This study develops a framework to conceptualize the use and evolution of machine learning (ML) in science assessment. We systematically reviewed 47 studies that applied ML in science assessment and classified them into five categories: (a) constructed response, (b) essay, (c) simulation, (d) educational game, and (e) inter‐discipline. We compared the ML‐based and conventional science assessments and extracted 12 critical characteristics to map three variables in a three‐dimensional framework: construct, functionality, and automaticity. The 12 characteristics used to construct a profile for ML‐based science assessments for each article were further analyzed by a two‐step cluster analysis. The clusters identified for each variable were summarized into four levels to illustrate the evolution of each. We further conducted cluster analysis to identify four classes of assessment across the three variables. Based on the analysis, we conclude that ML has transformed—but not yet redefined—conventional science assessment practice in terms of fundamental purpose, the nature of the science assessment, and the relevant assessment challenges. Along with the three‐dimensional framework, we propose five anticipated trends for incorporating ML in science assessment practice for future studies: addressing developmental cognition, changing the process of educational decision making, personalized science learning, borrowing 'good' to advance 'good', and integrating knowledge from other disciplines into science assessment.
The advancement of technologies has promoted the increasing popularity and integration of mobile technologies in science education in the past decade. These trends have led to an increased interest among scholars to understand the effects of mobile technologies in science education and whether those effects differ depending on how mobile technologies are used in learning and teaching (eg, student‐led, teacher‐led, collaborative). In this study, we performed a meta‐analysis of 34 studies that directly examined the effects of users' pedagogical role on K‐16 students' achievement in science when engaging in mobile learning (ML). The analysis of the 34 studies yielded an overall significant main effect of ML on K‐16 science learning outcomes. We applied the mixed‐effects model with moderator variables and found that users' pedagogical role significantly moderated the ML effects as a whole. Collaborative and student‐led uses had a statistically significant impact on student science learning, whereas teacher‐led use did not. Findings from this meta‐analysis are consistent with prior research, providing synthesized research‐based evidence of the effects of ML on science learning that holds implications for both mobile curriculum design and mobile technology use.
What is already known about this topic
Mobile technology has been increasingly adopted in science learning with great potential to support learning and teaching.
Prior meta‐analysis has suggested multiple moderators in measuring the mobile learning effect.
Prior empirical studies examined the effect of mobile users' pedagogical role in the specific subject domains (eg, physics) and grade levels (eg, high school).
What this paper adds
This meta‐analysis is among the first to examine the moderator effect of mobile users' pedagogical roles on ML in K‐16 science education.
This study found that mobile technology use is associated with significant science learning outcomes across 34 studies.
This study found that the effect of mobile learning was moderated by mobile users' pedagogical roles (ie, who initiated the use). Collaborative use between teachers and students tends to be the most effective. Teacher‐led use tends to be the least effective.
Implications for practice
This study suggests that we should consider who leads the use of mobile technology when integrating mobile learning in science education.
In particular, educators should encourage collaborative and student‐led mobile use for learning and instruction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.