Educational Psychology Review最新文献

{"title":"Examining the Relationship Between Mathematics-Specific Language and Mathematical Abilities in Children: a Three-Level Meta-Analysis","authors":"Tingyu Zhu, Haiyan Luo, Lijin Zhang","doi":"10.1007/s10648-026-10139-2","DOIUrl":"https://doi.org/10.1007/s10648-026-10139-2","url":null,"abstract":"Mathematical ability is a foundational cognitive skill, yet the role of mathematics-specific language (MS language; e.g., quantitative, spatial, relational language) in supporting children’s mathematical development remains variably estimated across studies. The present three-level meta-analysis aimed to synthesize evidence on the relationship between MS language and mathematical ability in children and to examine potential moderators. A systematic search of Web of Science, Elsevier, ProQuest, and EBSCO was conducted up to May 3, 2025. Forty-nine articles (54 independent samples; 219 effect sizes; <italic>N</italic> = 12,739; ages 3.67–11.33 years) met the inclusion criteria. A random-effects three-level model showed that MS language was moderately and positively related to mathematical ability (<italic>r</italic> = 0.50, 95% CI [0.45, 0.55]), with substantial heterogeneity (<italic>Q</italic>(218) = 2215.77, <italic>p</italic> &lt; 0.001; <inline-formula><tex-math>documentclass[12pt]{minimal} usepackage{amsmath} usepackage{wasysym} usepackage{amsfonts} usepackage{amssymb} usepackage{amsbsy} usepackage{mathrsfs} usepackage{upgreek} setlength{oddsidemargin}{-69pt} begin{document}$$:{I}_{text{T}text{o}text{t}text{a}text{l}}^{2}$$end{document}</tex-math></inline-formula> = 88.64%). Variance decomposition indicated that 74.75% of heterogeneity occurred between studies and 13.89% within studies. A within-study comparison demonstrated that the MS language–mathematics relationship was slightly larger than the general language–mathematics relationship (β = 0.131, <italic>p</italic> &lt; 0.001). Moderator analyses indicated that effect sizes varied by MS language component, assessment format, mathematics domain, country, and language, whereas age, gender, socioeconomic status, publication year, and MS language orientation did not show reliable moderating effects. Multiple sensitivity and publication-bias analyses yielded highly consistent estimates. These findings indicate a robust relationship between children’s MS language and mathematical ability, highlighting measurement characteristics and cultural–linguistic context as key sources of variability and suggesting MS language as a potential avenue for future intervention, longitudinal studies, or mechanistic research.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"9 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personality Traits and Test Anxiety: A Meta-Analysis","authors":"Yuqing Zhang, Jie Liu, Ying Li","doi":"10.1007/s10648-026-10145-4","DOIUrl":"https://doi.org/10.1007/s10648-026-10145-4","url":null,"abstract":"This meta-analysis examined the relationship between Big Five personality traits (neuroticism, conscientiousness, extraversion, agreeableness and openness) and test anxiety among student population. Based on Control-Value Theory, this meta-analysis aims to group Big Five traits into two clusters based on their relative importance to test anxiety. By searching from both Chinese and English databases and incorporating 26 studies with 13,764 participants from various countries, the results generally supported the two-cluster trait classification: one primary trait cluster, comprising neuroticism (<italic>r</italic> = 0.42, 95% CI [0.35, 0.48] and conscientiousness (<italic>r</italic> = -0.11, 95% CI [-0.20, -0.02]), was significantly related to test anxiety, and one secondary trait cluster, including agreeableness (<italic>r</italic> = -0.04, 95% CI [-0.15, 0.07]), openness (<italic>r</italic> = -0.04, 95% CI [-0.15, 0.06]) and extraversion (<italic>r</italic> = -0.13, 95% CI [-0.20, -0.06]), was not associated with test anxiety (except for extraversion). Potential moderators were also examined, and the results show that age significantly moderated some of these relationships. Specifically, for older students, conscientiousness, agreeableness and openness were negatively associated with test anxiety. Our meta-analysis makes the first attempt to provide a comprehensive and nuanced synthesis of the relationship between personality traits and test anxiety, and our conclusions could help to facilitate the development of targeted interventions to cope with test anxiety.