Journal of Educational Psychology

Leveraging learning theory and analytics to produce grounded, innovative, data-driven, equitable improvements to teaching and learning.
Research in educational psychology involves empirical investigation into the learning process with an aim to refine psychological theories of learning and their application to real-world settings where they can be used to benefit learners. Emergent methodological processes involved in learning analytics include the study of event-based data produced by individuals in learning environments where they use technology. Paradigms for substantive-methodological synergy can be used to align the strengths of educational psychology and learning analytics research. The Journal of Educational Psychology invites such collaborations. This issue illustrates the advancements to educational theory and practice that can be attained when learning analytics practices are aligned to reflect the assumptions within psychological theories of learning and learning analytics methods including feature engineering and multimodal modeling are leveraged. Exemplars demonstrate learning analytics’ potential contribution to the refinement and application of theories of learning and motivation. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Using theory-informed learning analytics to understand how homework behavior predicts achievement.
Educators, families, and students continue to debate whether homework promotes academic achievement. A resolution to this debate has proven elusive, given the often-mixed findings of the relationship between homework behavior, typically measured with often-unreliable student self-reports and achievement. We argue better estimates of these relationships require (a) changes to what data are collected to measure homework behavior and (b) more theory-informed ways to model those data. Thus, in this article, we pursued what Marsh and Hau (2007) called substantive-methodological synergy. We grounded our substantive investigation in Trautwein et al.’s (2006) Homework Model, wherein student characteristics and motivation predict homework behaviors (i.e., homework effort, homework time), which in turn predict achievement. To better understand students’ homework behavior, we used digital tools that produced trace data that could be understood and modeled via theory-informed learning analytics. We collected homework behavior data and subsequent achievements from 507 German academic-track school students who used an intelligent tutoring system to learn English as a foreign language. Our initial analyses showed that theory-aligned digital trace data captured unique information beyond self-report data. Then, we found homework effort, as conceptualized in the Homework Model and captured via theory-informed learning analytics, predicted academic performance, whereas homework time did not. Overall, behavioral trace measures of homework effort were more predictive than self-reports. These findings help to clarify the mixed findings in the homework literature and illustrate the benefits of substantive-methodological synergy between theory and learning analytic methods. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Temporal dynamics of meta-awareness of mind wandering during lecture viewing: Implications for learning and automated assessment using machine learning.
Remote learning settings require students to self-regulate their behavioral, affective, and cognitive processes, including preventing mind wandering. Such engagement in task-unrelated thoughts has a negative impact on learning outcomes and can occur with or without students’ awareness of it. However, research on the meta-awareness of mind wandering in education remains limited, predominantly relying on self-report measures that capture discrete information at specific time points. Therefore, there is a need to investigate and measure temporal dynamics in the meta-awareness of mind wandering continuously over time. This study examined the temporal patterns of 15 mind-wandering and meta-awareness probes in a sample of university students (N = 87) while they watched a video lecture. We found that the majority (60%) of mind wandering occurred with meta-awareness. Cluster analysis identified five distinct thought sequence clusters. Thought patterns dominated by unaware mind wandering were negatively associated with fact- and inference-based learning, whereas persistent aware mind-wandering patterns were linked to reduced deep-level understanding. Initial exploration into predictive modeling, based on eye gaze features, revealed that the models could distinguish between aware and unaware mind-wandering instances above the chance level (macro F1 = 0.387). Model explainability methods were employed to investigate the intricate relationship between gaze and mind wandering. It revealed the importance of eye vergence and saccade velocity in distinguishing mind-wandering types. The findings contribute to understanding mind-wandering meta-awareness dynamics and highlight the capacity of continuous assessment methods to capture and address mind wandering in remote learning environments. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Impact of an adaptive dialog that uses natural language processing to detect students’ ideas and guide knowledge integration.
This study leverages natural language processing (NLP) to deepen our understanding of how students integrate their ideas about genetic inheritance while engaging in an adaptive dialog. In Study 1, informed by knowledge integration (KI) pedagogy, we used responses from 1,485 students to test one NLP model to detect the ideas students express when explaining why siblings look similar but not identical and another NLP model to holistically score their response for KI. In Study 2, we used the tested NLP models from Study 1 to design an adaptive dialog that responds to students’ detected ideas. We assessed the impact of the dialog on students’ level of KI. We embedded the dialog in a web-based unit and implemented it in five middle and high schools with 11 teachers and 610 students. Students’ KI scores significantly improved across the unit, and from their initial to revised responses in the dialogs. Consistent with KI, students significantly added differing new accurate ideas. They generally linked their vague ideas to new ideas rather than dropping vague ideas. Two patterns emerged: Students who achieve partial KI form links between new accurate and initial vague ideas; Students who progress to integrated KI distinguish between initial vague and accurate ideas plus new accurate ideas to form varied links. These results clarify that students follow multiple paths to combine their ideas and construct coherent responses while studying a unit featuring adaptive dialogs. They point to designs for adaptive guidance to build on students’ ideas and promote integrated understanding. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Leveraging student planning in game-based learning environments for self-regulated learning analytics.
