An official website of the United States government
In this paper, we present a framework for quantifying the impact of interventions on the full trajectories of students' experiences. The interventions are given periodically based on student performance forecasting from an artificial intelligence (AI) model. We performed a small-scale randomized controlled trial for evaluating the impact of the AI-based intervention system on the undergraduate students of a science, technology, engineering, and mathematics (STEM) course. Intervention messaging content was based on machine learning forecasting models trained on data collected from the students in the same course over the preceding 3 years. Trial results show that the intervention produced a statistically significant increase in the proportion of students that achieved a passing grade. By applying the trajectory-analysis framework we find that the intervention impacts the stories of some types of students more than others, and use this to define new ways of identifying students who are most likely to benefit. Together these outcomes point to the potential and promise of just-in-time interventions for STEM learning and the need for larger fully-powered randomized controlled trials.
more »
« less
An AI-based intervention for improving undergraduate STEM learning
We present results from a small-scale randomized controlled trial that evaluates the impact of just-in-time interventions on the academic outcomes of N = 65 undergraduate students in a STEM course. Intervention messaging content was based on machine learning forecasting models of data collected from 537 students in the same course over the preceding 3 years. Trial results show that the intervention produced a statistically significant increase in the proportion of students that achieved a passing grade. The outcomes point to the potential and promise of just-in-time interventions for STEM learning and the need for larger fully-powered randomized controlled trials.
more »
« less
- Award ID(s):
- 2142558
- PAR ID:
- 10499289
- Editor(s):
- Carvalho, Paulo F.
- Publisher / Repository:
- PloS ONE
- Date Published:
- Journal Name:
- PLOS ONE
- Volume:
- 18
- Issue:
- 7
- ISSN:
- 1932-6203
- Page Range / eLocation ID:
- e0288844
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Many campuses have utilized linked-course communities, wherein students take two or more courses with the same peers, in an effort to enhance learning and build community among students. Previous research on the effectiveness of linked-course communities have utilized quasi-experimental designs that are subject to selection bias – the communities may be effective due to which students volunteered to join the communities. This research session reports findings from a randomized controlled trial that eliminated selection bias by randomly assigning first-time first-year College of Science and Math students to linked-course communities or a control group. Findings demonstrate that students in the communities earned higher GPAs and more STEM credits in their first semester than students in the control group. Session participants will identify a curricular intervention and consider the feasibility of conducting a randomized controlled trial to assess effectiveness.more » « less
-
In past work, time management interventions involving prompts, alerts, and planning tools have successfully nudged students in online courses, leading to higher engagement and improved performance. However, few studies have investigated the effectiveness of these interventions over time, understanding if the effectiveness maintains or changes based on dosage (i.e., how often an intervention is provided). In the current study, we conducted a randomized controlled trial to test if the effect of a time management intervention changes over repeated use. Students at an online computer science course were randomly assigned to receive interventions based on two schedules (i.e., high-dosage vs. low-dosage). We ran a two-way mixed ANOVA, comparing students' assignment start time and performance across several weeks. Unexpectedly, we did not find a significant main effect from the use of the intervention, nor was there an interaction effect between the use of the intervention and week of the course.more » « less
-
Dolan, Erin L. (Ed.)Mindset interventions, which shift students’ beliefs about classroom experiences, have shown promise for promoting diversity in science, technology, engineering, and mathematics (STEM). Psychologists have emphasized the importance of customizing these interventions to specific courses, but there is not yet a protocol for doing so. We developed a protocol for creating customized “peer-modeled” mindset interventions that elicit advice from former students in videotaped interviews. In intervention activities, clips from these interviews, in which the former students’ stories model the changes in thinking about challenge and struggle that helped them succeed in a specific course, are provided to incoming life sciences students. Using this protocol, we developed a customized intervention for three sections of Introductory Biology I at a large university and tested it in a randomized controlled trial ( N = 917). The intervention shifted students’ attributions for struggle in the class away from a lack of potential to succeed and toward the need to develop a better approach to studying. The intervention also improved students’ approaches to studying and sense of belonging and had promising effects on performance and persistence in biology. Effects were pronounced among first-generation college students and underrepresented racial/ethnic minority students, who have been historically underrepresented in the STEM fields.more » « less
-
BackgroundIncreasingly, college science courses are transitioning from a traditional lecture format to active learning because students learn more and fail less frequently when they engage in their learning through activities and discussions in class. Fear of negative evaluation (FNE), defined as a student’s sense of dread associated with being unfavorably evaluated while participating in a social situation, discourages undergraduates from participating in small group discussions, whole class discussions, and conversing one-on-one with instructors. ObjectiveThis study aims to evaluate the acceptability of a novel digital single-session intervention and to assess the feasibility of implementing it in a large enrollment college science course taught in an active learning way. MethodsTo equip undergraduates with skills to cope with FNE and bolster their confidence, clinical psychologists and biology education researchers developed Project Engage, a digital, self-guided single-session intervention for college students. It teaches students strategies for coping with FNE to bolster their confidence. Project Engage provides biologically informed psychoeducation, uses interactive elements for engagement, and helps generate a personalized action plan. We conducted a 2-armed randomized controlled trial to evaluate the acceptability and the preliminary effectiveness of Project Engage compared with an active control condition that provides information on available resources on the college campus. ResultsIn a study of 282 upper-level physiology students, participants randomized to complete Project Engage reported a greater increase in overall confidence in engaging in small group discussions (P=.01) and whole class discussions (P<.001), but not in one-on-one interactions with instructors (P=.05), from baseline to immediately after intervention outcomes, compared with participants in an active control condition. Project Engage received a good acceptability rating (1.22 on a scale of –2 to +2) and had a high completion rate (>97%). ConclusionsThis study provides a foundation for a freely available, easily accessible intervention to bolster student confidence for contributing in class. Trial RegistrationOSF Registries osf.io/4ca68 http://osf.io/4ca68more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1371/journal.pone.0288844
