General Call

We welcome submissions from both research and practice, encompassing different theoretical, methodological, empirical and technical contributions to the learning analytics field. Learning analytics research draws on many distinct academic fields, including psychology, the learning sciences, education, neuroscience, computer science and design. We encourage the submission of works conducted in any of these traditions. We also welcome research that validates, replicates and examines the generalizability of previously published findings, as well as examines aspects of adoption of existing learning analytics methods and approaches. 

This year, we encourage contributors to consider how collective action can tackle concerns and issues associated with the implementation of learning analytics. Learning analytics impacts on both technical and social systems. We invite papers that address areas of bias, privacy, ethics, transparency and accountability from multiple lenses including the design, implementation and evaluation stages of learning analytics. Accountable analysis refers to providing a certain degree of transparency and explanation, and adjusting the transparency of data and computation according to the differences of stakeholders. Trust goes hand in hand with transparency in decision-making; whether the decisions for predictions and interventions are fair and explainable is an ethical issue. There is still much to be done in human behavior and social values, such as respecting privacy, providing equal opportunities, and accountability. Based on diversity, equity, and belonging, inclusive learning analytics identifies and breaks down systemic barriers to inclusion, fosters a culture that every learner knows their belonging, feels empowered to bring their whole self to learning, and is inspired to learn.

For the 13th Annual conference, we encourage authors to address the following questions related to LAK23's theme of "Towards Trustworthy Learning Analytics:

• What are the essential components of building a trustworthy LA system?
• How do we give diverse stakeholders a voice in defining what will make LA trustworthy?
• How can we develop and evaluate instruments or frameworks for measuring the trustworthiness of a LA system?
• Is there anything distinctive about trustworthiness in teaching and learning or can we borrow unproblematically from notions of trustworthiness from other fields?
• How can we develop models or frameworks that can measure the fairness, bias, transparency or explainability level of a LA system?
• How do we develop human-in-the-loop predictive or prescriptive analytics that benefit from instructor judgement?
• How can we enable students or instructors to share their perceptions of the level of trustworthiness of a LA system?
• How can we reliably and transparently model student competencies? 

Other topics of interest include, but are not limited to, the following:

Implementing Change in Learning & Teaching:

• Ethical issues around learning analytics: Analysis of issues and approaches to the lawful and ethical capture and use of educational data traces; tackling unintended bias and value judgements in the selection of data and algorithms; perspectives and methods that empower stakeholders.
• Learning analytics adoption: Discussions and evaluations of strategies to promote and embed learning analytics initiatives in educational institutions and learning organizations. Studies that examine processes of organizational change and practices of professional development that support impactful learning analytics use.
• Learning analytics strategies for scalability: Discussions and evaluations of strategies to scale capture and analysis of information in useful and ethical ways at the program, institution or national level; critical reflections on organizational structures that promote analytics innovation and impact in an institution.
• Equity, fairness and transparency in learning analytics: Consideration of how certain practices of data collection, analysis and subsequent action impact particular populations and affect human well-being, specifically groups that experience long term disadvantage. Discussions of how learning analytics may impact (positively or negatively) social change and transformative social justice.

Understanding Learning & Teaching:

• Data-informed learning theories: Proposals of new learning/teaching theories or revisions/reinterpretations of existing theories based on large-scale data analysis.
• Insights into specific learning processes: Studies to understand particular aspects of a learning/teaching process through the use of data science techniques, including negative results.
• Learning and teaching modeling: Creating mathematical, statistical or computational models of a learning/teaching process, including its actors and context.
• Systematic reviews: Studies that provide a systematic and methodological synthesis of the available evidence in an area of learning analytics.

Evidencing Learning & Teaching:

• Finding evidence of learning: Studies that identify and explain useful data for analysing, understanding and optimising learning and teaching.
• Assessing student learning: Studies that assess learning progress through the computational analysis of learner actions or artefacts.
• Analytical and methodological approaches: Studies that introduce novel analytical techniques, methods, and tools for modelling student learning.
• Technological infrastructures for data storage and sharing: Proposals of technical and methodological procedures to store, share and preserve learning and teaching traces, taking appropriate ethical considerations into account.

Impacting Learning & Teaching:

• Human-centered design processes: Research that documents practices of giving an active voice to learners, teachers, and other educational stakeholders in the design process of learning analytics initiatives and enabling technologies.
• Providing decision support and feedback: Studies that evaluate the use and impact of feedback or decision-support systems based on learning analytics (dashboards, early-alert systems, automated messages, etc.).
• Data-informed decision-making: Studies that examine how teachers, students or other educational stakeholders come to, work with and make changes using learning analytics information.
• Personalised and adaptive learning: Studies that evaluate the effectiveness and impact of adaptive technologies based on learning analytics.
• Practical evaluations of learning analytics efforts:  Empirical evidence about the effectiveness of learning analytics implementations or educational initiatives guided by learning analytics.