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"47 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward an Understanding of Self-Efficacy Development as a Sociocultural Process","authors":"Ellen L. Usher, Xiao-Yin Chen","doi":"10.1007/s10648-026-10121-y","DOIUrl":"https://doi.org/10.1007/s10648-026-10121-y","url":null,"abstract":"Self-efficacy, the belief people hold in their personal capabilities to accomplish specific tasks, is a central component of motivation and persistence in learning situations. Bandura (<xref ref-type=\"bibr\">1997</xref>) theorized that self-efficacy develops as individuals interpret information from four primary sources: direct experiences of mastery and failure, vicarious experiences, social persuasion, and physiological and affective states. Although these sources have been widely studied, researchers have typically examined them in narrowly defined ways, with limited attention to the broader sociocultural forces at play. Embracing a social cognitive perspective, this paper considers how social and cultural factors affect the way learners perceive, process, and respond to information and thus form beliefs about their capabilities. This perspective emphasizes how signals in the proximal environment (e.g., social models, social messages, and institutional policies), along with learners’ interpretations of their experiences, are shaped by wider sociocultural norms (e.g., epistemological, sociopolitical, communicative) through which people learn what competence and success mean. By illuminating the sociocultural underpinnings of self-efficacy, the paper underscores the need for a more nuanced conceptualization of self-efficacy development that accounts for cultural variability, thereby advancing both theoretical understanding and practical applications in diverse educational settings.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"45 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Think First, ChatGPT Later: Guiding Human–AI Collaboration for Learning Gains in Independent Human Creativity","authors":"Sarah Shi Hui Wong, Sophia Xuefei Qiu","doi":"10.1007/s10648-026-10118-7","DOIUrl":"https://doi.org/10.1007/s10648-026-10118-7","url":null,"abstract":"Generative artificial intelligence (AI) tools such as ChatGPT can boost creative performance, but do these boosts translate into learning gains? This study examined whether the benefits of ChatGPT for creativity persist even when its assistance is removed, and how people can effectively use ChatGPT to enhance their learning and independent creativity. University students (<italic>N</italic> = 196) solved a creative product improvement task either independently (human-only group) or using ChatGPT freely (general-AI group) or using ChatGPT in a guided way (regulated-AI group). Specifically, the regulated-AI group used a novel “think first, ChatGPT later” approach—they first generated their own ideas, then collaborated with ChatGPT to improve, develop, and evaluate them. Thereafter, all groups independently solved a creative product invention task. On the first task, the general-AI group produced more creative solutions than the human-only and regulated-AI groups. But without ChatGPT assistance on the second task, the general-AI group’s creativity declined to levels comparable to the human-only group. In striking contrast, despite a lack of performance gains on the first task, the regulated-AI group outperformed both the human-only and general-AI groups in independent creativity on the second task. Process analyses revealed that the general-AI group most often simply dictated ChatGPT to directly generate the solutions. Conversely, the regulated-AI group more frequently collaborated with ChatGPT to improve their self-generated ideas, in turn mediating their later advantage over the general-AI group in independent originality. Thinking of one’s own ideas first, then collaborating with ChatGPT to improve them, promotes learning gains in independent human creativity.