Pre-conference Schedule
March 21, 2022 - Day 1, 9 AM to 12 PM PDT
Tutorial
Student clickstream data is a valuable data source in learning analytics research. These time-stamped records of student click events within a Learning Management System (LMS) provide researchers with rich and finely detailed information about the learning process. One of the main drawbacks of student clickstream data, however, is that it is complex, requiring a nuanced understanding of the structure of the data, as well as advanced data processing techniques. Adding to this issue is that there are few formalized trainings that teach the specific methods and techniques for working with clickstream data. Thus, the goal of this pre-conference tutorial is to directly train researchers on processing, inspecting, and visualizing clickstream data using the R programming language. During this workshop, attendees will learn about the general structure of clickstream data and methods for working time-stamped variables. In addition to learning fundamental data cleaning and processing techniques, attendees will also learn how to construct and visualize measures of engagement. Intermediate-level experience with the R programming language is required, as well as familiarity with the Tidyverse family of libraries.
Organizers:
Fernando Rodriguez, University of California, Irvine
Hye Rin Lee, University of California, Irvine
Website:
https://lak22-clickstream-tutorial.netlify.app/about-tutorial/
Interactive Workshop Session
This SoLAR initiated workshop aims to bring together the SoLAR community to explore how open science and scholarship can be incorporated into our culture and practice using a three-part interactive format. Amongst the questions to be discussed are: What could and should SoLAR do to encourage open science and scholarship?; What prevents researchers in SoLAR from contributing to open science?; Which learning analytics approaches could (not) be made open, and why?; And what could SoLAR do to make open science and scholarship more attractive and relevant? We aim to share the outcomes of the workshop broadly within the SoLAR community and invite the community to respond to both the outcomes of this workshop and the follow-up SoLAR position paper, Learning Analytics: Open Science, Open Scholarship.
This workshop is sponsored by the Society for Learning Analytics Research (SoLAR) and will be offered for free however, there is a limited capacity so you must be registered to join. Outcomes will be shared with the broader Learning Analytics community after the workshop.
Organizers:
Bart Rienties, Open University UK
Rebecca Ferguson, Open University UK
Christopher Brooks, University of Michigan
Simon Buckingham Shum, University of Technology Sydney
Maren Scheffel, Ruhr University Bochum
Website:
March 21, 2022 - Day 1, 12 PM to 3 PM PDT
Interactive Workshop Session
The 1st Workshop on Learning Analytics and Assessment was successfully organized as a part of LAK21 conference. At the workshop, we gathered around 30 leading scholars from dynamically emerging fields of learning analytics and assessment. Following the very productive interaction among the workshop participants, this initiative has resulted in multiple post-workshop collaborations. The workshop organizers jointly submitted a proposal for Special Issue (SI) on Learning Analytics and Assessment to the British Journal of Educational Technology (BJET). Recently, this proposal has been accepted. To take advantage of this momentum and continue productive discussions on this important and emerging research topic, we propose the 2nd workshop on Learning Analytics and Assessment. The intent of this workshop is to address some of the key open challenges in learning analytics that are related to reliability and validity of data collection and analysis, use of learning analytics in formative and summative assessment, measurement of learning progression, 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 a possible follow-up publication.
Organizers:
Dragan Gasevic, Monash University
Mladen Rakovic, Monash University
Naif Aljohani, King Abdulaziz University
José A. Ruipérez Valiente, Complutense University of Madrid
Sandra Milligan, University of Melbourne
Saeed-Ul Hassan, Information Technology University
Website:
Interactive Workshop Session
Over the past two decades, learning analytics has become an established field of research and practice, with a significant increase in the number of academic publications and related results in freely available web search engines. However, professional writing, to either an academic or general audience, can become an overwhelming task, particularly in an interdisciplinary field at the intersection of education, computer science, psychology, and other fields. In this participatory workshop, we invite postgraduate students and early to mid-career researchers to explore the differences among different publication venues in the field, and participate in practical exercises to strengthen their academic writing skills. Through this workshop, we expect to enhance the effectiveness of scientific communications on learning analytics, thereby expanding impact and increase understanding and use of learning analytics.
This workshop is sponsored by the Society for Learning Analytics Research (SoLAR) and will be offered for free however, there is a limited capacity so you must be registered to join.
