Patterns of Adults with Low Literacy Skills Interacting with an Intelligent Tutoring System

Abstract

A common goal of Intelligent Tutoring Systems (ITS) is to provide learning environments that adapt to the varying abilities and characteristics of users. This type of adaptivity is possible only if the ITS has information that characterizes the learning behaviors of its users and can adjust its pedagogy accordingly. This study investigated an intelligent tutoring system with computer agents (AutoTutor) designed to improve comprehension skills in adults with low reading literacy. One goal of this study was to classify adults into different clusters based on their behavioral patterns (accuracy and response time to answer questions) while they interacted with AutoTutor to help them improve their reading comprehension skills. A second goal was to investigate whether adults’ behaviors were associated with different reading components. A third goal was to assess improvements in reading comprehension skills, based on psychometric tests, of different clusters of readers. Performance on AutoTutor was collected in a targeted 100-hour hybrid intervention for adult readers (n = 252) that included both human teachers and the AutoTutor system. The adults’ average accuracy and response time in AutoTutor were used to cluster the adults into four categories: higher performers (comparatively fast and accurate), conscientious readers (slow but accurate), under-engaged readers (fast at the expense of somewhat lower accuracy) and struggling readers (slow and inaccurate). Two psychometric tests of comprehension were used to assess comprehension. Gains in comprehension scores were highest for conscientious readers, lowest for struggling readers, with higher performing readers and under-engaged readers in between. The results provide guidance to enhance the adaptivity of AutoTutor.

Role of AI in Blended Learning: A Systematic Literature Review

“…The literature on flipped learning has strongly emphasized the need for connection (Bergmann & Sams, 2014;Straw et al, 2015;Talbert, 2017), and we found that AI can serve as an assistant to support collaborative learning practices (Lechuga & Doroudi, 2022). For example, AI helped teachers create student groups or cohorts (Lechuga & Doroudi, 2022), provided meaningful feedback automatically to large student cohorts (Pardo et al, 2019), and classified clusters of learners so the instructor could adjust the learning environment based on their abilities and characteristics (Fang, Lippert, et al, 2021). In another case, machine learning models helped classify students' discussion content to determine if they were course relevant in an online discussion activity of blended learning using a problem-based learning pedagogy (Liao & Wu, 2022).…”

“…As another unique case, Méndez and González (2013) coined the term reactive blended learning to highlight the reactive feature of AI technology as applied in blended learning. Fang, Lippert, et al (2021) referred to it as hybrid intervention since their research practice consisted of a human teacher-led session and auto tutor session. Although the context studied by Ng and Chu (2021) was online learning only instead of blended learning, we considered it blended learning since the practices were a combination of asynchronous learning and F2F synchronous learning.…”

“…For example, in Tran and Meacheam (2020), in the Moodle LMS, the AI-based platform played a role as a supplementary assistant by supporting instructors' decision making in the LA report. Fang, Lippert, et al (2021) also contended that Autotutor was not only a pedagogical agent but also a conversation-based intelligent tutoring system that supported analytics.…”

“…• Augment the school experience (Chatzara et al, 2019) • Help class administration (Phillips et al, 2020) and orchestration through student tracking, classroom dynamics, and goal achievement (Mavrikis et al, 2019) • Help instructors customize course content, monitor students' learning progress (Phillips et al, 2020), decrease teachers' workload and save time (Lechuga & Doroudi, 2022;Lin & Mubarok, 2021) Facilitate interactions between instructor and student, and/or students • Help teachers form groups of students and identify the content appropriate for differentiated instruction (Lechuga & Doroudi, 2022) • Support instructors to provide meaningful feedback to large student cohorts (Pardo et al, 2019) • Classify clusters of learners and adjust the learning environment to learners' abilities and characteristics (Fang, Lippert, et al, 2021) • Support various collaborative learning practices (Lechuga & Doroudi, 2022) • Classify students' discussion content to determine relevance to the course (Liao & Wu, 2022) • Encourage teachers to start interaction with students, and inform teachers when intervention might be needed (Van Leeuwen, 2019) Change learning processes and improving performances…”

“…However, we only found a few cases for this review, perhaps because this study focused on blended learning. Nevertheless, several studies in this review presented the partial function as pedagogical agents (Whatley, 2004) such as a Chatbot (Annamalai et al, 2023;Lin & Mubarok, 2021;Neo, 2022), auto tutor (Fang, Lippert, et al, 2021), and voice assistant (Al-Kaisi et al, 2021), which allowed students to communicate and facilitated their learning with immediate feedback and scaffolding. It also helped teachers save time and reduce their workload.…”