Table of Contents
Fetching ...

Intelligent Tutors Beyond K-12: An Observational Study of Adult Learner Engagement and Academic Impact

Adit Gupta, Christopher MacLellan

TL;DR

This study investigates whether intelligent tutoring systems can benefit adult learners when used voluntarily as a supplementary resource. Using a two-year observational deployment of the Apprentice Tutors in College Algebra, the authors analyze usage demographics, learning progression via AFM, and associations with unit-level grades. They find within-tutor skill gains and a positive, though non-causal, relationship between tutor engagement and course performance, suggesting real-world potential for adult upskilling with ITS. The work highlights the importance of flexible access, demographic considerations, and rigorous future studies (e.g., randomized trials) to establish long-term impact and scalability across domains.

Abstract

Intelligent tutors have proven to be effective in K-12 education, though their impact on adult learners -- especially as a supplementary resource -- remains underexplored. Understanding how adults voluntarily engage with educational technologies can inform the design of tools that support skill re-learning and enhancement. More critically, it helps determine whether tutoring systems, which are typically built for K-12 learners, can also support adult populations. This study examines the adoption, usage patterns, and effectiveness of a novel tutoring system, Apprentice Tutors, among adult learners at a state technical college. We analyze three types of data including, user demographics, grades, and tutor interactions, to assess whether voluntary tutor usage translates into measurable learning gains. Our findings reveal key temporal patterns in tutor engagement and provide evidence of learning within tutors, as determined through skill improvement in knowledge components across tutors. We also found evidence that this learning transferred outside the tutor, as observed through higher course assessment scores following tutor usage. These results suggest that intelligent tutors are a viable tool for adult learners, warranting further research into their long-term impact on this population.

Intelligent Tutors Beyond K-12: An Observational Study of Adult Learner Engagement and Academic Impact

TL;DR

This study investigates whether intelligent tutoring systems can benefit adult learners when used voluntarily as a supplementary resource. Using a two-year observational deployment of the Apprentice Tutors in College Algebra, the authors analyze usage demographics, learning progression via AFM, and associations with unit-level grades. They find within-tutor skill gains and a positive, though non-causal, relationship between tutor engagement and course performance, suggesting real-world potential for adult upskilling with ITS. The work highlights the importance of flexible access, demographic considerations, and rigorous future studies (e.g., randomized trials) to establish long-term impact and scalability across domains.

Abstract

Intelligent tutors have proven to be effective in K-12 education, though their impact on adult learners -- especially as a supplementary resource -- remains underexplored. Understanding how adults voluntarily engage with educational technologies can inform the design of tools that support skill re-learning and enhancement. More critically, it helps determine whether tutoring systems, which are typically built for K-12 learners, can also support adult populations. This study examines the adoption, usage patterns, and effectiveness of a novel tutoring system, Apprentice Tutors, among adult learners at a state technical college. We analyze three types of data including, user demographics, grades, and tutor interactions, to assess whether voluntary tutor usage translates into measurable learning gains. Our findings reveal key temporal patterns in tutor engagement and provide evidence of learning within tutors, as determined through skill improvement in knowledge components across tutors. We also found evidence that this learning transferred outside the tutor, as observed through higher course assessment scores following tutor usage. These results suggest that intelligent tutors are a viable tool for adult learners, warranting further research into their long-term impact on this population.

Paper Structure

This paper contains 17 sections, 10 figures, 2 tables.

Figures (10)

  • Figure 1: User interface of Apprentice Tutors platform with key features: (a) penalization through adaptive problem selection (b) real-time correctness feedback (c) four available tutors (d) hint box and multi-layer hints (e) user profile screen with progress bars corresponding to knowledge components.
  • Figure 2: Tutor usage by course unit in College Algebra. The x-axis represents the different units, and the y-axis shows the number of transactions recorded for each unit. Unit 1 has significantly higher tutor usage compared to other units, suggesting a higher tutor coverage in this area.
  • Figure 3: Demographic Data of Apprentice Tutors: Gender distribution comparison between tutor and non-tutor users.
  • Figure 4: Demographic Data of Apprentice Tutors: Age distribution comparison between tutor and non-tutor users.
  • Figure 5: Demographic Data of Apprentice Tutors: Ethnicity distribution comparison between tutor and non-tutor users.
  • ...and 5 more figures