Pre-conference Schedule

Interactive Workshop Session

Actionable Learning Analytics requires causal claims; to take well-informed action implies we have an understanding of the causal effect of that action. Causal claims that are made in the field of Learning Analytics (LA) are most commonly made in an experimental framework, such as a randomised control trial (RCT), but RCTs are not always feasible, ethical or practical. Without an RCT we need other ways to build trustworthy LA systems from observational data. Graphical causal models can be used to make causal inferences from observational data, but they require some principled scientific reasoning. This half-day hands-on workshop will introduce you to drawing such graphical causal models, using them to think about the causal assumptions underlying your LA system, and utilising the causal structure to identify and minimise potential bias in order to make stronger scientific claims.

Organizers:

Ben Hicks, Charles Sturt University
Joshua Weidlich, DIPF - Leibniz Institute for Research and Information in Education

Website:

https://benwhicks.github.io/LAK23-causal-modelling/

Interactive Workshop Session

The first two editions of the Workshop on Learning Analytics and Assessment were successfully organized at LAK21 and LAK22 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. 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 formation of a community of practice and possible follow-up publications.

Organizers:

Dragan Gasevic, Monash University
Mladen Rakovic, Monash University
Naif Aljohani, King Abudlaziz University
José A. Ruipérez Valiente, University of Murcia
Sandra Milligan, University of Melbourne
Blazenka Divjak, University of Zagreb

Website:

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

Mini-track/Symposium with tutorial

Analytics applied to the student record, although limited for describing individual student learning and experiences, are effective in revealing institutional systemic inequities at different levels and in different spaces. In this session we will discuss and share analytical tools developed by students, faculty, and staff engaged in the (working group de-identified for review) of the (collaboration de-identified for review). We have been engaged in establishing metrics for measuring equity and inclusion in foundational STEM courses, conducting the measurements, and identifying actionable data to promote change. In the course of this path of discovery, the group established theoretically informed guidelines for framing, analyzing, and interpreting quantitative data in support of equity goals in STEM. Building on this understanding, we have focused analyses on institutional structural inequities at different scales, revealing inequities in the students’ experience in their first STEM course, at the curriculum level, and at the course level. The goal of this Mini-Symposium and Tutorial is to provide participants with these theoretical and practical tools first by presenting the methods and results of the studies, and then by providing hands-on training, ultimately empowering participants to apply these analyses to their own institutions’ data.

Organizers:

Stefano Fiorini, Indiana University
Rebecca Matz, University of Michigan
Meagan Pearson, University of Michigan
Sarah Castle, Michigan State University
Angel Sylvester, University of Minnesota
Kameryn Denaro, University of California Irvine
Victoria Farrar, University of California Davis
Nita Tarchinski, University of Michigan

Website:

https://www.seismicproject.org/working-groups/measurement/lak_workshop/

Interactive Workshop Session

As the field of learning analytics has matured over the past decade, the demand for individuals with the necessary knowledge and skills to investigate and improve learning experiences and outcomes has increased dramatically. Over the past few years, universities have launched a number of graduate programs that aspire to fill the training gap for researchers and practitioners alike with additional institutions currently in the development process. To date, there have been few broad discussions of competencies, curriculum, and instructional approaches for teaching learning analytics and this session will bring together existing graduate programs to discuss key elements that can improve current efforts and provide guidance for institutions that plan to develop degrees and certificates. The goal of this workshop is to identify common and divergent program elements, successes and challenges, effective and ineffective strategies and approaches, and commit to the sharing of curricular resources for existing and future programs.

Organizers:

Justin T. Dellinger, Texas A&M University
Shaun B. Kellogg, North Carolina State University
George Siemens, University of Texas at Arlington / University of South Australia

Website:

https://learninganalytics.net/la-graduate-programs/

Interactive Workshop Session

The term human-centred learning analytics (HCLA) is an emerging subcommunity of learning analytics (LA) researchers and practitioners interested in creating reliable and trustworthy LA systems that amplify and augment the abilities of educational stakeholders and which are aligned to intentions, revealed preferences, ideal preferences, interests and values. This is the fourth edition of this HCLA workshop which seeks to build on the momentum from recent years within the LA and TEL communities around the contributions that Human-Centred Design and Human-Centred Artificial Intelligence theory and practice should make to LA system conception, design, implementation and evaluation.

