Facial micro-expression states as an indicator for conceptual change in students’ understanding of air pressure and boiling points Mei-Hung Chiu, Hongming Leonard Liaw, Yuh-Ru Yu and Chin-Cheng Chou Mei-Hung Chiu is a professor in the Graduate Institute of Science Education at National Taiwan Normal University specialized in conceptual change, models and modeling and alternative assessment in science education. She has published peer-reviewed articles in British Journal of Education Technology, Chemical Education Research and Practice, International Journal of Science Education, Journal of Research in Science Teaching, and Science Education. She also has edited four books on science education, such as Science Education Research and Practice in Asia: Opportunities and Challenges by Springer. Hongming Leonard Liaw is a post-doctoral research fellow at National Taiwan Normal University specializing in educational technology. Yuh-Ru Yu is a post-doctoral research fellow in the Graduate Institute of Science Education at National Taiwan Normal University with expertise in statistical computing and simulations. Chin- Cheng Chou is an associate professor in the Department of Science Education at National Taipei University of Education whose research foci are chemistry education, curriculum design and development and technology-assisted instruction. Address for correspondence: Prof Mei-Hung Chiu, Graduate Institute of Science Education, National Taiwan Normal University, 88, Sec. 4 Ting-Chou Road, Taipei 11677, Taiwan. Email: mhchiu@ntnu.edu.tw Abstract Utilizing facial recognition technology, the current study has attempted to predict the likelihood of student conceptual change with decision tree models based on the facial micro-expression states (FMES) students exhibited when they experience conceptual conflict. While conceptual change through conceptual conflicts in science education is a well-studied field, there is little research done on conceptual change through conceptual conflict in terms of students’ facial expressions. As facial expressions are one of the most direct and immediate responses one can get during instruction and that facial expressions are often representations student’s emotions, a link between students’ FMES and learning was explored. Facial data was collected from 90 tenth graders. Only data from the 72 students who made incorrect predictions were analyzed in this study. The concept taught was the relationship between boiling point and air pressure. Through facial recognition software analysis and decision tree models, the current study found Surprised, Sad and Disgusted to be key FMES that could be used to predict student conceptual change in a conceptual conflict-based scenario. Introduction In a conceptual conflict-based instructional scenario, conceptual conflicts often precede the intro- duction of the targeted concept. It is hoped that learners’ emotional state would be aroused in such a way that they would be willing and ready to explore, understand and accept the newly introduced and scientifically accurate concepts; in other words, to become conceptually changed. Yet, conceptual change is far from a guarantee, even in conceptual conflict based instructions (Kang, Scharmann, Kang, & Noh, 2010). A variety of factors can influence learning outcomes and learners’ emotions are one of the major factors (Bellocchi & Ritchie, 2015; Chen et al., 2012; Chiu, Yu, Liaw, & Lin, 2016; Liaw, Chiu, & Chou, 2014; Pekrun, Goetz, Titz, & Perry, 2002). V C 2017 British Educational Research Association British Journal of Educational Technology doi:10.1111/bjet.12597 Vol 50 No 1 2019 469–480