit perspectives.

Organizers:

Angela Stewart, Stephen Hutt and Caitlin Mills

Website:

https://sites.google.com/view/lak-2024-asset-based-workshop/

The purpose of this interactive workshop is to provide a hands-on introduction to curriculum developed as part of the Anonymized Institute, a professional development program for early and mid-career researchers funded by the National Science Foundation (ECR: BCSER). The intended audience for this workshop includes early-career and experienced scholars seeking who currently teach, or have a desire to teach, learning analytics methodologies. The primary aim of this workshop is to support participants interested in incorporating LASER curriculum materials into webinars, workshops, courses or programs at their home institution. Participants in this workshop will learn about the design and structure of the 25+ learning modules covering a range of topics and techniques like machine learning, network analysis, and text mining. Participants will also gain hands-on experience with instructional activities such as conceptual overviews, interactive code-alongs, tutorials, case studies using Python and R, essential readings and discussion activities, and badging and microcredential opportunities. Finally, participants will learn pedagogical tips and information on the computing infrastructure, technology stack, and logistics required for leveraging these materials for their own undergraduate, graduate or professional learning programs

Organizers:

Shaun Kellogg, Jeanne McClure, Shiyan Jiang, Susan Hibbard, Doreen Mushi and Ryan Baker

Website:

https://laser-institute.github.io/lak24-kyoto/laser-workshop.html

The workshop aims to establish first conversations and bring together researchers and practitioners working on topics on the intersection of learning analytics (LA) and (immersive) virtual reality (VR) in educational settings. Overall, it aims to advance research on the potential and challenges of rich sensory data generated from VR for learning purposes. Ultimately, we strive to better understand how LA can improve the future design of educational VR applications. Therefore, we call for contributions on the role of LA in foundational research about the VR infrastructure and its multimodal analytics; VR for asynchronous learning experiences; and VR for synchronous teaching in the metaverse.

Organizers:

Martin Hlosta, Ivan Moser, Amir Winer, Nitza Geri, Umesh Ramnarain and Christo Van der Westhuizen

Website:

https://hlostam.github.io/lavr-lak24/