|Title:||Combining Advantages of Collaborative and Individual Learning with an Intelligent Tutoring System for Fractions|
|Principal Investigator:||Aleven, Vincent||Awardee:||Carnegie Mellon University|
|Program:||Cognition and Student Learning [Program Details]|
|Award Period:||3 years (9/1/2012-8/31/2015)||Award Amount:||$1,500,000|
|Type:||Development and Innovation||Award Number:||R305A120734|
Co-Principal Investigator: Nikol Rummel (Ruhr-Universitšt Bochum, Germany and Carnegie Mellon University)
Purpose: Classroom instruction often involves both individual and collaborative modes of learning. Yet relatively little is known about the ways in which these learning modes complement each other, or how best to combine them. In this project, the research team will combine features of both individual and collaborative learning interventions that each on their own have evidence of efficacy into a revised version of a current web-based intelligent tutoring system. Previous research has found that intelligent tutoring systems (ITSs) can be an effective platform for supporting individual learning. In addition, scripted collaborative learning within a computer-based collaborative environment can lead to robust learning outcomes. Prior research indicates that collaborative learning is most effective with activities that promote conceptual sense making, whereas individual learning works best with activities that promote procedural fluency development. The tutoring system that will be adapted is based on the Cognitive Tutor technology, and covers a comprehensive set of topics in fourth- and fifth-grade fractions learning. Using an iterative design process, the researchers will adapt the tutors to support a combination of collaborative learning and individual learning that reflects experimental findings.
Project Activities: The researchers will carry out a laboratory experiment and two classroom experiments to test how to best combine individual learning (that is, individual students solving problems at the computer) with collaborative learning (that is, networked dyads of students working together on solving problems while communicating via chat). The researchers will use eye-tracking technologies to investigate the relationship between learning mode (individual versus collaborative learning), task type (procedural versus conceptual), and attentional processes as reflected by eye gaze data. The existing tutoring system will be adapted to emphasize either conceptual sense making or procedural fluency and refinement. New versions of the tutor will be pilot tested with small numbers of participants from the target population as part of the researchers' iterative design process.
Products: The product of this project will be a fully adapted web-based intelligent tutor for fourth- and fifth-grade children learning fractions that supports a combination of individual and collaborative learning. Peer reviewed publications will also be produced.
Setting: The researchers will carry out one lab experiment on the Carnegie Mellon University campus in Pittsburgh, PA, and two classroom studies. The classroom studies will be carried out in several elementary schools in an urban area of Western Pennsylvania where the researchers have an established research partnership.
Sample: The participants will be students in grades 4 and 5. Experiment 1 will involve 184 students; Experiment 2, 560 students; and Experiment 3, 640 students. The largest of the participating school districts includes over 50 percent ethnic minorities, with the other school districts having lower percentages of minorities. The school districts vary substantially in terms of their ranking among Pennsylvania school districts.
Intervention: The research will produce an adapted version of the researchers' intelligent tutoring system that covers a comprehensive set of topics in fourth- and fifth-grade fractions learning. The researchers will adapt the existing tutor for use by networked dyads working together on solving problems, while communicating via chat, and to support new activity types focused on conceptual sense making and procedural fluency development. The tutors will be made freely available on the Mathtutor website, which was funded by a previous IES grant.
Research Design and Methods: The research team will carry out three experiments. In the first two studies, the researchers will use a 2x2 design to test the hypothesized complementary strengths of individual and collaborative learning, with task type and collaboration being the two variables of interest. In the laboratory study, the researchers will use eye tracking technologies to test the hypothesis that eye movements are a direct mediator of the expected interaction between task type (procedural versus conceptual) and collaboration (individual versus collaborative learning). The tutors will be adapted to emphasize either conceptual sense making or procedural fluency and refinement. New versions of the tutor will be pilot tested with small number of participants from the target population as part of the researchers' iterative design process. In the third study, the researchers test whether and how to combine collaborative and individual learning. The researchers will compare three combination conditions, and include a purely individual and a purely collaborative condition.
Control Condition: The control conditions vary across each of the three experiments as a function of the hypothesis being tested.
Key Measures: The researchers will use pre- and posttests that they created and validated in their previous research to assess students' procedural fluency with and conceptual knowledge of fractions. Tutor log data will give insight into students' rate of learning for the targeted knowledge components.
Data Analytic Strategy: Analysis: The researchers will analyze the pre- and post-test data using multiple analyses of covariance and, if appropriate for the classroom studies, hierarchical linear models. The team will extract "learning curves" and other measures of student learning behavior from the tutor log data using DataShop, a large and open online repository for tutor log data with associated analysis tools. The eye tracking and tutor log data will be analyzed to uncover differences between conditions in how students direct their attention to the relevant parts of the tutor activities, and to analyze the coupling of eye movements of collaborating partners, compared across conditions.
Related IES Projects: Bringing Cognitive Tutors to the Internet: A Website that Helps Middle-School Students Learn Math (R305A080093)
Olsen, J.K., Aleven, V., and Rummel, N. (2017). Exploring Dual Eye Tracking as a Tool to Assess Collaboration. In A. A. von Davier, M. Zhu, & P. C. Kyllonen (Eds.), Innovative Assessment of Collaboration. New York: Springer.
