Workshop and Tutorial Overview

Organizers: Daniele Di Mitri, Adam Cooper, Kirsty Kitto, Gábor Kismihók, Stefan T. Mol, Niall Sclater, Jan Schneider and Alan Berg

Venue: LSA 101

Abstract: Welcome to the Fifth Learning Analytics Hackathon (LAK Hackathon). In this event, we focus on improving the learner's experience of through trusted and inclusive learning analytics across spaces. We want to give visibility to new LA tools, standards and infrastructures. If you have a research question, data set, idea or a problem bring it to the hackathon. We encourage joining the event no matter what your background. We aim to address the science-practice divide, by having practitioners and researchers working in multidisciplinary teams towards common objectives. To ensure continuity with the whole LAK community, this year we allow also one-day participation to the LAK Hackathon, to allow people interested in parallel pre-conference workshops also to join and bring their research questions. 

For more, visit http://lakhackathon.com 

This workshop has already reached its maximum capacity.

Organizers: Alina Von Davier, Michael Yudelson, Kenneth Koedinger, Steven Ritter and Peter Brusilovsky

Venue: Senita C

Abstract: The workshop will focus on the conceptual frameworks, algorithms, and examples of performing operational and post hoc analytics for supporting learning and assessment. Modern systems of computer-supported education have matured enough so that there is a nascent need for starting a conversation on forming a conceptual schema covering a wide array of learning analytical procedures embedded into the existing and future products at various stages of the educational support process from the operational recommendation and adaptation to the offline investigation. These approaches, are often grounded in compartmentalized cognitive and psychometric theories and would greatly benefit from a joint discussion to address the issues education is facing today.

For more, visit http://actnext.info/LASSPLAS19/index4.html

Organizers: Srecko Joksimovic, George Siemens, Shane Dawson and Vitomir Kovanovic

Venue: LSE 204

Abstract: Given the rapid changes confronting society, important questions remain regarding how theory influence the work of researchers. Within learning and knowledge building literature, cognitivism and constructivism have remained the primary theories. Connectivism learning theory has more recently been posited and has been heavily cited over the past 15 years. Unfortunately, it has not been explored empirically. In this full day workshop, we utilize learning analytics methods and techniques to operationalize a research agenda. Specifically, we will explore the core assertions of connectivism with the goal of fostering a research community.

For more, visit http://connectivism.net/ 

Organizers: Rwitajit Majumdar and Hiroaki Ogata

Venue: LSE B52

Abstract: The multi-disciplinary research approach of Learning Analytics (LA) has provided methods to understand learning logs collected during varied teaching-learning activities and potentially enrich such experiences. This workshop aims to explore the frontiers of how technology can help to extract evidence of effective teachinglearning practices by applying the knowledge base of LA and developing novel techniques. It focuses discussions on realizing a technology-enhanced evidencebased education and learning (TEEL) system. We invite research articles conceptualizing foundations, methodologies and utility of TEEL system. Further, we plan to have a focus group activity to validate an initial technical proposal of Learning Evidence Analytics Framework (LEAF) and drawing a research road-map of log data-driven evidence-based education system.

For more, visit https://sites.google.com/view/teel-workshop/

Organizers: Daniel Spikol, Daniele Di Mitri, Vanessa Echeverria, Roberto Martinez-Maldonado, Mutlu Cukurova, Luis P. Prieto, María Jesús Rodríguez-Triana, Xavier Ochoa, Marcelo Worsley and Michail Giannakos

Venue: LSE 244

Abstract: Students’ learning is ubiquitous. It happens wherever the learner is rather than being constrained to a specific physical or digital learning space (e.g. the classroom or the institutional LMS respectively). A critical question is: how to integrate and coordinate learning analytics to provide continued support for learning across physical and digital spaces? CrossMMLA is the successor to the Learning Analytics Across Spaces (CrossLAK) and MultiModal Learning Analytics (MMLA) series of workshops that were merged in 2017 after successful cross-pollination between the two communities. Although it may be said that CrossLAK and MMLA perspectives follow different philosophical and practical approaches, they both share a common aim. This aim is to develop strong research foundations for the analytics of learning through different modalities in different learning contexts.  Also, at LAK’19, the CrossMMLA workshop will run in conjunction with the MMLA challenge at LAKHackathon as complementary workshops. While CrossMMLA aims at a more theoretical confrontation among MMLA researchers, the LAKHackathon offers the space to share practical MMLA challenges, to show early-stage prototypes or share MMLA datasets. To strengthen the linkage for CrossMMLA with the other workshops and research communities, we encourage therefore participation in both CrossMMLA and LAKHackathon workshops.