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"23 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classroom Active Breaks as a Physical-Educational Intervention for Executive Functions and Mathematical Outcomes: a Systematic Review with Meta-Analysis","authors":"Eduardo Melguizo-Ibáñez, Félix Zurita-Ortega, Pedro Tadeu, José Luis Ubago-Jiménez, José Manuel Alonso Vargas","doi":"10.1007/s10648-026-10146-3","DOIUrl":"https://doi.org/10.1007/s10648-026-10146-3","url":null,"abstract":"The present study aimed (a) to examine, through a systematic review and meta-analysis, the effects of active breaks on attention, inhibitory control, working memory, and mathematical outcomes in schoolchildren and (b) to analyse whether break intensity, duration and modality moderate the effects of active breaks on executive function and mathematical outcomes. A systematic search was conducted in Web of Science, Scopus, ERIC, APA PsycArticles, APA PsycINFO, EBSCO, PubMed, Cochrane Library, Applied Social Sciences Index and Abstracts and ProQuest between November 2025 and February 2026. The quantitative synthesis consisted of 35 scientific articles. The total sample was 7701 students between 6 and 16 years old. Robust Variance Estimation was applied to account for dependent effect sizes within studies. Results suggest a small but statistically significant positive effect on working memory (g = 0.14, 95% CI [0.002, 0.288], <italic>p</italic> = 0.04). Exploratory meta-regression findings suggest that moderate-to-vigorous intensity, compared to moderate intensity, was associated with a small but significant improvement in working memory (β = 0.25, 95% CI [0.05 to 0.45], <italic>p</italic> = 0.02). In conclusion, active breaks may have a small positive effect on working memory, though effects on other cognitive and academic outcomes were not statistically significant. Meta-regression results suggest that higher intensity breaks could be associated with slightly greater improvements in working memory, but these findings should be interpreted cautiously. The limited and observational nature of the moderating evidence highlights the need for more rigorously designed studies to clarify how specific characteristics of active breaks relate to cognitive and academic outcomes.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"197 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing School Students’ Self-Regulated Learning through Generative AI Support: A Randomized Controlled Trial","authors":"Tim Fütterer, Lisa Bardach, Jochen Kuhn, Stefan Daniel Keller, Peter Gerjets","doi":"10.1007/s10648-026-10133-8","DOIUrl":"https://doi.org/10.1007/s10648-026-10133-8","url":null,"abstract":"Self-regulated learning (SRL) is a critical competency for academic success and lifelong learning, yet providing personalized SRL support in real-time classroom settings remains challenging. In this randomized controlled trial, we investigated whether generative-AI-(GenAI)-based interventions can effectively support SRL in secondary school students. Drawing on an integrative model of self-regulation in education, the study contrasted two types of GenAI-supported interventions—targeting either motivational (utility value) or strategic (cognitive-learning-strategy-based) aspects of SRL—with a control condition using standard ChatGPT. A total of 371 students (Grades 7–9) were randomly assigned to one of the three conditions and participated in six 45-min sessions during regular physics or English lessons. Outcome measures included self-reported utility value, strategy use (self-reported and tested performance), interest, effort, and tested domain-specific knowledge, assessed at pre- and posttest. The results showed that students in the utility value condition reported more favorable development of perceived utility value than those in the cognitive strategy condition. However, no statistically significant advantages of either intervention over the control condition were found for effort, domain-specific knowledge, or elaboration-based strategy use. Exploratory analyses indicated that students who engaged more meaningfully with the GenAI tended to have more sustained interest than those in the control group. No subject-specific (physics or English) differences in intervention effects were observed. Findings suggest GenAI-based interventions may help preserve motivational aspects of SRL under certain conditions, but further development is needed to effectively support cognitive strategies and improve learning outcomes in secondary school settings.