Erin Walker’s research while affiliated with University of Pittsburgh and other places

Purpose The Parent–Enhanced Moved by Reading to Accelerate Comprehension in English (Parent EMBRACE) program offers a bilingual parent-training literacy intervention for Latino families. Within the context of shared book reading, the application leverages both the home language and technology to increase parent question-asking during shared reading. Research goals were to (a) examine the potential of the Parent EMBRACE tutoring system at teaching parents to increase the quantity and variety of their question-asking during shared book reading, (b) examine changes to parents' reading attitudes or motivation, and (c) examine whether children's reading attitude is correlated with parent interactions. Method Twenty-one participants were randomized into three conditions: a digital storybook (DS) group ( n = 7), an interactive storybook (EMBRACE) group ( n = 6), and a parent-teaching interactive storybook (Parent EMBRACE) group ( n = 8). Participants received iPads with digital storybooks for use during the intervention (in which the parent-teaching group received prompts from the app to ask questions while reading). Shared book reading assessments before and after the intervention involved hard-copy books, and behaviors were analyzed using video-recorded reading sessions before and after the intervention. Group differences were explored using descriptive analysis. Reading attitude and motivation were measured through pre- and post-intervention surveys. The relationship between parent interactions and reading attitudes was explored through regression. Results Results indicate that after the intervention, four out of seven parents in the parent-teaching interactive storybook group asked more questions to their children. Parents' reading attitudes and motivations did not significantly change. There was a nonlinear relationship with parent interactions and children's reading attitude. Conclusion Overall, the Parent EMBRACE tool shows feasibility and warrants further study on its efficacy as a linguistically responsive literacy-based language intervention for Latino parents to develop shared book reading strategies.

One of the keys to the success of collaborative learning is balanced participation by all learners, but this does not always happen naturally. Pedagogical robots have the potential to facilitate balance. However, it remains unclear what participation balance robots should aim at; various metrics have been proposed, but it is still an open question whether we should balance human participation in human-human interactions (HHI) or human-robot interactions (HRI) and whether we should consider robots' participation in collaborative learning involving multiple humans and a robot. This paper examines collaborative learning between a pair of students and a teachable robot that acts as a peer tutee to answer the aforementioned question. Through an exploratory study, we hypothesize which balance metrics in the literature and which portions of dialogues (including vs. excluding robots' participation and human participation in HHI vs. HRI) will better predict learning as a group. We test the hypotheses with another study and replicate them with automatically obtained units of participation to simulate the information available to robots when they adaptively fix imbalances in real-time. Finally, we discuss recommendations on which metrics learning science researchers should choose when trying to understand how to facilitate collaboration.

We propose incorporating biophysical data with behavioral data to inform digital learning environments on an individual’s current cognitive state and how it relates to their learning. We used a rule learning paradigm drawn from cognitive psychology to define phases of rule learning across multiple domains. This paradigm can simulate an inductive reasoning framework seen during mathematics education while reducing the number of covariates compared to real-world settings. We combined the time series brain data with behavioral and contextual data in machine learning models for prediction of rule learning phases with the aim of developing approaches to incorporate a mixture of behavioral and neural data into digital learning designs.Keywordsrule learninginductive reasoningfunctional near-infrared spectroscopybrain-computer interfaces

The use of artificial intelligence (AI) in education has been on the rise, and government and non-government organizations around the world are establishing policies and guidelines to support its safe implementation. However, there is a need to bridge the gap between AI research practices and their potential applications to design and implement educational policies. To help the community to address this challenge, we propose a workshop on AI and Educational Policy with the theme “Opportunities at the Intersection between AI and Education Policy.” The workshop aimed to identify global challenges related to education and the adoption of AI, discuss ways in which AI might support learning scientists in addressing those challenges, learn about AI and education policy initiatives already in place, and identify opportunities for new policies to be established. We intend to develop action plans grounded in the learning sciences that identify opportunities and guidelines for specific AI policies in education.KeywordsPolicy designPolicy implementationEducational technology

While speech-enabled teachable agents have some advantages over typing-based ones, they are vulnerable to errors stemming from misrecognition by automatic speech recognition (ASR). These errors may propagate, resulting in unexpected changes in the flow of conversation. We analyzed how such changes are linked with learning gains and learners’ rapport with the agents. Our results show they are not related to learning gains or rapport, regardless of the types of responses the agents should have returned given the correct input from learners without ASR errors. We also discuss the implications for optimal error-recovery policies for teachable agents that can be drawn from these findings.KeywordsTeachable agentsAutomatic speech recognitionRapport

The dual mechanisms of control framework describes two modes of goal-directed behavior: proactive control (goal maintenance) and reactive control (goal activation on task demands). Although these mechanisms are relevant to learner behaviors during interaction with intelligent tutoring systems (ITS), their relation to ITSs is under-researched. We propose a manipulation to induce proactive or reactive control during interaction with an online tutoring system. We present two experiments where students solved problems using either proactive or reactive control. Study 1 validates the manipulation by investigating behavioral measures that reflect usage of the intended strategy and assesses whether either mode impacted learning. Study 2 investigates if alternating between control modes during problem solving affects student performance.KeywordsCognitive controlproblem solvinglearning environments

While speech-enabled teachable agents have some advantages over typing-based ones, they are vulnerable to errors stemming from misrecognition by automatic speech recognition (ASR). These errors may propagate, resulting in unexpected changes in the flow of conversation. We analyzed how such changes are linked with learning gains and learners' rapport with the agents. Our results show they are not related to learning gains or rapport, regardless of the types of responses the agents should have returned given the correct input from learners without ASR errors. We also discuss the implications for optimal error-recovery policies for teachable agents that can be drawn from these findings.

Speakers build rapport in the process of aligning conversational behaviors with each other. Rapport engendered with a teachable agent while instructing domain material has been shown to promote learning. Past work on lexical alignment in the field of education suffers from limitations in both the measures used to quantify alignment and the types of interactions in which alignment with agents has been studied. In this paper, we apply alignment measures based on a data-driven notion of shared expressions (possibly composed of multiple words) and compare alignment in one-on-one human-robot (H-R) interactions with the H-R portions of collaborative human-human-robot (H-H-R) interactions. We find that students in the H-R setting align with a teachable robot more than in the H-H-R setting and that the relationship between lexical alignment and rapport is more complex than what is predicted by previous theoretical and empirical work.