Journal article, monograph, or newsletter
Aleven, V., McLaren, B.M., Sewall, J., van Velsen, M., Popescu, O., Demi, S., Ringenberg, M., and Koedinger, K.R. (2016). Example-Tracing Tutors: Intelligent Tutor Development for Non-Programmers. International Journal of Artificial Intelligence in Education, 26(1): 224–269.
Rau, M.A., Aleven, V., and Rummel, N. (2017). Supporting Students in Making Sense of Connections and in Becoming Perceptually Fluent in Making Connections Among Multiple Graphical Representations. Journal of Educational Psychology, 109(3): 355–373.
Rau, M.A., Aleven, V., and Rummel, N. (2017). Making Connections among Multiple Graphical Representations of Fractions: Sense-Making Competencies Enhance Perceptual Fluency, but Not Vice Versa. Instructional Science: An International Journal of the Learning Sciences, 45(3): 331–357.
Belenky, D.M., Ringenberg, M., Olsen, J., Aleven, V., and Rummel, N. (2014). Using Dual Eye-Tracking to Evaluate Students' Collaboration With an Intelligent Tutoring System for Elementary-Level Fractions. In Proceedings of the 36th Annual Cognitive Science Conference (pp. 176–181). Austin, TX: Cognitive Science Society.
Belenky, D.M., Ringenberg, M., Olsen, J.K., Aleven, V., and Rummel, N. (2013). Using Dual Eye-Tracking Measures to Differentiate Between Collaboration on Procedural and Conceptual Learning Activities. In Proceedings of the workshop DUET 2013: Dual Eye Tracking in CSCL—CSCL 2013 Conference.
Olsen, J. K., Aleven, V., and Rummel, N. (2016). Enhancing Student Modeling for Collaborative Intelligent Tutoring Systems. In 13th International Conference on Intelligent Tutoring Systems, ITS 2016 (pp. 485–487). Zagreb, HR: Springer International Publishing.
Olsen, J. K., Rummel, N., and Aleven, V. (2016). Investigating Effects of Embedding Collaboration in an Intelligent Tutoring System for Elementary School Students. In 12th International Conference of the Learning Sciences, ICLS 2016 (pp. 338–345). Singapore: International Society of the Learning Sciences (ISLS).
Olsen, J.K., Aleven, V., and Rummel, N. (2015). Adapting Collaboration Dialogue in Response to Intelligent Tutoring System Feedback. In Proceedings of the 17th International Conference, AIED 2015 (pp. 748–751). New York: Springer International Publishing.
Olsen, J.K., Aleven, V., and Rummel, N. (2015). Predicting Student Performance In a Collaborative Learning Environment. In Proceedings of the 8th International Conference on Educational Data Mining (pp. 211–217). Worcester, MA: Educational Data Mining.
Olsen, J.K., Belenky, D.M., Aleven, A., and Rummel, N. (2014). Using an Intelligent Tutoring System to Support Collaborative as Well as Individual Learning. In Proceedings of the 12th International Conference on Intelligent Tutoring Systems (pp. 134–143). Berlin, Heidelberg: Springer.
Olsen, J.K., Belenky, D.M., Aleven, A., Rummel, N., Sewall, J., and Ringenberg, M. (2014). Authoring Tools for Collaborative Intelligent Tutoring System Environments. In Proceedings of the 12th International Conference on Intelligent Tutoring Systems (pp. 523–528). Berlin, Heidelberg: Springer.
Olsen, J.K., Belenky, D.M., Aleven, V., and Rummel, N. (2013). Intelligent Tutoring Systems for Collaborative Learning: Enhancements to Authoring Tools. In Proceedings of the 16th International Conference on Artificial Intelligence in Education AIED 2013 (pp. 900–903). Berlin, Heidelberg: Springer.
Olsen, J.K., Belenky, D.M., Aleven, V., and Rummel, N. (2014). Collaboration on Procedural Problems may Support Conceptual Knowledge More Than you may Think. In Proceedings of the 3rd Workshop on Intelligent Support for Learning in Groups at the 12th International Conference on Intelligent Tutoring Systems. Honolulu: Intelligent Support for Learning in Groups.
Olsen, J.K., Belenky, D.M., Aleven, V., Rummel, N., Sewall, J., and Ringenberg, M. (2013). Authoring Collaborative Intelligent Tutoring Systems. In Proceedings of the 2nd Workshop on Intelligent Support for Learning in Groups at the 16th International Conference on Artificial Intelligent in Education (pp. 1–10). Memphis: AIED.
Olsen, J.K., Rummel, N., and Aleven, V. (2015). Finding Productive Talk Around Errors in Intelligent Tutoring Systems. In Proceedings of the 11th International Conference on Computer Supported Collaborative Learning, Volume 2 (pp. 821–822). Gothenburg, Sweden: International Society of the Learning Sciences.