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"224 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Virtual Reality in Education: A Stratified Meta-Analysis of Experimental Rigor and Bias","authors":"Samy Layadi, P. Huguet, K. Pavic, J. Chevalère","doi":"10.1007/s10648-026-10130-x","DOIUrl":"https://doi.org/10.1007/s10648-026-10130-x","url":null,"abstract":"Research on VR-based learning is characterized by substantial heterogeneity, inconsistent findings, and uneven methodological quality. While benefits have been reported, they vary considerably across meta-analyses (MAs), raising concerns about methodological quality and making it difficult to draw firm conclusions for research and practice. To critically assess the evidential strength of this literature, we conducted a MA stratified by methodological quality, covering four decades of research (1993–2022) and integrating 26 first-order MAs, 180 primary studies, 281 comparisons between VR and alternative instructional methods, and a total of 18,792 participants. Four MAs were performed: one including all comparisons, and three restricted to studies grouped by assessed risk of bias. When aggregating all available evidence, the results indicated a statistically significant moderate effect favoring VR (Standardized Mean Difference, SMD = 0.55), but also a modest publication bias. Statistically significant effects were observed mainly in studies classified as having a high risk of bias or some concerns (SMDs = 0.38 and 0.43, respectively). In contrast, the subset of studies rated as low risk of bias (representing the highest methodological quality) showed a nonsignificant effect (SMD = 0.35). Analyses restricted to the most rigorous studies therefore suggest both limited statistical power and inconsistent evidence. All analyses showed substantial heterogeneity, largely driven by between-study variance. To reduce methodological confounds, moderator analyses were restricted to studies of moderate to high methodological quality and focused on four theoretically motivated moderators: type of skill, outcome measure, level of VR immersion, and type of alternative instructional method. None of them significantly explained for the observed heterogeneity. Importantly, analyses based on the best-available evidence did not yield consistent or robust support for a reliable learning advantage of VR. Effects reported in the broader literature appear to be driven largely by studies of lower methodological quality, whereas higher-quality studies provide limited and inconsistent evidence. Overall, these findings indicate substantial uncertainty and suggest that current evidence is insufficient to support firm, general conclusions regarding when, how, and for whom VR enhances learning.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"29 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Race, Resistance, and the Redefinition of Motivation: The Dynamics of Goal Regulation","authors":"Akane Zusho, Revathy Kumar","doi":"10.1007/s10648-026-10143-6","DOIUrl":"https://doi.org/10.1007/s10648-026-10143-6","url":null,"abstract":"Since Maehr’s (<xref ref-type=\"bibr\">1974</xref>) pioneering work, motivation theory has acknowledged its cultural foundations. Yet dominant goal regulation frameworks often give limited attention to how systemic inequities shape students’ self-regulation. Developed within paradigms that have often bracketed race and structural power, traditional motivation theories frequently overlook the lived experiences of students from structurally marginalized communities. This paper reorients motivation theory by embedding goal regulation within a racialized ecological framework that foregrounds structural constraint, cultural wealth, and resistance. Building on Kim et al.’s (<xref ref-type=\"bibr\">2023</xref>) multiple goals regulation framework, we introduce four key processes: identity-affirming goal prioritization (deciding which goals to pursue amid competing demands), constraint-driven goal switching (recalibrating aspirations in response to systemic exclusion), epistemic goal shielding (resisting deficit narratives that devalue students’ ambitions), and resistance-driven goal adaptation (redefining success in terms of dignity, collective uplift, and self-determination). Drawing on critical and ecological models, we argue that goal regulation is not merely a cognitive process but one shaped by sociopolitical and institutional conditions. Using an illustrative case study of youth in the Bronx, grounded in both ethnographic engagement and lived experience, we show how students navigate systemic barriers with cultural resilience, critical consciousness, and community care. Rather than internalizing dominant narratives that delegitimize their identities, these students enact epistemic resistance by reimagining success on their own terms. This work extends existing models by offering a culturally grounded alternative, the Liberatory Motivation Framework, that centers race, power, and agency as essential to understanding self-regulation and educational success.