Organizers:

Roberto Martinez-Maldonado, Monash University
Patricia Santos, Universitat Pompeu Fabra
Khadija El Aadmi Laamech, Universitat Pompeu Fabra
Carla Barreiros, Graz University of Technology
Luettamae Lawrence, Utah State University
Juan Pablo Sarmiento, New York University
Mohamed Chatti, University of Duisburg-Essen
Yannis Dimitriadis, Universidad de Valladolid

Website:

https://sites.google.com/view/hcla23/home

Tutorial

Across the past decade, Open science has increased in momentum, making research more openly available and reproducible. In parallel, learning analytics, as a subfield of education technology, has been increasing as well, providing more accurate statistical models and integrations to improve learning. However, open science and learning analytics rarely tend to intersect, causing a bit of difficulty when trying to reuse methodologies, datasets, analyses for replication, reproduction, or an entirely separate end goal. In this tutorial, we will provide an overview of open science principles and their benefits and mitigation within research. In the second part of this tutorial, we will provide an example on using the Open Science Framework to make, collaborate, and share projects. The final part of this tutorial will go over some mitigation strategies when releasing datasets and materials such that other researchers may easily reproduce them. Participants in this tutorial will gain a better understanding of open science, how it is used, and how to apply it themselves.

Organizers:

Aaron Haim, Worcester Polytechnic Institute
Stacy Shaw, Worcester Polytechnic Institute
Neil Heffernan, Worcester Polytechnic Institute

Website:

https://lak2023-tutorial.howtoopenscience.com/

Interactive Workshop Session

This half-day interactive workshop focuses on participatory design of future learning experiments that could be embedded within emerging digital learning platforms that are guided by the Standards of Excellence in Education Research (SEER) principles published by the U.S. Department of Education, Institute of Education Sciences (IES). Researchers (including students), practitioners, policy makers, and others attending the workshop will learn about the SEER principles and opportunities to conduct platform-based learning research on six widely used digital learning platforms before getting the opportunity to participate in co-design activities with representatives/developers of the platform of their choice.

Organizers:

Ryan Baker, University of Pennsylvania
Stephen Fancsali, Carnegie Learning, Inc.
Neil Heffernan, Worcester Polytechnic Institute
Rene Kizilcec, Cornell University
Debshila Basu Mallick, Rice University
Danielle McNamara, Arizona State University
Benjamin Motz, Indiana University
Steve Ritter, Carnegie Learning, Inc.
Jeremy Roschelle, Digital Promise

Website:

https://sites.google.com/carnegielearning.com/lak2023-workshop-pele/home

Interactive Workshop Session

We propose the first annual workshop on Partnerships for Cocreating Educational Content. This workshop explores ample opportunities in leveraging humans, AI, and learning analytics to generate content, particularly appealing to instructors, researchers, learning engineers, and many other roles. The process of humans and AI cocreating educational content involves many stakeholders (students, instructors, researchers, instructional designers, etc.), thus multiple viewpoints can help to inform what future generated content might be useful, new and better ways to assess the quality of such content and to spark potential collaborative efforts between attendees. We ultimately want to show how everyone can leverage recent advancements in learnersourcing, AI, and learning analytics, and engage all participants in shaping the landscape of challenges and opportunities in this space. Our hope is to attract attendees interested in scaling the generation of instructional and assessment content and those interested in the use of online learning platforms.

Organizers:

Steven Moore, Carnegie Mellon University
Hassan Khosravi, University of Queensland
Paul Denny, University of Auckland
Anjali Singh, University of Michigan
Christopher Brooks, University of Michigan
John Stamper, Carnegie Mellon University

Website:

https://sites.google.com/andrew.cmu.edu/partnerships-for-cocreating-ed

Interactive Workshop Session

This workshop is the 4th annual pre-conference meeting at LAK to discuss the ways in which theory informs and arises from learning analytics research. The organisers will briefly set the scene then hand over to Andy Nguyen to give the keynote presentation on a new generic Framework for Analysing Regulation in Collaborative Learning (FARCL). The second half of the workshop will be devoted to conversation. Participants are invited to nominate a current research project or new research idea that would benefit from a roundtable-style discussion with colleagues, including a theoretical framework that is of interest. In groups, participants will consider how nominated projects can demonstrate the role of theory in their design, model validation, and interpretation of findings.

