2025/03/01 by Yi Zheng, Sijia Huang, Steven Nydick +1 · 1 voice
Engineering · Decision Sciences · Business, Management and Accounting · #Advanced Data Processing Techniques #Scientific Computing and Data Management #Big Data and Business Intelligence
paper · pdf · doi:10.59863/gvze8492
openalex publication_date 2025/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31
The field of educational measurement (hereafter shortened as measurement) has seen rapid growth in applications of machine learning (ML) recently. However, it is imperative to examine potential gaps between ML and the fundamental principles of measurement. The MxML project seeks to shed light on how to close the gaps between the two to harness the power of ML to serve measurement practices. Phase 1 of the project was a systematic review of the recent 10 years of measurement literature, in which we provided a snapshot of the literature in (1) areas of measurement where ML is discussed, (2) types of articles, (3) ML methods discussed, and (4) potential gaps between measurement and ML. This paper reports the findings from Phase 2 of the project, a survey of the international measurement community to understand measurement professionals’ experiences, attitudes, and thoughts toward incorporating ML techniques into measurement.