For more, visit http://crossmmla.org 

Organizers: Antonette Shibani, Ming Liu, Christian Rapp and Simon Knight

Venue: LSA 109

Abstract: Writing analytics as a field is growing in terms of the tools and technologies developed to support student writing, methods to collect and analyze writing data, and the embedding of tools in pedagogical contexts to make them relevant for learning. This workshop will facilitate discussion on recent writing analytics research by researchers, writing tool developers, theorists and practitioners to map the current state of the field, identify issues and develop future directions for advances in writing analytics.

For more, visit http://wa.utscic.edu.au/events/lak19-workshop-on-advances-in-writing-analytics-mapping-the-state-of-the-field/

Organizers: Simon Buckingham Shum, Mutlu Cukurova, Mingyu Feng, Andrew Krumm, Jojo Manai

Venue: Senita B

Abstract: The LAK conference has always welcomed work from the K-12 school sector, but to date, has been dominated by higher education. To rebalance this, LAK18 ran a successful inaugural K-12 workshop. Over 60 people attended, the vast majority being teachers and analysts from the schools sector, plus ed-tech companies, most of them first timers at LAK. While being expert with conventional school data, most school staff were just beginning to consider the potential of data science approaches, and even fewer had experience with analytical techniques that use the new forms of digital data generated by student activity in digital learning environments. Building on this event, SoLAR is keen to forge stronger links with the K-12 analytics community, so we are delighted to announce this workshop for LAK19.

You are warmly invited to join us to learn from leading researchers and practitioners in the field, and to share your own experiences, insights, and questions. The target audience for this workshop includes school leaders, teachers, and researchers.

For more, visit https://lak19.solaresearch.org/2nd-international-workshop-on-learning-analytics-in-schools/ 

Organizers: Bor-Chen Kuo, Chen-Huei Liao, Kai-Chih Pai, Chia-Hua Lin, Xiangen Hu, Zhiqiang Cai and Arthur C. Graesser

Venue: LSE B04

Abstract: Conversational Intelligent tutoring system is a class of Adaptive Instructional Systems that are among the most studied and efficiently implemented in the last 20 years. This tutorial will introduce the most successful example C-ITS called AutoTutor and focuses on the authoring of AutoTutor lessons and Data analysis process of Tutoring data. Authoring of AutoTutor lessons include a) implementing discourse strategies in AutoTutor dialogues and trialogues, b) creating conversation elements (such as media elements); c) conversation rules, and d) using existing well-made authoring templates. Data analysis process of tutoring data include applying learning analytics methods, such as Bayesian Knowledge Tracing (BKT), Learning Factors Analysis (LFA), Intervention-Bayesian Knowledge Tracing (Intervention-BKT), Cognitive Diagnostic Model,…etc., to leverage the sequences of observations from student-ITS interaction log files to continually update the estimate of student latent knowledge.

For more, visit http://lak19.x-in-y.com/ 

Organizers: Tom Broos, Dragan Gašević, Abelardo Pardo, Hendrik Drachsler, Rafael Ferreira, Katrien Verbert and Tinne De Laet

Venue: LSA 119

Abstract: Research about Learning Analytics has increasingly gained attention, as demonstrated by the geographic and substantive scope of LAK. However, as the domain of LA is maturing, the connection of research to long-term applicability is relatively underdeveloped. This may hinder further investment of policy makers and administrators. The goal of our half-day workshop is to explore and discuss the scalability and sustainability of existing and proposed solutions, and to initiate the creation of a framework of strategies available to researchers and practitioners.

For more, visit http://saslas.org

Organizers: Danielle Hagood and Robert Bodily

Venue: LSE 250

Abstract: This workshop addresses critical components of interdisciplinary collaboration in learning analytics: how you think, how your collaborators think, and your collective interactions. Workshop time will be split between presentations and structured collaborations, allowing participants gain both knowledge and skills needed to collaborate across disciplines in learning analytics. We anticipate these topics are widely applicable, though this workshop is tailored to new scholars and graduate students. Talks will present key perspectives and ideas from two domains: social science and computational science. The methods and mindsets from these two fields will be discussed, in exploration of the barriers and channels to collaboration. Finally, activities applying interdisciplinary theory will create hands-on collaboration opportunities.