Organizers:

Kathryn Bartimote, University of Sydney
Sarah K. Howard, University of Wollongong
Dragan Gasevic, Monash University

Website:

https://sites.google.com/view/lak23theorylaworkshop/home

Interactive Workshop Session

The challenges that emerge from the use of educational data in sociotechnical systems have received increasing attention in recent years. However, much of the discussion has centered around analysis of problems, such as issues of ethics and equity, or solutions to specific local quandaries. We lack holistic examination of embedded assumptions and values contributing to such problems and radical innovation of LA that might shift us away from such paradigms. In this half-day interactive workshop, we take up the idea of a “subversive stance” as a tool for generative discussions and insights around these questions and to spur ideas for unorthodox possibilities in LA that support equitable educational practices. Participants will reflect about deep seated assumptions of our discipline, consider alternatives, and ideate LA artifacts that could deal with these challenges.

Organizers:

Juan Pablo Sarmiento, New York University
Alyssa Wise, New York University

Website:

https://sites.google.com/nyu.edu/sla-workshop-lak23

Mini-track / Symposium

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 and LAK22 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, and a multi-source dataset for higher education programming classes consisting of reading behavior and coded programming logs. 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. Participant contributions will be collected as evidence in a repository provided by the workshop and will be shared with the research community to promote reading analysis research.

Organizers:

Brendan Flanagan, Kyoto University
Atsushi Shimada, Kyushu University
Fumiya Okubo, Kyushu University
Hsin Tse Lu, National Pingtung University
Stephen J.H. Yang, National Central University, Taiwan
Hiroaki Ogata, Kyoto University

Website:

https://sites.google.com/view/lak23datachallenge/home

Interactive Workshop Session / Mini-track Symposium

This is the proposal for an interactive workshop on measuring and facilitating self-regulated learning (SRL). Prior research has shown that SRL skills are essential for successful life-long learning. Measuring SRL based on unobtrusive trace data and facilitating SRL based on real-time analysis. Such trace data have been pointed out as very valuable research directions. However, major challenges and significant gaps in this area are still many, such as i) the detection, measurement, and validation of SRL processes with trace data is still a much-debated issue within the SRL community; and ii) the design principles for effective interventions and the complex conditions and contexts when these interventions facilitated learning are still not known. Therefore, we aim to improve the measurement and facilitation of SRL by hosting this full-day workshop, which will i) initiate a project-to-project level dialogue to foster deep, cross-team collaborations and ii) provide the participants with hands-on opportunities to experience the measurement and facilitation of SRL. An open call for contributions will be distributed, and the participants will join roundtable-style discussions and hands-on co-design activities. Expected outcomes are forming a community of practice, potential collaborative projects, and possible follow-up joint publications and grant submissions.

Organizers:

Yizhou Fan, University of Edinburgh
Mladen Raković, Monash University
Shaveen Singh, Monash University
Megan Wiedbusch, University of Central Florida
Daryn Dever, University of Central Florida
Xinyu Li, Monash University
Joep van der Graaf, Radboud University
Lyn Lim, Technical University of Munich
Inge Molenaar, Radboud University
Maria Bannert, Technical University of Munich
Roger Azevedo, University of Central Florida
Dragan Gašević, Monash University

Website:

https://sites.google.com/monash.edu/lak23-trace-srl

Interactive Workshop Session 

Learning analytics (LA) have been implemented to improve teaching and learning practices in different countries using a variety of approaches and with different levels of success. To effectively transfer an LA system from one country to another, we need to carefully consider contextual, technical, and cultural factors. In this interactive workshop, we will explore the role of the cultural values that are important for the successful adoption and use of LA systems around the world: 1. the acceptance of LA services and related ethical concerns, 2. the design of LA systems, and 3. the evaluation of LA interventions. This one-day workshop will focus on the role of culture in LA from a value-sensitive perspective. In particular, we will: 1. discuss and identify possible cultural differences and similarities for the wider adoption of LA systems at scale, and 2. introduce and practice several culture- and value-sensitive design methods on selected LA tools.