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"5 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"I Feel Competent, Therefore I Am: Self-concept and Skill Interact at Different Speeds","authors":"Fernando Núñez-Regueiro, Herbert W. Marsh, Pascal Bressoux, Anatolia Batruch, Marinette Bouet, Marco Bressan, Genavee Brown, Fabrizio Butera, Anthony Cherbonnier, Céline Darnon, Marie Demolliens, Anne-Laure de Place, Olivier Desrichard, Luc Goron, Brivael Hémon, Pascal Huguet, Eric Jamet, Vincent Mazenod, Nathalie Mella, Estelle Michinov, Nicolas Michinov, Nana Ofosu, Laurine Peter, Céline Poletti, Isabelle Régner, Mathilde Riant, Anaïs Robert, Ocyna Rudmann, Camille Sanrey, Arnaud Stanczak, Farouk Toumani, Emilio Paolo Visintin, Pascal Pansu","doi":"10.1007/s10648-026-10131-w","DOIUrl":"https://doi.org/10.1007/s10648-026-10131-w","url":null,"abstract":"Do perceptions about one’s competence shape learning, or are they simply reflections of actual skills? This study revisits this longstanding question by replicating and extending preliminary findings by Marsh et al. (2024) on the temporal dynamics linking students’ academic self-concept (i.e., their perceived academic competence) and their academic skills. Using longitudinal data from a large-scale field study (<italic>N</italic> &gt; 9000 students, 3 measurement points), we tested how academic self-concept and skills relate to each other over time. Consistent with Marsh et al., results revealed a consistent temporal asymmetry: Academic skills predicted concurrent changes in self-concept within the same semester (contemporaneous effects), whereas self-concept predicted changes in academic skills across semesters (lagged effects). These findings were robust to several stress tests, including measurement error, unmeasured confounding, and competing models of change. Together, the results are consistent with a renewed theory of learning behavior, in which perceived competence and skills influence each other at different speeds. This temporal asymmetry helps integrate short-term and long-term cognitive-motivational processes in theories of learning behavior. It also underscores the importance of aligning intervention strategies and model specifications with the timescales of the underlying psychological processes, with implications for both fundamental and intervention research.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"280 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Data Extraction by Large Language Models: Assessing Accuracy in Comparison to Human Experts Using the Example of Visible Learning","authors":"Thorben Jansen, Lucas W. Liebenow, Nils-Jonathan Schaller, John Hattie, Jens Möller","doi":"10.1007/s10648-026-10136-5","DOIUrl":"https://doi.org/10.1007/s10648-026-10136-5","url":null,"abstract":"By quantitatively integrating results of meta-analyses, second-order meta-analyses (SOMAs) from educational psychology address far-reaching questions of interest to adjacent scientific fields, policy, and educational practice. Conducting a SOMA, however, is time-consuming, particularly the extraction of statistical results from meta-analyses. Large Language Models (LLMs) have the potential to accelerate data extraction, as evidenced by evaluations of data extraction from primary studies. Evaluations of their accuracy in extracting results from meta-analyses to conduct SOMA are needed. We compare the accuracy of three LLMs with that of human experts extracting data from 156 educational meta-analyses investigating students’ achievement, randomly chosen from the <italic>Visible Learning</italic> database. LLMs and humans extracted effect sizes, the number of included studies, and the number of students. To assess accuracy, we established a gold standard benchmark by resolving discrepancies between LLMs and human experts through expert adjudication. Results show that the distributions of data from all coders and the standard were similar and showed no systematic bias. Accuracy reached ICCs of 0.95/0.81 for the two human experts, and 0.96/0.97/0.96 for LLMs (Gemini2.5Pro/GPT4.1/GPTo3), with percentage agreement of 86%/80% (humans) and 81%/78%/77% (LLMs). The results demonstrate that LLMs achieve data extraction accuracy comparable to that of human experts. We discuss the conditions under which data extracted by LLMs, humans, or a hybrid of both can be considered validated for use in educational SOMAs.","PeriodicalId":48344,"journal":{"name":"Educational Psychology Review","volume":"65 1","pages":""},"PeriodicalIF":10.1,"publicationDate":"2026-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}