Improving Learning Systems with Social and Computer Sciences
Working closely with undisputed leaders in educational data mining, as well as faculty at the cutting edge of intelligent tutoring, cognitive psychology, and artificial intelligence, Learning Sciences & Technologies (LST) graduate students focus on methods to increase success in STEM (science, technology, engineering, and mathematics) learning and teaching in the United States, in grades K-12.
Research opportunities in this program—an interdisciplinary effort that combines social sciences and computer science—are diverse and deep, involving both laboratory and actual K-12 classroom studies. Topics include instructional technologies, learning with visualizations and simulations, learner characteristics, human-computer interaction, and machine learning.
SCIENCE INQUIRY LEARNING GROUP
Professor Gobert brings a focus to science pedagogy, developing technology-based systems and analytic techniques to support students and teachers in real time. The key to this pedagogical approach is assessment and tutoring of the student’s science skills utilizing logfile data to inform scaffolding. Dr. Gobert’s research has been funded by federal grants totaling close to 17 million dollars to date. Learn more…
Within the diverse population of urban middle schools, federally funded researchers continue the development of a computer-based system to improve students’ science inquiry skills, which are gauged using fine-grained logging technologies while learners are engaged in experimentation in microworlds in Physical, Life, and Earth Sciences. Measurement of inquiry skills utilizing knowledge engineering and educational data mining provide real-time information to teachers, who can then adjust instructional strategies for optimum individual outcomes. Transfer of skills is tested to ensure achievement of pragmatic goals, such as increased scores on state examinations. Given the population in this research, results are, we think, generalizable to students across the United States. Learn more…
In this new Science Inquiry Learning Group project, researchers are developing the technological capacity for an intelligent pedagogical agent to provide real-time scaffolding to students as they engage in inquiry with microworlds in the Physical Sciences. With microworlds, students generate hypotheses, collect data to test these, interpret data, warrant their claims with data, and communicate the findings. The system assesses student inquiry skills using models developed through knowledge engineering and educational data mining. Based on these data, a pedagogical agent, Rex (a cartoon dinosaur), identifies students who are flailing at specific inquiry skills, and give them multilevel feedback targeted toward helping them understand both conceptual and procedural aspects of inquiry. The project began in July, 2012.
ASSISTMENTS AND ASSESSMENT FOR RETENTION
Computer science is the foundation for research in expanding, proving, and improving web-based ASSISTments, an intelligent tutoring device, and for educational data mining to maximize functionality in learning approaches. Attractive to funders because of its efficacy, computer-aided learning is studied to extend its subject flexibility and increase helpful feedback to teachers and students alike.
Professor Beck leads the National Science Foundation (NSF) funded Automatic Reassessment and Retention System (ARRS) project, which evaluates student topic understanding. Rather than repeat the process of learning something only to quickly forget it, as can occur with computer-based systems that label a topic “mastered” when a certain number of correct responses are attained in a day, this research aims at periodically reassessing students on the topic - one week later, two weeks after that, then a month further along. Earlier studies showed better knowledge retention with the latter approach, and current LST research furthers the creation of a system that will study how to optimize student learning through this method for better retention. Learn more…
ASSISTments for Mathematics in Maine Schools
Funding of $3.5 million from the U.S. Department of Education underwrites this project, in which LST students evaluate the effectiveness of an online tutoring system for mathematics homework. Earlier investigation by SRI International demonstrated that 5th- and 8th-grade students using ASSISTments for immediate feedback when doing homework assignments learned more than those for whom feedback was delayed until the next day’s class. In this 4-year study, the ASSISTments system will provide 7th grade students at more than 50 schools in Maine with instant feedback and custom-tailored tutoring, while their teachers receive morning reports on students’ nightly progress, as well as instruction in how to adapt teaching plans to include this information. SRI International will continue to externally evaluate student test results. Learn more…