Organizers:

Olga Viberg, KTH Royal Institute of Technology
Ioana Jivet, Goethe University Frankfurt & DIPF
Rene F. Kizilcec, Cornell University
Maren Scheffel, Ruhr University Bochum

Website:

https://sites.google.com/view/carla-workshop

Interactive Workshop Session

Learning Analytics research increasingly involves large amounts of complex language data. This conincides with a widespread surge in interest in natural language processing (NLP), with models like BERT, GPT-3, and DALL-E making headlines. Such tools excel at raw predictive power, but often fall short on other important measures such as ease of use, explainability, and strong theoretical foundations. Fortunately, tools for NLP such as LIWC, Coh-Metrix and CGA do not suffer from these drawbacks. These tools may have slightly lower accuracies than cutting-edge NLP models, but their ease of use, explainability, and theoretical foundations make them compelling options for LA researchers and practitioners. This workshop will serve to highlight such tools, the research being done with them, and the roles they can play in advancing Learning Analytics research. This workshop also welcomes work focusing on the explainability, auditability, and trustworthiness of cutting edge NLP models. Building on a successful foundational NLP workshop at LAK22, this year’s gathering will continue to build NLP capacity within Learning Analytics, and develop lasting networks for future scholarly exchange.

Organizers:

Pete Smith, University of Texas Arlington
Hendry Anderson, University of Texas Arlington
Elizabeth Powers, University of Texas Arlington
James Pennebaker, University of Texas Austin
Justin T. Dellinger, University of Texas A&M
George Siemens, University of Texas Arlington / University of South Australia

Website:

https://learninganalytics.net/laln/lowering-barriers-to-trustworthy-nlp/

Interactive Workshop Session

The CROSSMMLA workshop series has focused on collecting and analysing multimodal data across the physical and virtual spaces for understanding and optimising learning processes. In this year's CROSSMMLA workshop, we invite all submissions focusing on multimodal learning analytics, with a particular interest in approaches to "closing the feedback loop" by leveraging multimodal data for generating meaningful feedback. Aligned with the LAK'2023 format, it will be conducted as a synchronous face-to-face one-day workshop and include hybrid options for the presenters and participants who want to attend online.

Organizers:

Daniele Di Mitri, DIPF | Leibniz Institute for Research and Information in Education
Namrata Srivastava, Monash University
Roberto Martinez-Maldonado, Monash University
Mutlu Cukurova, University College London
Daniel Spikol, University of Copenhagen

Website:

http://crossmmla.org/

Interactive Workshop Session

Learning from Large Scale Data: Generating Knowledge to Improve Practice in K12 Schools is a full day pre-conference workshop of expert panel discussions, lectures on data-intensive improvement through the lenses of improvement science and learning analytics, and practical data unpacking activities. This workshop is an opportunity for educators to gain practical data-centric improvement knowledge for application in their respective institutions, as well as dedicated time to network with like-minded professionals. Workshop participants will receive a formal Certificate of Attendance.

Organizers:

Jojo Manai, Carnegie Foundation
Catherine Robert, University of Texas Arlington
Andrew Krumm, University of Michigan
Simon Buckingham Shum, University of Technology Sydney
Susan Haynes, Carnegie Foundation
Judi Fusco, Digital Promise
Jeremy Roschelle, Digital Promise
Grace Lynch, University of New England

Website:

https://sites.google.com/carnegiehub.org/learningfromlargescaledata/home

Interactive Workshop Session

This full day event is for those students selected to the LAK23 Doctoral Consortium. 