For more, visit https://sites.google.com/view/interdisciplinary-analytics/home 

This workshop has been cancelled. Apologies for the inconvenience.

Organizers: Ouajdi Manai, Hiroyuki Yamada and Susan Haynes

Abstract: We confront a growing chasm between rising aspirations for our educational systems and what schools can routinely accomplish. Although educators at the classroom, school, and district levels are expending significant energy generating and testing promising interventions, we often observe a failure to scale up research-based knowledge across varied contexts. This interactive half-day workshop presents a way to move from trying to get better to getting good at getting better. We will introduce an improvement science approach that focuses on learning-by-doing to make progress toward a specific aim on a shared problem of practice by leveraging the power of networked communities. We will present how to apply the six core principles of improvement and organize improvement work through an online technology called NILS™ (Networked Improvement Learning and Support platform), emphasizing that (a) knowledge about the innovation itself and associated knowhow around effective implementation flow through the interpersonal relationships between different actors; (b) attending to variation in performance and seeing the system that produces the current outcomes help us to identify areas for improvement. Utilizing NILS, participants will engage in structured activities and data exercises, learn how to identify areas for improvement from data, and create a driver diagram as a theory of practice improvement.

For more, visit https://sites.google.com/carnegiehub.org/tempearizonalak19workshop/home

Organizers: James Cunningham and William Morgan

Venue: LSE 232

Abstract: This workshop is designed to be an introduction to R for learning analytics for researchers who have no experience using a programming language to do data analysis. This will not be a class to teach R, rather it will be an opportunity for attendees to learn about R and its capabilities in a learning analytics context using a hands-on approach. Attendees will learn how to install R and RStudio on their own computers and will be able to watch demonstrations of R being used for data exploration, visualization, and publication. They will then work in small groups with prewritten scripts and synthetic datasets to learn what it feels like to use R on their own computer. They will see first-hand the power of using R and will be informed about resources for learning R and building their own programming skills.

For more, visit https://sites.google.com/asu.edu/tryrlak19/home

Organizers: Christopher Brooks, Dan Davis, Nia Dowell, Joshua Gardner, Timothy Necamp, Oleksandra Poquet, Rene Kizilcec and Joseph Williams

Venue: LSE 232

Abstract: The path to improving educational efficacy, equity, and experience is paved with questions of cause and effect. This workshop focuses on the most reliable approach for estimating causal effects: randomized experiments. The workshop’s aim is to promote and strengthen the use of online experiments within the learning analytics community. To this end, we will review best practices for the design, implementation, and analysis of experiments in educational settings and learn about recent innovations in the field.

For more, visit http://replicate.education/lak-18-workshop/

Organizers: Lishan Zhang, Baoping Li, Yigal Rosen, Kristin Stoeffler and Shengquan Yu

Venue: LSE 505

Abstract: Solving dynamic and ill-structured problem is one of the most important skills for the 21st century. In addition, people often need to collaborate to solve problems together in real-life. Therefore, it is important to establish the assessments for evaluating both individual and collaborative problem solving ability for K12 students to ensure that the students are ready for dealing with real-life problems when they leave schools. To achieve this goal, learning scientists have designed various simulations to implement interactive and dynamic assessments. On the other hand, some techniques of learning analytics such as regression model, neural network, and hidden markov model have been used to analyze problem solving procedures. The workshop aims for further exploring how learning analytics could facilitate both of individual and collaborative problem-solving assessment through presentation, interactive event and roundtable discussion among the researchers with different backgrounds but the same interest.

For more, visit http://aic-fe.bnu.edu.cn/en/events/upevents/was/56584.html 

Organizers: Yoav Bergner, Geraldine Gray and Charles Lang

Venue: LSE 250

Abstract: Learning analytics is an interdisciplinary and inclusive field, a fact which makes the establishment of methodological norms both challenging and important. Building on the success of the LAK17 and LAK18 workshops on methodology, this community-building workshop intends to convene methodology-focused researchers to discuss new and established approaches and co-develop guidelines to help move the field forward with quality and rigor.

