Industry Partners & Consultants
Building on a long history of sharing de-identified learner data with academic researchers, dozens of academic research projects and published articles in educational data science and related areas make use of data from Carnegie Learning's MATHia intelligent tutoring systems, formerly Cognitive Tutor (Ritter et al., 2007). In addition to datasets from MATHia, a dataset is also now available from LiveHint, a chat-based app that provides support for learners using Carnegie Learning's physical work-texts (Fisher et al., 2020). Datasets from MATHia and LiveHint are available via Carnegie Mellon's LearnSphere DataShop (Koedinger et al., 2011).
Fancsali & Ritter (2020) provide details about MATHia data as well as learning engineering and data science research efforts that make use of these data.
In Summer 2021, Carnegie Learning released a new collection of datasets (a DataShop "project," with anonymized learner data from 5,000+ learners) from the MATHia platform to DataShop. Check it out here: Carnegie Learning MATHia 2019-2020.
Please reach out to Stephen Fancsali for more information.
References
Fancsali, S.E., Ritter, S. (2020). Data-Intensive Learning Engineering & Applied Education Research with Carnegie Learning’s MATHia Platform. In V. Rus & S.E. Fancsali (Eds.) Proceedings of the The First Workshop of the Learner Data Institute (@ EDM2020): Big Data, Research Challenges, & Science Convergence in Educational Data Science.
Fisher, J., Fancsali, S.E., Lewis, A., Fisher, V., Hausmann, R.G.M., Pavelko, M., Finocchi, S.B., Ritter, S. (2020). LiveHint: Intelligent Digital Support for Analog Learning Experiences. In S. Sosnovsky, P. Brusilovsky, R. Baraniuk, A. Lan (Eds.) iTextbooks 2020: Proceedings of the Second International Workshop on Intelligent Textbooks 2020 (@ AIED 2020). CEUR Workshop Proceedings, Vol. 2674. pp. 80-89.
Koedinger, K.R., Baker, R.S.J.d., Cunningham, K., Skogsholm, A., Leber, B., Stamper, J. (2011). A Data Repository for the EDM Community: The PSLC DataShop. In C. Romero, S. Ventura, M. Pechenizkiy, and R.S.J.d. Baker (Eds.) Handbook of Educational Data Mining, CRC, Boca Raton, FL, 43-55.
Ritter, S., Anderson, J.R., Koedinger, K.R., and Corbett, A.T. (2007). Cognitive Tutor: Applied Research in Mathematics Education. Psychonomic Bulletin & Review, 14, 249-255.
The Workbay platform provides a shared common database and system of support for all the stakeholders in a community, providing valuable workforce information needed to make smart education and economic decisions from an individual and organizational standpoint. Using the Workbay technology, connects the information gap between workforce counsellors, educators, and corporations. Together, we can optimize the efficiency of the workforce at critical junctures by creating better resource and data-sharing, and better multi- dimensional analytics to engage all stakeholders in the education-to-employment bridge.
SoarTech is an industry leader in incorporating advanced technology into training and decision-support systems. Their philosophy is three-fold: to be an augmentation to, not a replacement of, the human; to think “top-down, not bottom-up;” and to be transparent so that decisions and processing are communicated to the human and in human-like terms. Representatives have put forward initiatives with the LDI, including a system for root-cause analysis that would better identify critical features of complex learning and training environments.
Gooru along with transdisciplinary researchers in major universities and lab school practitioners has formalize the Navigated Learning approach, an approach that understands the complete learner- their knowledge, skills, and mindset in relation to a competency framework, recommends a personalized pathway of learning activities, and modifies their routes based on performance to ensure they reach their learning destination. Many practitioners worldwide have been implementing Navigated Learning with small cohorts. Gooru developed the free and open Learning Navigator tool to assist scaled practice of Navigated Learning. Navigator provides a GPS-like experience for learners and real-time data to all stakeholders. Gooru collaborates with practitioners across disciplines and geographies to validate and evolve the science, technology, and practice of learning to accelerate outcomes for all learners. Navigator is continuously informed by practice and backed by science. Gooru partners with companies and governments to integrate the Navigator tools into their applications and reach millions of users.
