LASI Abstracts

Monday 9:55 – 10:40

Plenary: Data Mining and Intelligent Tutors – John Behrens

ITSs have provided a major source of data for educational data mining. Researchers have used such data to explore questions of modeling and prediction of student performance and learning, ideal decomposition of knowledge, metacognitive learning behaviors, motivation, and affect. We will illustrate these uses along with some of the many data mining techniques.

Monday 11:30 – 12:30

Panel: Ethics, Privacy, Access
Chair: Grace Lynch

Panellists:
Abelardo Pardo
Patricia Hammar
Grace Lynch

Tuesday 2:00 – 4:00

1. Machine Learning – Ryan Baker

2. Hacking Educational Data: Open Tools for Techie-Educators – Dragan Gasevic

Complementing many of the formally defined research projects and product development activities associated with the recent upsurge in activity around the notion of learning analytics, a hacker ethic of quick win (or at least, quick to try) activity is also flourishing around educational datasets, as well as datasets created informally around education related activity on open social networks.

In this workshop, I will review a variety of tools and techniques for capturing, organising, wrangling and analysing education related datasets, showing how we can appropriate freely available open IT tools to support the rapid trialling and prototyping of learning analytics related ideas that we might ordinarily expect would require developer expertise. The aim is to identify tools and data grabbing techniques which allow a rapid exploration of the space of what’s possible, without the requirement to spend months, weeks, days, or even hours in preliminary application development activity.

The workshop will offer an opportunity to see – and use – some of the tools that can provide the data enthusiast with heretofore unimaginable powers, or at least, the ability to grab and tidy data, and then generate interesting, novel, and rich data visualisations, without the need to hire a developer first. Tools covered may include, but surely will not be limited to: Gephi network visualisations, Shiny R applications, Google spreadsheet powered social media analyses and OpenRefine data gathering and reshaping techniques.

3. Assessment Regimes & Analytics – John Behrens

4. Dispositional Learning Analytics – Simon Buckingham Shum (Open U.)

This LASI workshop does not assume any prior knowledge of learning dispositions, although background papers and resources are provided in advance for those who wish. The goal is to forge new connections between people already working in the field, and spark new conversations for the rest of LASI and beyond, hopefully, growing into new initiatives. Goals: • introduce research on how students’ and educators’ dispositions to learning can shape outcomes describe software tools grounded in that research, which enable the techniques to be deployed at scale • review the impact of such tools on learners and educators show how, as a by-product of web delivery, one can build quality datasets • describe how this data is amenable not only to traditional educational analysis, but explore the prospects for using machine learning and big data approaches • consider user interfaces which enable different stakeholders (eg. learners; educators; researchers) to interact with that data coherently • looking to the future, what ideas can we brainstorm for the tough questions this field faces, e.g. Can we develop dispositional analytics based on learners’ activity traces (rather than self-report)? Can we move from analytics, to recommendation engines able to make timely interventions for educators, or guidance to learners?

Wednesday 2:00 – 4:00

1. Building Courses – George Siemens

2. Social Learning Analytics Workshop – Associate Professor Shane Dawson, University of South Australia, Australia

Much of the learning analytics research to date has adopted grades or assessment items as a proxy for learning. While assessment scores and grades provide easy access to a performance measure it does not necessarily provide a measure of the process of learning. That is, an indication of the types of behaviours and patterns a learner undertakes in association with their peers. The importance of social learning to education has now been well established. The growing popularity in the education literature surrounding concepts such as social learning, social networks, social presence, and social architecture testify to the importance of the relational nature and purpose of learning. This workshop seeks to unpack social network and discourse analysis as dimensions of social learning analytics. The workshop will cover contemporary learning theory and its relationship with analytics methodologies. Participants will examine the learning spaces of a new building and work through the methodologies for assessing the impact of the design space on social learning. This will scenario will be increasingly problematized to engage participants in thinking about alternate virtual and blended spaces.

3. Multimodal Learning Analytics

4. Analytics Startups – Taylor Martin

Thursday 11:30 – 12:30

Analytics for 21st Century Skills – Caroline Haythornthwaite

The session will open discussion around analytic literacy, tools and technologies for 21st century learners and learning. Panel members will highlight relevant information, trends, research questions, and policy issues on the topic, followed by open discussion on challenges relating to analytics and 21st century skills. The panel will focus on questions such as:
· What analytic literacies do people need for the 21st century?
· How can analytic tools/technologies help people become literate for the 21st century?
· How can analytic tools/technologies help in teaching people to become literate in skills needed for the 21st century?

Thursday 2:00 – 4:00

1. Visualization and data presentation – Dragan Gasevic

Learning analytics is making it possible to transform learner’s and teacher’s digital footprints and their digital artefacts into models of learners and learning processes.

To make such information really valuable, we need interfaces that enable people to make effective use of that data. A central challenge for this field is to establish a set of principles and tools for ViziLA, vizualisation interfaces for learning analytics. This interactive presentation will present a set of such ViziLA principles and cases studies from diverse examples of at two major levels: for learners, their peers, their mentors and teachers to gain insights about individual, group and classroom learning; and at an institutional level for curriculum custodians and administrators. Participants will actively engage in studying these ViziLA tools, as well as their own, by analyzing using a set of proposed principles for design of VizLA. An outcome of the session will be an assessment of the tools and a critique of the principles

2. Approaches to Data Sharing: Data Shop – Ken Koedinger / Ryan Baker

3. LSA and NLP in education – John Behrens

Friday 11:30 – 12:30

Educating the Educational Data Scientist / Learning Analyst – John Behrens

Founding Members
Previous Image
Next Image

info heading

info content