For more, visit http://www.lakmethlab.org/

Organizers: Nirmal Patel, Derek Lomas and Collin Sellman

Venue: LSA 119

Abstract: The primary goal of this workshop is to produce open source data visualizations that help communicate results of learning analytics (LA) research to educators. Instructors are increasing their use of data to drive instruction, and various results of LA research are useful towards this end. However, the actionable insights discovered by the LA community are often inaccessible to educators due to their relative complexity. In this case, it is possible to use data visualization to communicate actionable insights about learners to optimize instruction effectively. Visualizations of learner data can make it easy for teachers and other education stakeholders to take evidence-based action. Organizers of the workshop intend to invite authors to describe and implement educational data visualizations that can aid decision making in online and offline classrooms. The workshop will result in a gallery of open source educational data visualizations that can be freely used by the LA community.

For more, visit https://sites.google.com/view/edviz-2019/home

Organizers: Daniele Di Mitri, Adam Cooper, Kirsty Kitto, Gábor Kismihók, Stefan T. Mol, Niall Sclater, Jan Schneider and Alan Berg

Venue: LSA 101

Abstract: Welcome to the Fifth Learning Analytics Hackathon (LAK Hackathon). In this event, we focus on improving the learner's experience of through trusted and inclusive learning analytics across spaces. We want to give visibility to new LA tools, standards and infrastructures. If you have a research question, data set, idea or a problem bring it to the hackathon. We encourage joining the event no matter what your background. We aim to address the science-practice divide, by having practitioners and researchers working in multidisciplinary teams towards common objectives. To ensure continuity with the whole LAK community, this year we allow also one-day participation to the LAK Hackathon, to allow people interested in parallel pre-conference workshops also to join and bring their research questions. 

For more, visit http://lakhackathon.com 

Organizers: George Siemens, Katy Borner, Ryan Baker, Kylie Peppler, Michael Richey and Shane Dawson

Venue: Memorial Union – Pinal

Abstract: This full day workshop will engage researchers and practitioners in the process of solving complex problems that require collaboration between specialized knowledge domains. The National Science Foundation details the need for convergence to “stimulate innovation and discovery”, requiring engagement from “academic, government, and industry stakeholders”. Our workshop focuses on the processes involved in this type of complex knowledge work by incorporating theory and methods from the learning analytics community. Specifically, we focus on methods that evaluate group development, detail social network formation, visualize large data sets, and describe the evolution of ideas and creativity through process mining. Aligning with the LAK19 theme of learner success and inclusion, this workshop will evaluate how convergence work is experienced in different regions, cultures, and under-represented populations.

For more, visit http://knowledgeconvergence.org/

Organizers: Katrien Verbert, Robin De Croon, Tinne De Laet, Tom Broos, Xavier Ochoa, Robert Bodily, Judy Kay, Hendrik Drachsler and Cristina Conati

Venue: Memorial Union – Gila

Abstract: One of the most visible tools used in Learning Analytics is the dashboard. These dashboards use a wide range of visualization techniques to explore and understand relevant user traces that are collected in various (online) environments and to improve (human) learning. The design and evaluation of learning analytics dashboards within the educational practice does not receive enough research attention. The goal of our workshop is to build a strong research capacity around visual approaches to learning analytics. The longer-term goal is to improve the quality of learning analytics research that relies on information visualization techniques. This proposal describes the goal and activities of the VISLA 2019 workshop on Visual Approaches to Learning Analytics.

For more, visit http://augment.cs.kuleuven.be/visla19

Organizers: Brendan Flanagan, Atsushi Shimada, Stephen Yang, Bae-Ling Chen, Yang-Chia Shih and Hiroaki Ogata

Venue: LSA 109

Abstract: 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, such as: teachers, students and researchers. In this workshop, participants will be offered a chance to analyze the event logs from three different universities datasets with information on over 1000 students reading behaviors. Additional information on lecture schedules will also enable the analysis of learning context for further insights into the preview, in-class, and review reading strategies that learners employ. Finally, workshop contributors will be encouraged to implement their research results as a feature of an open LA dashboard.

