Encyclopedia:
From Scholars for Scholars

The apprenticeship of observation is a form of anticipatory socialization that is experienced by all individuals who attend K-12 schooling, and is particularly consequential for the subset of this population that eventually becomes professional educators. Based on extensive interviews with professional teachers, sociologist Dan C. Lortie found that the 13,000 h of experience teachers had spent watching their own K-12 teachers constituted a sort of apprenticeship in teaching. This prolonged period of observation is thought to have a profound impact on the work of teachers. By observing their own teachers across thousands of hours, professional educators are said to make decisions in the classroom and in their teaching based on their own individual personalities and preferences instead of pedagogical frameworks or theories; the teacher learning brought about by the apprenticeship of observation leads professional educators to identify teaching they liked and disliked. Teaching decisions made by these educators in the classroom are ultimately based on a binary choice between replicating or rejecting the teaching they previously witnessed as K-12 students. Over time, the apprenticeship of observation has, for some researchers and teacher educators, served as shorthand for describing the replication of traditional teaching approaches across time, in effect suggesting that teachers teach the way they were taught. The power and negative consequences of the apprenticeship of observation have led teacher educators to devise multiple interventions within teacher education programs and pedagogies, which have sought to challenge and overcome the apprenticeship of observation and its negative influence on professional educators’ teacher learning and practice.

Artificial Intelligence (AI)-based crack detection in buildings uses computer vision and deep learning to automatically identify structural cracks from inspection images. In recent years, many studies have explored this topic, but the overall development of the field, its methodological practices, and the remaining challenges are still not fully clear. Unlike most previous reviews that focus mainly on technical methods, this study combines a large-scale scientometric mapping of the research field with a focused technical analysis of recent AI-based crack detection methods specifically applied to building structures. This study therefore provides a dual-layer review covering research published between 2015 and 2025. A total of 146 Scopus-indexed publications were analysed using Visualization of Similarities viewer (VOSviewer) to examine publication growth, thematic evolution, collaboration patterns, and citation structures. In addition, a focused technical review of 36 highly relevant studies was carried out to analyse task formulations, model families, datasets, evaluation protocols, and methodological practices. The results show a rapid increase in research activity after 2020, largely driven by advances in deep-learning and Unmanned Aerial Vehicle (UAV)-based inspections. At the same time, collaboration networks remain uneven, and citation influence is concentrated in a limited number of research communities. The technical review further shows that most studies focus on detection-level tasks, particularly You Only Look Once (YOLO)-based models, while predictive diagnostics, automated inspection reporting, and decision-oriented Structural Health Monitoring (SHM) are still rarely addressed. Current datasets and evaluation protocols also remain mostly perception-oriented, which makes it difficult to assess robustness, generalisability and long-term predictive capability.