The process of setting goals and creating plans is crucial for self-regulated learning (SRL), yet students often struggle to construct efficient plans and establish goals. Adaptive learning environments hold promise for assisting students with such processes through adaptive scaffolding. Through the examination of data collected from 144 middle school students, we present a data-driven analysis of students’ explicit planning activities in Crystal Island, a narrative game-based learning environment. In this game, students are provided with a planning support tool that aids them in externalizing their science-related goals and plans before putting them into action. We extracted features from their planning tool use and connected them to several SRL processes and problem-solving outcomes. We found that students who engaged with the planning support tool were more likely to successfully complete the learning scenario. To investigate the potential for adaptive support with this tool, we also constructed a student plan recognition framework aimed at predicting students’ goals and planned action sequences. This framework uses student gameplay sequences as input and student interactions with the planning tool as labels for both prediction tasks. We evaluated these tasks using six machine learning models and found that all approaches improved on the majority baseline classification performance. We then investigated additional machine-learning architectures and a technique for detecting when students enact all steps in their plans as methods for improving the framework. We demonstrated performance improvement with these enhancements. Overall, results demonstrated that the planning support tool can help students engage in SRL activities and drive adaptive support in real time. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Dissecting the temporal dynamics of embodied collaborative learning using multimodal learning analytics.
Embodied collaborative learning, intertwining verbal and physical behaviors, is an intricate learning process demanding a multifaceted approach for comprehensive understanding. Prior studies in this field have often neglected the temporal dynamics and the interplay between verbal and bodily behaviors in collaborative learning settings. This study bridges this gap by employing an integrative approach combining social constructivism, situated cognition, and embodied cognition theories through multimodal learning analytics (MMLA) to dissect the temporal dynamics of embodied collaborative learning in a simulated clinical setting. The study operationalized the linguistic, contextual, and bodily elements of each theoretical perspective, focusing on analyzing the verbal communication, spatial behavior, and physiological responses of 56 students across 14 sessions. These multimodal data were analyzed using correlation analysis and epistemic network analysis. The results illustrated the interconnected nature of students’ verbal communication and spatial behaviors during collaborative learning and demonstrated that an MMLA approach could effectively capture the temporal dynamics of these behaviors across different learning phases. The study also identified significant differences in the behaviors of efficient and inefficient teams and between satisfied and dissatisfied students, primarily linked to spatial behaviors. These insights underline the utility of MMLA in providing a nuanced understanding of collaborative learning behavior from an integrated theoretical perspective, with implications for learning design and the development of reflection and in-the-moment analytics. This study sets the stage for further exploration of the multifaceted dynamics of collaborative learning, underscoring the value of a multimodal approach to learning analytics and educational research. (PsycInfo Database Record (c) 2024 APA, all rights reserved)
Communicative influence: A novel measure of team dynamics that integrates team cognition theory with collaborative problem solving assessment.
We present and test communicative influence as a novel measure of team dynamics that integrates theories of team cognition with collaborative problem solving (CPS) assessment frameworks. We define influence as the degree to which a teammate’s behavior dynamically predicts patterns in their team’s future CPS state, quantified as the average mutual information (AMI) between the two signals. We evaluated this novel metric in the laboratory with college students (Study 1), in middle school classrooms (Study 2), and in semistructured interviews with teachers (Study 3). In the laboratory study, influence was related to experimental assignment of students’ role (i.e., those assigned control over a shared interface had more influence than those who verbally contributed to the solution) and predicted CPS task success and students’ subjective perceptions of the collaboration. In the classroom study, the influence was not related to team size (2–4) but was negatively related to teams’ adherence to collaborative norms. Analyses of collaborative discourse suggested that influence in this context may reflect the tendency to posit ideas and make claims without building on the ideas of others. Together, these results suggest that if the distribution of influence is dominated by a controlling team member, the collaboration may be less productive and negatively perceived than if influence is more distributed across the team. Feedback from semistructured interviews with four middle school teachers (Study 3) highlighted the potential for influence to be embedded in teacher interfaces (e.g., dashboards) to help them orchestrate classrooms for collaborative learning. (PsycInfo Database Record (c) 2024 APA, all rights reserved)

Journal of Educational Psychology - Vol 117, Iss 1