For more, visit https://sites.google.com/view/lak19datachallenge

Organizers: David Azcona, Yancy Vance Paredes, Sharon Hsiao and Thomas Price

Venue: Memorial Union – Apache

Abstract: The objective of this workshop is to facilitate a discussion among our research community around Artificial Intelligence (AI) in Computer Science Education. The workshop is meant to be an interdisciplinary event. Researchers, faculty and students are encouraged to share their data mining approaches, methodologies and experiences where AI is transforming the way students learn Computer Science (CS) skills.

For more, visit https://sites.google.com/asu.edu/csedm-ws-lak-2019/ 

This workshop has been cancelled. Apologies for the inconvenience.

Organizer: Pablo Munguia

Abstract: Learning analytics is a young field and beyond its research space its uptake has been slow across academics. Often, top down strategies are not easy adopted or focus on metrics that may not align across all disciplines in a university while bottom up approaches, while well focused have difficulty increasing their reach and capacity. Ultimately, designing a professional development plan in a university is not enough at best, and incorrect at worst. This workshop focuses on developing strategies on how create interest with academics and other units to help improve the student experience. The workshop is split into two half-day sections. The first focuses on the components of that strategy such as the data sets needed, the visualization tools and the analytical solutions, and how to combine these to ensure they can cater to different disciplines. The second focuses on developing tactics for increasing engagement with learning analytics solutions across a university or large unit. The workshops will be run as a blended course where participants are encountering the material first hand, and their reflections provide solutions for designing the engagement strategies in their respective institutions.

For more, visit http://www.rmit.edu.au/lak-19

Venue: Memorial Union – Graham

For more, visit https://lak19.solaresearch.org/doctoral-consortium/

Organizers: Alfred Essa, Shirin Mojarad and Neil Zimmerman

Venue: Memorial Union – Coconino

Abstract: The hands-on tutorial will provide a rigorous introduction to python for learning analytics practitioners. The intensive tutorial consists of five parts: a) basic and intermediate python; b) statistics and visualization; c) machine learning d) causal inferencing and d) deep learning. The tutorial will be motivated throughout by educational datasets and examples. The aim of the tutorial is to provide a thorough introduction to computation and statistical methodologies in modern learning analytics.

For more, visit https://github.com/alfredessa/lak19 

Organizers: Kenneth Holstein and Shayan Doroudi

Venue: Memorial Union – Yuma

Abstract: The potential for data-driven algorithmic systems to amplify existing social inequities, or create new ones, is receiving increasing popular and academic attention. A surge of recent work, across multiple researcher and practitioner communities, has focused on the development of design strategies and algorithmic methods to monitor and mitigate bias in such systems. Yet relatively little of this work has addressed the unique challenges raised in the design, development, and real-world deployment of learning analytics systems. This interactive workshop aims to provide a venue for researcher and practitioners to share work-in-progress related to fairness and equity in the design of learning analytics and to develop new research and design collaborations around these topics. The workshop will begin with a brief overview of the state-of-the-art in fair AI and machine learning, followed by presentations of accepted contributions and a series of visioning and design exercises. A key outcome of the workshop will be a research agenda for the LAK community, around fairness and equity. Workshop participants will collaboratively construct this agenda through a sequence of small- and whole-group design activities. At the end of the workshop, participating researchers and practitioners will then explore opportunities for collaboration around specific research and design thrusts within this agenda.

For more, visit https://tinyurl.com/FairLAK

Organizers: Elle Yuan Wang, Maria Ofelia San Pedro, Srecko Joksimovic and Jason Way

Venue: LSE B52

Abstract: The importance of fostering and measuring non-cognitive or social and emotional learning (SEL) skills, commonly viewed as critical personal attributes necessary for success in classroom, labor market, and life in general, has been widely recognized. Most existing SEL skill research connect with “academic excellence” at the individual level, as the key or primary outcome measure, this workshop proposes to incorporate “inclusive excellence” at the community level in SEL research. Particularly, we call on SEL research that address challenges that non-traditional adult learners face or those than can promote diversity and inclusion. This workshop aims to promote diversity and inclusion in the field of learning analytics and knowledge through the lens of SEL research. Organizational plans are also included and explained.