The conference has three different tracks with distinct types of submissions that are described below. Please see the submission guidelines page for information on paper format and other technical details of submission for each track.

1. RESEARCH TRACK

The focus of the research track is on advancing scholarly knowledge in the field of learning analytics through rigorous reports of learning analytics research studies. The primary audience includes academics, research scientists, doctoral students, postdoctoral researchers and other types of educational research staff working in different capacities on learning analytics research projects.

Submission types for the research track are similar to other years, starting for LAK21, LAK follows ACM’s one column format for submissions. Templates and formatting details are included in the submission guidelines. Please note that published Proceedings will appear in ACM two column format.

• Full research papers (up to 16 pages in ACM 1 column format, including references) include a clearly explained substantial conceptual, technical or empirical contribution to learning analytics. The scope of the paper must be placed appropriately with respect to the current state of the field, and the contribution should be clearly described. This includes the conceptual or theoretical aspects at the foundation of the contribution, an explanation of the technical setting (tools used, how are they integrated into the contribution), analysis, and results. See bulleted list of questions above for more detailed ideas on useful elements to include.
• Short research papers (up to 10 pages in ACM 1 column format, including references) can address on-going work, which may include a briefly described theoretical underpinning, an initial proposal or rationale for a technical solution, and preliminary results, with consideration of stakeholder engagement issues. See bulleted list of questions above for more detailed ideas on useful elements to include.

NOTE: If you are a newcomer to the LAK conference, it might be helpful to review the LAK22 ACM proceedings, openly available from the SoLAR website via ACM’s OpenTOC service. For Tips on writing LAK papers see here.

Should you have further questions regarding paper length or format, please contact us at lakconference@gmail.com 

 

2. PRACTITIONER AND CORPORATE LEARNING ANALYTICS TRACK

The Practitioner and Corporate Learning Analytics (PaC-LA) track is complementary to the research track as part of the main conference program and provides a way in which real-world learning analytics implementations and/or related tools, products, product development and researched-based product evaluations in use by practitioners can be shared with the entire community. The intent of the stream is to contribute to our collective understanding of learning analytics in practice, including product development and improvement, researched-based product evaluations, learning analytics deployment, intervention development and evaluation.  Specifically, some of the goals of PaC-LA presentations are to:

1. contribute to the conversation between researchers and practitioners around adoption, implementation, scaling and evaluation of learning analytics, 
2. provide insights from practice around factors affording or constraining learning analytics adoption and implementation, 
3. present effective learning analytics adoption strategies and approaches, and
4. share experiences on developing a business case for learning analytics adoption.

To meet these goals, submissions are encouraged to reflect on the context and purpose of the presented learning analytics initiative, discuss implementation, outcomes, impacts, and learning, and consider implications for others attempting similar work. We also encourage submissions where an initiative did not achieve what was expected, as we believe that such papers can also provide valuable knowledge to the community. 

We welcome submissions that fall in the scope described above from anyone regardless of their professional roles. Some examples of PaC-LA participants are:

1. Developers, designers, analysts, and other representatives from commercial and industry entities, non-profit organizations, and government bodies. 
2. Policy makers, department leads, instructional technologists, analysts, learning designers and other services staff from education institutions

Successful submissions are expected to offer unique or distinct insights into practical applications, intervention designs, analyses, and/or the processes surrounding their implementation. There is also special interest to explore the growing role of learning analytics in corporate learning, including the skills development of employees, alternative credentialing models, reliance on non-traditional education providers, and the impact of using data to guide corporate learning programs.

While submissions are not formal research papers, the more complete the report of the work is, including usage of the learning analytics and their impact, the higher the probability of being selected for inclusion. Further, while the stream is intended for non-researchers, papers are still expected to adhere to high standards of scholarly writing, including: 

• thorough description of the institutional context for the work
• detailed presentation of the innovation and the results found about it
• discussion of issues that arose / lessons learned / implications for future efforts by others attempting similar work

The following criteria will guide reviewers when selecting submissions, although we recognise that this list may not be applicable to all submissions. Authors are encouraged to consider the following when preparing their submissions:

• Learning/education related: The submission should describe work that addresses learning/academic analytics, either at an educational institution or in an area (such as corporate training, health care or informal learning) where the goal is to improve the learning environment or professional learning outcomes.
• Implementation track record: The project should have been used by an institution or have been deployed in a learning site. There are no hard guidelines about user numbers or how long the project has been running.
• Stakeholder involvement: All submissions should include information collected from people who have used the tool or initiative in a learning environment (such as faculty, students, administrators and trainees).
• Overall quality, including potential interest and value for LAK attendees: Project success (or failure) accounts are encouraged, but a focus must be placed on what the community of other practitioners and researchers can gain from learning about the work. What was successful (and why)? What was unsuccessful (and why)?
• No sales pitches: While submissions from commercial suppliers are welcomed, reviewers will not accept overt (or covert) sales pitches. Reviewers will look for evidence that the presentation will take into account challenges faced, problems that have arisen, and/or user feedback that needs to be addressed. 

