OLDaily

Explainable Artificial Intelligence in education
HassanKhosravi, et al., Computers and Education: Artificial Intelligence, 2022/05/17

This paper introduces "a framework, referred to as XAI-ED, that considers six key aspects in relation to explainability for studying, designing and developing educational AI tools" where explainability is presented in terms of fairness, accountability, transparency, and ethics (FATE). It then illustrates the application of XAI-ED in four case studies of adaptive educational systems (AESs) that use data about students and learning processes. The framework is fairly straightforward, describing several facets of each of the six aspects, but the real value of the paper is in the case studies, where we get a good look at these four applications: RiPPLE, FUMA, AcaWriter and TeamWork Analytcis.

Web: [Direct Link] [This Post]

The MOOC Replication Framework
Miggy Andres-Bray, MOOC Replication Framework, 2022/05/17

The MOOC Replication Framework (MORF) is "a big data repository and analysis environment for Massive Open Online Courses (MOOCs)." This approach is needed to take advantage of personal and demographic data for learning analytics without violating individual privacy. MORF is in limited release alpha but the documention describes the MORF API "used to construct and evaluate predictive models from raw MOOC platform data." The repository hosted by the Educational Technology Collective is a little out of date, so the project may have died, but a BERA paper (specifically, BJET) was just published on it (behind a paywall, unfortunately) but there's an earlier open access paper.

Web: [Direct Link] [This Post]

On my bike ride this morning, saw a delivery robot lost in the woods
Matthew McCormack, Twitter, 2022/05/17

This is one of the best Twitter threads I have seen, perhaps ever. And it speaks to how quickly robots are about to enter our folklore. This photo is exactly as the title suggests (though my first question was, is it really lost?). There are more like it, some comedy, others tragedy.

Web: [Direct Link] [This Post]

Microsoft FarmBeats for Students harnesses data and AI to plant big ideas in young minds
Tiffany Wright, Microsoft Education, 2022/05/17

This article describes Australia's FarmBeats for Students initiative that offered "the opportunity to participate in a hands-on AI sustainable learning experience applying smart farming techniques to food production." The initiative, which consisted of lesson plans and relevant technology, allowed students to "gain access to historical data from the local area to examine the changes that have taken place in the climate over time and to consider how those changes impact current and future growing conditions." This is the sort of blending of tech, real-world data, and authentic practice that I think will become more common in education. Its impact will have to be measured through more than just test scores, though.

Web: [Direct Link] [This Post]

WUI-NITY 2: the integration, verification, and validation of the wildfire evacuation platform
Enrico Ronchi, et al., Fire Protection Research Foundation, 2022/05/17

This report (117 page PDF) would serve as a really good case study of virtual reality in action. It develops the science of predictive model development for wildfire evacuations while functioning as a learning and development tool. " Evacuation performance outcomes, like the ones produced by WUI-NITY, are crucial to develop both (i) pre-event community and evacuation plans, training programs and educational outreach materials and (ii) response-based evacuation and warning decisions that are safe and cost-effective."

Web: [Direct Link] [This Post]