Organizers:
Yi-Shan Tsai, Monash University
Melanie Peffer, University of Colorado, Boulder
Antonette Shibani, University of Technology Sydney
Isabel Hilliger, Pontificia Universidad Católica de Chile
Bodong Chen, University of Minnesota
Yizhou Fan, University of Edinburgh
Rogers Kaliisa, University of Oslo
Nia Dowell, University of California, Irvine
Simon Knight, University of Technology Sydney
Website:
https://www.solaresearch.org/events/lak/lak22/workshop-writing-for-publication/
Mini-track/Symposium
The workshop proposal for CrossMMLA focused on Smart Learning Environments to collect and analyse multimodal data across the physical and the virtual. The rapidly changing nature of education that has begun to embrace hybrid learning and this changes the landscape of how MMLA is used. This year's CROSSMMLA will focus on SLEs supported by MMLA that support diverse learning scenarios. The Workshop proposes an asynchronous format that includes pre-recorded video demonstrations and position papers for discussion, followed by a half-day virtual meeting at LAK'2022.
Organizers:
Daniel Spikol, UCPH, Denmark
Miguel L. Bote-Lorenzo, UVA, Spain
Mutlu Cukurova, UCL, UK
Elise Lavoue, Université de Lyon, France
Michail Giannakos, NTNU, Norway
Xavier Ochoa, NYU, USA
Daniele Di Mitri, DIPF, Germany
Davinia Hernandez-Leo, UPF Spain
Website:
March 21, 2022 - Day 1, 3 PM to 6 PM PDT
Interactive Workshop Session
While the field of learning analytics (LA) has made enormous strides in improving and understanding learning processes with data-driven approaches, some questions have remained difficult to answer using quantitative data alone. Incorporating qualitative, textual data can help address many of these questions, while also providing rich context and nuance that may be otherwise difficult to discover. The field of natural language processing (NLP) has itself undergone a renaissance over the past decade, turning more to massive datasets, enormous compute budgets, and rapid tool development. NLP has potential for an expanded role in LA and emphasis on increasingly debated artificial intelligence (AI) topics, such as inclusivity, interdisciplinarity, impact, and roles of educator-researchers.
This workshop focuses on connecting scholars and applied experience across fields by asking how: 1) underexplored questions in LA can be addressed by developments in NLP and 2) how the LA field can further dialog in and investigate key areas that are at the center of AI research and application. Participants will 1) explore how LA researchers can incorporate NLP’s approaches and tools into their current practices and amplify them into the broader areas of AI research and applied practice and 2) develop lasting networks for future scholarly exchange.
Organizers:
Pete Smith, University of Texas Arlington
Elizabeth Powers, University of Texas Arlington
Henry Anderson, University of Texas Arlington
Justin Dellinger, University of Texas Arlington
George Siemens, University of Texas Arlington
Website:
https://learninganalytics.net/laln/broadening-the-nlp-agenda-in-la-for-ai/
Mini-track/Symposium
This half day workshop is the 3rd 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 Roger Azevedo to give the keynote presentation on ‘Emotion Theories and Learning Analytics’. 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, along with a theoretical framework of interest. In groups, participants will consider how nominated projects can demonstrate the role of theory in design, model validation and interpretation of findings.
Organizers:
Kathryn Bartimote, University of Sydney
Sarah K. Howard, University of Wollongong
Dragan Gasevic, Monash University
Website:
March 21, 2022 - Day 1, 6 PM to 9 PM PDT
Mini-track/Symposium
There are a growing number of evaluated writing analytics tools and technologies targeting the improvement of academic writing. As the field grows, there is potential for new writing analytics tools to target formative feedback for higher-order thinking skills. This writing analytics workshop, the sixth in the series at LAK, will explore how writing analytics can potentially support these life skills among learners, and the data, tools, analytics, and pedagogic contexts for such implementations.
Organizers:
Antonette Shibani, University of Technology Sydney
Andrew Gibson, Queensland University of Technology
Simon Knight, University of Technology Sydney
Philip H Winne, Simon Fraser University
Diane Litman, University of Pittsburgh
Website:
March 22, 2022 - Day 2, 3 AM to 6 AM PDT
Interactive Workshop Session
Advances in learning analytics have led to a proliferation of data-informed solutions for delivering personalised feedback to students at scale. A very recent trend has also seen the use of learning analytics approaches to create data-informed educational nudges. However, little research exists to guide practitioners regarding the characteristics of effective personalised feedback and educational nudges. This workshop is the third in a series of workshops delivered at LAK which explored tools and applications for personalised feedback, and how students perceived such feedback. In this 3-hour, interactive workshop, we explore examples of how educators and system developers can co-design personalised feedback and nudge processes in ways that promote students’ engagement with this feedback.