There is a single submission type for the PaC-LA track that has a special format emphasizing practical aspects of project implementations rather than a research paper format: 

PaC-LA Presentation Reports (2-4 page document, using the SoLAR companion proceedings template) should include accounts and findings that stem from practical experience in implementing learning analytics projects. The report gives PaC-LA authors a channel for sharing: the background of why the a) project was implemented and/or b) product was developed; data and the design process that drove the development of the project or product; details about how the project or product has been implemented in a real-world environment; findings from the project or product implementation and its significance, including a reflection on the importance of the reported initiatives in your paper to the broader LAK community. See bulleted lists above for more detailed ideas on useful elements to include and consider in crafting a submission.

All accepted submissions to the PaC-LA track will be published in the LAK23 Companion Proceedings and archived on the SoLAR website.

 

3. POSTERS AND DEMOS

• Posters (3 pages, SoLAR companion proceedings template) represent i) a concise report of recent findings or other types of innovative work not ready to be submitted as a full or short research paper or ii) a description of a practical learning analytics project implementation which may not be ready to be presented as a practitioner report. Poster presentations are part of the LAK Poster & Demo session, and authors are given a physical board or virtual space to present and discuss their projects with delegates. 
• Interactive demos (200 words abstract in SoLAR companion proceedings template + 5 min video) provide opportunities to showcase interactive learning analytics tools. Interactive demonstrations are part of the LAK Poster & Demo session, and presenters are given a (virtual) space to demonstrate their latest learning analytics projects, tools, and systems. Demos should be used to communicate innovative user interface designs, visualisations, or other novel functionality that tackles a real user problem. Tools may be prototypes in an early stage of development or relatively mature products. In whichever stage, tools should have been field-tested with an authentic use case and provide some results and feedback. Submissions for conceptual products or for products that have not been used by instructors and/or students are unlikely to be accepted.

 

4. PRE-CONFERENCE EVENT TRACK

The focus of pre-conference events is on providing space for new and emerging ideas in learning analytics and their further development. Events can have either research or practical focus and can be structured in the way which best serves their particular purpose.

The types of submissions for the pre-conference event track are:

• Workshops (4 pages, SoLAR companion proceedings template) provide an efficient forum for community building, sharing of perspectives, training, and idea generation for specific and emerging research topics or viewpoints. Successful proposals should be explicit regarding the kind of activities participants should expect, for example from interactive/generative participatory sessions to mini-conference or symposium sessions.
• Tutorials (4 pages, SoLAR companion proceedings template) aim to educate stakeholders on a specific learning analytics topic and/or stakeholder perspective. Proposals should be clear about what the need is for particular knowledge, target audience and their prior knowledge, and the intended learning outcomes.

LAK23 will use a double-blind peer review process for all submissions except demos and the doctoral consortium (which each require elements that prevent blinding). To continue to strengthen the review process for both authors and reviewers LAK23 will have a rebuttal phase for full and short research papers in which authors will be given five days to respond to remarks and comments raised by reviewers in a maximum of 500 words. Rebuttals are optional, and there is no requirement to respond. Authors should keep in mind that papers are being evaluated as submitted and thus, responses should not propose new results or restructuring of the presentation. Therefore, rebuttals should focus on answering specific questions raised by reviewers (if any) and providing clarifications and justifications to reviewers. Meta-reviewers, senior members of the research community, make final recommendations for paper acceptance or rejection with justification to the program committee chairs after the rebuttal phase is concluded. Acceptance decisions are ultimately taken by the program committee chairs based on all available information from the review process in combination with the constraints of the allowable space in the conference program.

Finally, please note that the conference timeline allows for rejected submissions to be re-submitted in revised form as poster, demo and workshop papers. 

Accepted full and short research papers will be included in the LAK23 conference proceedings published and archived by ACM. Other types of submissions (posters, demos, workshops, tutorials, practitioner reports and doctoral consortium) will be included in the open access LAK companion proceedings, published on SoLAR’s website. Please note at least one of the authors of each accepted submission must register for the conference by the Early Bird deadline in order for the paper to be included in the ACM or LAK Companion Proceedings.