For more, visit http://noncog-lak.info/

Organizers: Christine Armatas, Ada Tse and Chun Sang Chan

Venue: LSE B04

Abstract: The large amounts of data recorded about student behavior in a learning management system (LMS) is only useful if it can be accessed, analysed and interpreted easily and on demand. In this workshop, participants will be introduced to an easy to use Excel tool developed specifically for teachers to understand their students’ online activity and enhance their teaching. Activities during the workshop will allow participants to use the tool to conduct analysis of an LMS data set to produce tables, figures and visualizations about student engagement in the LMS. Case-studies will be explored to demonstrate how the indicators provided in the tool are informative and actionable for enhancing their online teaching. The analyses used in the case-studies will focus on helping students be more successful while studying, as well as how to use analysis of LMS data to enhance learning and the student experience for future course delivery. The tool will be made available for participants after the workshop, giving them autonomy in accessing and analyzing students’ online activity which they can use for evidence-based enhancement of their teaching.

For more, visit https://www.polyu.edu.hk/edc/lak2019/

Organizers: Andrew Krumm, Jeremy Roschelle and Particia Schank

Venue: LSE 204

Abstract: This workshop will provide participants with the opportunity to develop skills needed to lead and support data-intensive research-practice partnerships. Using insights gleaned from multiple cases, workshop participants will engage in whole- and small-group activities around setting up a partnership and conducting collaborative data analyses using cloud-based tools that have been integrated into a free and open source set of services referred to as TeamSpace. The combination of a grounded data-intensive improvement process and an easy-to-launch set of analysis tools, will put participants on a path toward organizing more and more of their learning analytics work as a “team sport.”

For more, visit https://circlcenter.org/events/teamspace-lak19/

Organizers: Nancy Law, Linda Corrin, Sandra Milligan and Ulla Ringtved

Venue: LSA 119

Abstract: The 4th Annual DesignLAK Workshop focuses on how learning design can be used to inform validity of the measures used for assessment analytics. It has long been acknowledged that the validity of measures for assessment is one of the most important, but complex, concepts in education (Black & Wiliam, 2014; Newton & Baird, 2016). The field of learning analytics, and more specifically assessment analytics, is opening up new ways to collect data that can be used to measure student learning. However, with this increase comes concern about whether such measures are valid in helping us to assess student knowledge, competencies and/or skills. This half-day, interactive workshop aims to explore how learning design can be used to inform how we evaluate validity of assessment measures. Participants will have an opportunity to engage with key issues through expert presentations, discussion and assessment design scenarios. The outcome of the workshop will include the generation of key considerations for addressing validity in learning analytics with reference to learning design.

For more, visit https://sites.google.com/site/designlak19/

Organizers: Charles Lang, Stephanie Teasley and John Stamper

Venue: LSE 232

Abstract: Learning Analytics courses and degree programs both on- and offline have begun to proliferate over the last five years. Building on the success and collaboration of the LAK18 curriculum workshop we plan to work through specific best practices that relate to the conference theme of using learning analytics to promote inclusion and success. This will include 1.) Attracting more diverse students and faculty to learning analytics programs 2.) Developing programming that is attuned to a more diverse audience, and 3.) Development of a repository of learning analytics classroom activities. We also again hope to foster synergy between instructors that can benefit the field as a whole.

For more, visit http://bit.ly/BLAC2019 

Organizers: Abelardo Pardo, Shane Dawson, Dragan Gasevic and George Siemens

Venue: LSE 244

Abstract: Although we have seen significant progress in the wealth of data captured in learning environments and the tools and techniques to deploy learning analytics methods, the true impact on the overall quality of a learning experience needs further study. We posit that the provision of personalized feedback for large student cohorts offers an ideal context to connect the variety of data sources currently emerging in institutions, the connection with a learning design, and the specifics to connect derived knowledge with tangible student support actions. The half-day session is targeted to researchers and practitioners interested on the use of data to adapt their design to provide personalized support to learners. Attendees will be offered the possibility of exploring this context using the open-source tool OnTask with a synthetically generated data set. Additionally, the session includes a discussion on how the proposed paradigm is being used in used in various educational institutions throughout the world.