Organizers:
Lisa-Angelique Lim, University of Technology Sydney
Caitlin Hayward, University of Michigan
Benjamin Hayward, University of Michigan
Holly Derry, University of Michigan
Rebecca Matz, University of Michigan
Danny Liu, University of Technology Sydney
Mette Trier Damgaard, Aarhus University
Website:
March 22, 2022 - Day 2, 6 AM to 9 AM PDT
Interactive Workshop Session
This interactive workshop aims to raise the participants’ awareness of possible effects of stakeholders’ cultural values and preferences on: 1. the acceptance of learning analytics (LA) services and related privacy concerns, 2. the design of LA tools, and 3. the evaluation of LA interventions. LA have been implemented in various countries, often at a limited scale. Also, we have seen that LA have been used in different ways in different countries. This makes the transfer of LA solutions from one country to another challenging, due to varying contextual, technical, and cultural factors. In this interactive workshop, we aim to discuss and identify possible cultural differences and also similarities–the factors that have hitherto not been extensively studied by LA researchers–for the wider adoption at scale. Through this workshop, we will explore whether the stakeholders’ cultural values are some of the factors that the LA community should consider in the design and evaluation of LA systems. In the workshop, we will introduce the participants to culture-sensitive and value-sensitive design methods, and practice some of them.
Organizers:
Ioana Jivet, DIPF, Leibniz Institute for Research and Information in Education
Olga Viberg, KTH Royal Institute of Technology
Maren Scheffel, Ruhr University Bochum
Website:
Tutorial
Data-informed decision-making tools help participants in the learning process predict likely outcomes and how to affect those outcomes. However, implementations of these systems depend upon assumptions, often implicit, about the curriculum theory paradigm(s) prioritized by the learning institution in deciding what outcomes to support. Making these assumptions explicit can help us to construct predictive learning analytics models that generate predictions and guidance in keeping with the needs of all participants and stakeholders. This half-day tutorial workshop begins with an interactive exercise to “unpack” our assumptions about the nature of teaching and learning and explore how those assumptions can guide model design. We will explore the practical considerations of collecting and processing data most appropriate to those curriculum priorities, using data sets provided by the organizer. Participants may use sample data or to import data to a supplied secure instance of a model building tool to construct features from commonly available data elements and to experiment with model construction and validation. At the conclusion of the workshop, each participant will present a model design to the group that aligns with their chosen curriculum paradigm, including ideal features and labels, possible proxies, and risks to avoid. Future directions will be discussed.
Organizers:
Elizabeth Dalton, IntelliBoard
Website:
March 22, 2022 - Day 2, 9 AM to 12 PM PDT
Mini-track/Symposium
Social Network Analysis (SNA) is established as one of the most common methods in learning analytics research. SNA has been used to analyze learners’ interactions, to inform learning design, and to model students’ performance. The workshop entitled "Using Network Science in Learning Analytics: Building Bridges towards a Common Agenda", carried out within the LAK2021 conference, resulted in valuable insights and outcomes: guidelines for better reporting, methodological improvements, and discussions of several novel research threads. However, the focus of the conversation has been on methodological issues of SNA. This year, we would like to extend the conversation by maintaining the focus on what learning analytics of networks in learning settings can do to improve learning and educational opportunities. As such, this new edition of the workshop aims at building on the fruitful accomplishments of the previous iteration to address new themes, which we refer to as “challenges and opportunities” in relation to practice. We encourage submissions around examples of applications and impact, including those that can help address societal challenges embedded within educational practices. This also includes an open conversation about privacy and ethical implications of network data.
Organizers:
Mohammed Saqr, University of Eastern Finland
Sonsoles López-Pernas, Universidad Politécnica de Madrid
Ángel Hernández-García, Universidad Politécnica de Madrid
Miguel Ángel Conde González, Universidad de León
Oleksandra Poquet, University of South Australia
Website:
Interactive Workshop Session
Higher education is in flux in a datafied world. Students in all disciplines need new forms of data literacy. But curricular responses are slow, and the most expedient solution is patchwork of courses without considering deeper curriculum design concerns. The result is often the transplanting of data science courses and making shallow disciplinary connections. The resulting graft is neither transformative nor existing. As a response, this workshop offers a design experience for participants to conceptualize data literacy in a deeper way, informed by interdisciplinary and systems theory. By focusing on instructional, institutional, and international levels— and importantly, relationships within and between these levels—we present a framework for curriculum development that goes beyond copying computer science instruction into other disciplines.