Yixue Education/Squirrel AI Learning
MIBA: This large-scale Multimodal teaching and learning analytics dataset is coming from a complex real learning environment. This dataset includes time synchronized multimodal data records of students (learning logs, videos, EEG brainwaves) as they work on various subjects from Squirrel AI Learning System (SAIL) to solve problems of varying difficulty levels. The multimodal dataset resources include user records from the learner records store of SAIL, brainwave data collected by EEG headset devices, and video data captured by web cameras while students worked in the SAIL products.
Student Learning Events Data: This dataset is about students’ learning events as they learn various subjects from SAIL system both online and offline schools in real learning environment. The students learning events in this dataset contain students get the question, students click the analysis file after submit the answer, students view the report after the test, students submit the answer, and students play the teaching videos or skip to watch the videos. The dataset resources include different types of videos events while students working on different knowledge components too. For example, videos begin time and videos end time.
We shared the LDI mission of enabling global education efficacy through data convergence and technology advancement. Our two datasets can greatly enhance data convergence to build comprehensive learner profiles and time series of learner’s behavioral and cognitive journeys within our adaptive learning environment (both software environment including our core learning management system and ancillary facilities such as mobile homework systems, and our physical learning environment where the learners can be observed and monitored). Those datasets are part of the Squirrel AI (Total Education Experience) TEE datasets that have been approved for educational and learning science research purposes through our IRB and sensitization process.
Age of Learning is a leading educational technology innovator of digital learning resources for children ages 2 – 11. Their goal is to create engaging and highly effective educational experiences that help children achieve specific learning outcomes and develop a lifelong love of learning. Their flagship product ABCmouse Early Learning Academy is a comprehensive online curriculum and the #1 digital learning product for young children. To-date, more than 30 million children worldwide have completed over 8 billion learning activities on ABCmouse. They recently launched Adventure Academy, the first massively multiplayer online (MMO) game designed specifically to help elementary- and middle-school-aged children learn. It features thousands of engaging Learning Activities—including minigames, books, original animated and live action series, and more—in a fun and safe virtual world. Other Age of Learning programs include immersive English language learning products for children in China and Japan; ReadingIQ, a digital library and literacy platform; and My Math Academy, a groundbreaking personalized, adaptive digital learning system that individualizes math instruction for every child through game-based and AI-driven technology. With logs of game play data that include click-level descriptions of game play sessions, theirs is among the largest learning datasets for learners ages 2-11.
Age of Learning is committed to learning engineering best practices. Partnership with LDI and similar organizations support Age of Learning’s ongoing research efforts in identifying areas for system design improvements, informing teacher and family interventions, and driving additional research in learning engineering domains toward improving learning at scale.
The Adaptive Instructional Systems Consortium
The Adaptive Instructional Systems (AIS) Consortium is a not-for-profit alliance (US 501.c.6) under the IEEE Industry Standards & Technology Organization (ISTO). The mission of the AIS Consortium is to promote the development and adoption of effective AIS solutions and to support the industry and organizations that produce them. To this end, the consortium is developing an open source resource repository to be hosted on IEEE SA Open in 2021. The first three projects to migrated under this repository will be open-source for use by the general public in developing effective AIS solutions: Generalized Intelligent Framework for Tutoring (GIFT), Competency and Skills System (CaSS), and Gooru Navigator. These three projects provide broad authoring capabilities, embedded learning theory with adaptive instruction, ability to model learners and teams, visualize learning pathways and share data as a node in LearnSphere. The resource repository will be the basis for the development of an evaluation and certification process that supports testing of emerging AIS standards under IEEE Project 2247. Those effectiveness evaluations will be conducted with both real and simulated students. The resulting sanitized datasets (personally identifiable information extracted) are expected to be available for modeling and experimentation via LearnSphere. AIS Consortium POC: Robert A. Sottilare, Ph.D., Chairman of the Board & Executive Director, AIS Consortium. Inquiries should be directed to: bob.sottilare@ieee.org.