More Like this

1. Expanding the Frame: Designing a Learning Analytics System Using a Theory of Learning

   Philip, Philip (January 2020, International Conference of the Learning Sciences)

   null (Ed.)

   This essay presents the case of designing a learning analytics system using a theory of learning. Learning analytics systems are often institutional artifacts using data collected from and to support educational practice and practitioners including learners, teachers, and administrators. There is a substantial and growing body of work under the learning analytics banner. Much of it framed technically around data harvested from digital tools and presentation mechanisms called dashboards. Using a specific case involving a collaborative game-based education research project, this paper provides a broad, sociotechnical design perspective through three frame expanding sections: the educational game’s learning theory-driven approach, the information architecture of the learning analytics system, and the activity system that the information from learning analytics information are used within. This paper illustrates a portion of the conceptual landscape that can guide the design, development, and research for these data systems that are potentially consequential for students and educators. 

   more » « less
2. Evaluating the Impact of Data Representation on EHR-Based Analytic Tasks

   Oh, Wonsuk; Steinbach, Michael S.; Castro, M. Regina; Peterson, Kevin A.; Kumar, Vipin; Caraballo, Pedro J.; Simon, Gyorgy J. (August 2019, Medinfo 2019)

   Different analytic techniques operate optimally with different types of data. As the use of EHR-based analytics expands to newer tasks, data will have to be transformed into different representations, so the tasks can be optimally solved. We classified representations into broad categories based on their characteristics and proposed a new knowledge-driven representation for clinical data mining as well as trajectory mining, called Severity Encoding Variables (SEVs). Additionally, we studied which characteristics make representations most suitable for particular clinical analytics tasks including trajectory mining. Our evaluation shows that, for regression, most data representations performed similarly, with SEV achieving a slight (albeit statistically significant) advantage. For patients at high risk of diabetes, it outperformed the competing representation by (relative) 20%. For association mining, SEV achieved the highest performance. Its ability to constrain the search space of patterns through clinical knowledge was key to its success. 

   more » « less
3. Seeing Learning Sciences Research as Modeling

   Roschelle, Jeremy (January 2021, International Conference of the Learning Sciences)

   de Vries, E; Hod, Y; Ahn, J (Ed.)

   Researchers in the Learning Sciences take two prevalent stances: research as building theories or as developing designs. The connection between theories and designs is most often filled in by methods, but an alternative stance is possible: research as improving models. The modeling stance seeks parsimonious, useful, illuminating descriptions of learning activity systems. Models can help us understand and express how variability (in all its forms) plays into, is enacted during, and results from designed learning activities. Building models often requires employing multiple theories, methods, and design elements; a modeling stance recognizes that our research often elaborates a multi-level systems view. An explicit modeling stance may lead to developing descriptions of complex systems, inviting multi-stakeholder teamwork to improve these systems, integrating advances in learning analytics and educational data mining, and adding to ability of learning sciences research to tackle challenges at scale. 

   more » « less
4. Perspectives on Computational Models of Learning and Forgetting

   Sense, Florian; Jastrzembski, Tiffany S.; Mozer, Michael C.; Krusmark, Michael; van Rijn, Hedderik (July 2019, International Conference on Cognitive Modeling)

   Technological developments have spawned a range of educational software that strives to enhance learning through personalized adaptation. The success of these systems depends on how accurate the knowledge state of individual learners is modeled over time. Computer scientists have been at the forefront of development for these kinds of distributed learning systems and have primarily relied on data-driven algorithms to trace knowledge acquisition in noisy and complex learning domains. Meanwhile, research psychologists have primarily relied on data collected in controlled laboratory settings to develop and validate theory-driven computational models, but have not devoted much exploration to learning in naturalistic environments. The two fields have largely operated in parallel despite considerable overlap in goals. We argue that mutual benefits would result from identifying and implementing more accurate methods to model the temporal dynamics of learning and forgetting for individual learners. Here we discuss recent efforts in developing adaptive learning technologies to highlight the strengths and weaknesses inherent in the typical approaches of both fields. We argue that a closer collaboration between the educational machine learning/data mining and cognitive psychology communities would be a productive and exciting direction for adaptive learning system application to move in. 

   more » « less
5. Leveraging learning theory and analytics to produce grounded, innovative, data-driven, equitable improvements to teaching and learning.

   https://doi.org/10.1037/edu0000933  

   Bernacki, Matthew L (January 2025, Journal of Educational Psychology)

   Research in educational psychology involves empirical investigation into the learning process with an aim to refine psychological theories of learning and their application to real-world settings where they can be used to benefit learners. Emergent methodological processes involved in learning analytics include the study of event-based data produced by individuals in learning environments where they use technology. Paradigms for substantive-methodological synergy can be used to align the strengths of educational psychology and learning analytics research. The Journal of Educational Psychology invites such collaborations. This issue illustrates the advancements to educational theory and practice that can be attained when learning analytics practices are aligned to reflect the assumptions within psychological theories of learning and learning analytics methods including feature engineering and multimodal modeling are leveraged. Exemplars demonstrate learning analytics’ potential contribution to the refinement and application of theories of learning and motivation. Educational Impact and Implications Statement Theories about learning describe complex processes and how the ways individuals undertake them affect the understanding they obtain and performances they achieve. Many of these learning processes are difficult to observe in the naturalistic settings where people learn. When data individuals produce during learning with technologies are collected and modeled in alignment with learning theories and using learning analytics methods, they can make learning processes observable. Incorporating learning analytics into the study of learning and the development of instruction can help refine learning theories and the design of technologies that individuals use to learn. 

   more » « less