Organizers:
Danielle Hagood, University of Copenhagen
Mark Johnson, University of Copenhagen
Morten Misfeldt, University of Copenhagen
Website:
March 22, 2022 - Day 2, 12 PM to 3 PM PDT
Interactive Workshop Session
The term human-centred learning analytics (HCLA) was recently coined to refer to the subcommunity of LA researchers and practitioners interested in utilising the body of knowledge and practice from design communities, such as participatory design and co-design, into data-intensive educational contexts. Although there is a growing interest in designing LA systems with students and teachers, several questions still remain regarding how the LA community can appropriate design approaches from other communities and identify best practices that can be more suitable for LA developments. This workshop intends to address some of these questions.
Organizers:
Yannis Dimitriadis, Universidad de Valladolid
Roberto Martinez-Maldonado, Monash University
Juan Pablo Sarmiento, New York University
Fabio Campos, New York University
Patricia Santos, Universitat Pompeu Fabra
Carla Barreiros, Graz University of Technology
Website:
Interactive Workshop Session
Over the last decade, learning analytics has come a long way from measuring shallow proxies of learners' engagement towards capturing fine grained sensor data that allow for measuring complex dimensions such as affect or creativity. The unprecedented amounts of data, both in terms of quantity and quality, brought a plethora of opportunities and raised various ethical and privacy concerns. In that sense, managing and protecting learners' privacy risk reliably and consistently across all datasets in a pragmatic and cost-effective way is of utmost importance for further adoption of learning analytics. In this interactive, half-day workshop session, we will present the “state-of-the-art” work on data privacy risk measurement and reduction. In so doing, we will discuss a variety of methods that provide measurable, policy driven, and provable mitigation mechanisms for maintaining learners' privacy. Participants will also have an opportunity to explore in practice a learning analytics toolbox developed based on the "privacy by design" principles, incorporating some of those novel algorithms. In the final part, participants will be asked to reflect on their perceived usefulness of the proposed solution, as well as to provide an input on their expectations for maintaining learners' privacy.
Organizers:
Srecko Joksimovic, University of South Australia
Djazia Ladjal, Practera
Chen Zhan, University of South Australia
Thierry Rakotoarivelo, CSIRO
Alison Li, Practera
Website:
March 22, 2022 - Day 2, 3 PM to 6 PM PDT
Interactive Workshop Session
The 7th Annual DesignLAK Workshop addresses the challenge of visualising the alignment between learning outcomes, activities, behaviour, and achievement to inform feedback on learners’ progress and refinement of course design. Many advances have been made in the field of learning analytics (LA) that have focused on ways that learner behaviours and performance can be visualised for educators and learners. However, there is an ongoing tension between the value of representations of learner behaviour and activity versus a focus on performance and progression outcomes. To reap the potential benefits of LA greater consideration needs to be given to how learning design and models of learner progress can inform the design of analytics and visualisations to enable the provision of pedagogically appropriate feedback to learners while also providing information that can be used by educators to refine course design. In this interactive, half-day workshop participants will be given the opportunity to explore these points of intersection between LA measures, models of learner progress, and learning design. Using the Learning Design Studio tool (Law et al., 2017), participants will also have a chance to create visualisations that can provide feedback to learners and educators to enhance learning progress and design.
Organizers:
Nancy Law, University of Hong Kong
Sandra Milligan, University of Melbourne
Linda Corrin, Swinburne University of Technology
Aneesha Bakharia, University of Queensland
Sadia Nawaz, University of Melbourne
Website:
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 on secondary school reading behavior. As the COVID-19 pandemic has bought about sudden change in learning environments around the world, participants of this year’s workshop will be given the unique opportunity to analyze the changes from onsite classes in 2019 and online classes in 2020 in the same education institution. 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 wider research community to promote the development of research into reading analysis systems.
Organizers:
Brendan Flanagan, Kyoto University
Atsushi Shimada, Kyushu University
Fumiya Okubo, Kyushu University
Rwitajit Majumdar, Kyoto University
Huiyong Li, Kyoto University
Hiroaki Ogata, Kyoto University
Website:
March 22, 2022 - Day 2, 6 PM to 9 PM PDT
Mini-track/Symposium
This workshop aims at discussing and sharing ideas to help construct a philosophical framework that learning analytics needs as a field. LAK’22 would be the second year the workshop runs and it builds on the success and reflection of its 2021 iteration. This workshop is the first step towards the development of a philosophical approach to help practitioners collaborate, interrogate, and develop this foundation. The workshop is a half-day event. Participants will be invited to submit a brief position paper for review in advance of the workshop. During the event there will be brief presentations of these papers followed by collaborative activities to create robust, but intellectually stimulating and constructive conversations. The workshop will be synthesized via a multi-authored publication summarizing the points discussed to share with the broader field.
Organizers:
Pablo Munguia, Flinders University
Andrew Gibson, Queensland University of Technology
Website: