 An AI-enhanced granular analysis of Thailand’s mathematics performanceOecd No 348, OECD Education Working Papers from OECD Publishing Abstract: This paper applies the Collective Intelligence Model for Education (CIME) to Thailand’s Programme for International Student Assessment (PISA) 2022 mathematics data and assessment materials to generate fine-grained diagnostic evidence for curriculum review and instructional support. The study combines AI-assisted scoring, expert review and psychometric scaling, using bilingual item-facet rubrics, with Thai serving as the operational scoring language. The resulting profiles examine student performance across 12 content topics and 17 cognitive operators. Findings indicate relative strengths in geometry-related content, measurement, estimation, chance and probability, and selected procedural tasks. More demanding areas include formulating situations mathematically, interpreting results in context, recognising functional relationships, and working with algebraic, functional and data-representation content. The analysis also identifies limited gender differences in most areas, alongside substantial variation by economic, social and cultural status. Overall, the paper shows how large-scale assessment data can be translated into competency-oriented evidence for Thailand’s ongoing education reform Keywords: Artificial Intelligence; Educational Assessment; Mathematics Education; PISA; Psychometrics; Thailand (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:oec:eduaab:348-en Access Statistics for this paper More papers in OECD Education Working Papers from OECD Publishing Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.