Organizers:

Sasha Poquet,  Learning Planet Institute
Jelena Jovanovic, University of Belgrade
Christopher Brooks, University of Michigan
Dragan Gasevic, Monash University

Mini-track/Symposium

This half-day workshop will focus on situating affect in learning analytics. Interdisciplinary researchers will present state-of-the-art research on techniques for measuring and modeling affect within the context of learning and education, emphasizing key conceptual, theoretical, methodological, and analytical challenges and opportunities for learning analytics (LA). Focus will be placed on interdisciplinary approaches that use contemporary theories of affect and learning sciences and discussing operational links with methods and analyses to other learning constructs. During the workshop, we will discuss implications of situating affect in learning analytics and highlight implications for building more inclusive, equitable, and quality educational experiences for diverse learning that contribute to trustworthy LA for a range of stakeholders including teachers and researchers.

Organizers:

Elizabeth Cloude, University of Pennsylvania
Ryan Baker, University of Pennsylvania
Caitlin Mills, University of Minnesota
Vitomir Kovanovic, University of South Australia
Dragan Gasevic, Monash University

Website:

https://affectla.wixsite.com/affectla2023

Interactive Workshop Session

The aim of this half-day workshop, organized in cooperation of three universities, is twofold. First, it will provide a platform for sharing of experiences, research and challenges related to the link between learning analytics (LA) and learning design (LD). Second, the workshop will enable participants to engage with an innovative, free-to-use LD tool (learning-design.eu), and create advanced learning analytics on LD using the tool. Participants will be invited to work collaboratively on LD of their own courses, reflect on the LA generated by the LD tool and improve the course LD accordingly. This will also contribute to the further development of the concept and tool, based on a pre-established research protocol. Participants will take away recommendations for improvement of their own courses, as well as know-how on how to use an innovative LD tool at their own institutions. Ahead of the workshop, if interested, participants will be invited to apply for a short presentation (5-10 minutes). They will also be asked to consider their courses and particular learning outcome(s) which could be redesigned at the workshop.

Organizers:

Blaženka Divjak, University of Zagreb, FOI
Darko Grabar, University of Zagreb, FOI
Dragan Gašević, Monash University
Mladen Raković, Monash University
Bart Rienties, Open University

Website:

https://learning-design.eu/lak-2023

Interactive Workshop Session

The 8th Annual workshop brings together work by the learning analytics community over the past decade to assess what has been achieved in bridging learning design (LD) and learning analytics (LA) and explore what further challenges need to be overcome in order to guide the development of systems that can support the provision of pedagogically meaningful learning analytics to teachers and learners. A working paper written for the purpose of this workshop will be used to introduce key frameworks proposed in literature, and situate how these contributions provide building blocks in relation to what would be needed to create an integrated, continuous bridge between LD and LA. The workshop activities will involve learning scenarios to enable the critique of a proposed integrated framework for LD/LA. Participants will work in and share across groups to identify the usefulness of the framework presented in the working paper, as well as the gaps and challenges that remain to be resolved to realise an operationalisable link between LD and LA. Another outcome of the workshop will be the development of evaluation projects that will be conducted throughout the year and showcased in next year’s DesignLAK workshop.

Organizers:

Sadia Nawaz, University of Melbourne
Nancy Law, University of Hong Kong
Linda Corrin, Deakin University
Aneesha Bakharia, University of Queensland
Minghui Chen, McMaster University
Sandra Milligan, University of Melbourne

Website:

https://sites.google.com/view/designlak23

Interactive Workshop Session / Mini-track symposium

Collaboration is central to learning. However, analytic methods applied to analysis of small group collaboration are still in research stages and have yet to have significant impact in supporting students and educators in the classroom. In addition, collaboration analytics methods have been developed across a wide range of field, focusing on different aspects of group interaction, and cognitive, social, and affective states. This half-day interactive workshop will bring together a diverse group of researchers who are working with student collaboration data and developing collaborative analytics. Participants will have the opportunity to share their methodology as well as learn about other approaches that may come from different perspectives of collaborative analytics. In a series of guided discussions and interactive sessions, participants will be able to work with their own and others’ sets of data to try different approaches to analyzing student collaborative work.

Organizers:

Peter Foltz, University of Colorado, Boulder
Sadhana Puntambekar, University of Wisconsin, School of Education
Jamie Gorman, Arizona State University
Jason Reitman, University of Colorado
Sidney D'Mello, University of Colorado, Boulder

Website:

https://sites.google.com/colorado.edu/collaborativeanalytics/home