For more, visit http://bit.ly/LAK19ONTASK

Organizers: Kenneth Koedinger, John Stamper and Paulo Carvalho

Venue: LSE 204

Abstract: This workshop will explore LearnSphere, an NSF-funded, community-based repository that facilitates sharing of educational data and analytic methods. The workshop organizers will discuss the unique research benefits that LearnSphere affords. In particular, we will focus on Tigris, a workflow tool within LearnSphere that helps researchers share analytic methods and computational models. Authors of accepted workshop papers will integrate their analytic methods or models into LearnSphere’s Tigris in advance of the workshop, and these methods will be made accessible to all workshop attendees. We will learn about these different analytic methods during the workshop and spend hands-on time applying them to a variety of educational datasets available in LearnSphere’s DataShop. Finally, we will discuss the bottlenecks that remain, and brainstorm potential solutions, in openly sharing analytic methods through a central infrastructure like LearnSphere. Our ultimate goal is to create the building blocks to allow groups of researchers to integrate their data with other researchers in order to advance the learning sciences as harnessing and sharing big data has done for other fields.

For more, visit http://learnsphere.org/workshops.html

Organisers: James Folkestad, George Rehrey, Linda Shepard, Dennis Groth and Matthew Hickey

Venue: LSE 232

Abstract: This half-day interactive workshop responds to an on-going need to thoughtfully and intentionally consider, and sometimes reconsider, the ethical implications of the rapidly advancing field of Learning Analytics (LA). The pioneering work of other scholars will provide the starting point for our conversations, including Drachsler & Greller’s (2016) DELICATE checklist Hoel and Chen’s (2018) EP4LA Toolkit, and Sclater’s (2014) Code of Practice. Case studies and possible dilemmas (Willis, Slade, & Prinsloo, 2016), along with previous institutional efforts (Colorado State University) will also frame our discussions. During the workshop, participants will develop strategies for creating a sustainable and inclusive community to advance principle-based LA practices on their campuses. By completing an Action Plan Worksheet, participants will consider the alignment of institutional goals with LA, the value of including key stakeholders in ethical discourse, and the development of a flexible framework for reviewing emerging LA practices and activities. They will also reflect upon how the development of local communities dedicated to ethical discourse can contribute to, and benefit from, joining a broader international Community of Transformation across higher education.

For more, visit https://alt.colostate.edu/lak19-workshop-ethical-discourse/ 

Organizers: Lorenzo Vigentini, Danny Y.T. Liu and Lisa Lim

Venue: LSA 119

Abstract: After a successful workshop at LAK’18, in which presenters explored tools used to provide feedback at scale, this workshop shifts the attention to data-driven approaches to support the provision of feedback and the students, especially considering how they perceive the feedback and what they do with the feedback received. The workshop aims to bring together scholars and practitioners to find a common ground for showcasing interesting examples of effective feedback and explore what and how data can be used to improve the process and richness of feedback for both learners and educators. Key outcomes will be a better understanding of approaches and existing cases of good practice which will foster discussion and collaboration in the LA community.

For more, visit https://sites.google.com/view/lak19workshop/ 

Organizer: Gu Xiaoqing

Venue: LSE 244

Abstract: The workshop comprises three stages. Stage one features presentations on data intelligence in three different levels. In stage two, group discussions on the presentations ensue with the aim of understanding by invoking the broader perspectives of researchers from the audience. The third stage is to seek consensus on what we have learned and what we can do further to pursue data intelligence in education.

For more, visit https://sites.google.com/view/lak19-workshop-exploiting/overview

Organizer: Erkan Er

Venue: Memorial Union – Yuma

Abstract: The existing predictive research has been mostly based on post-hoc techniques (e.g., cross validation). These techniques cannot be applied in real-world practice as they are built only after the target action occurs in the context (e.g., after students dropout). As a result, the research thus far has had a very limited impact on pedagogy. Building on past machine learning workshops and tutorials in LAK conferences, this tutorial session will introduce the machine learning approaches for creating actionable predictions (i.e., in-situ learning and transferring across courses) that can offer many utilities for designing real-world interventions. The participants will be guided through several hands-on examples to practice the use of these approaches in several real-world scenarios. Python Scikit-Learn will be used to implement the practice examples. At the end of the activity, the participants will reflect on their experience and share their opinions on the use of in-situ learning and transfer across courses techniques in their own research. This session will increase the awareness of LA researchers and practitioners about the ways of building actionable predictive models and will inspire future use of these approaches in research and practice.

For more, visit https://feelthedata.wordpress.com/