Conceptual learning in pre-service teacher groups through a Text Mining intervention

Concept acquisition is a critical aspect in the education of teachers yet is especially challenging in group contexts in which traditional teaching strategies often fail to convey complex notions effectively. This study investigates the potential of text mining (TM) based learning analytics as a teaching tool to enhance conceptual learning in pre-service teachers. To do so, it analyses how the learning of complex and abstract educational concepts was affected by a TM-based learning analytics intervention, in comparison with traditional teaching strategies, including the elaboration of an individual project, and the attendance of a master class. Quasi-experimental pre- and post-tests were thus administered to three non-equivalent groups (A, B, and C, respectively) of a total of 81 master’s students enrolled in a distance education teacher training programme at a Spanish university, and token corpora were analysed using TM techniques in collected definitions of abstract educational concepts (1017 pre-test and 1133 post-test tokens from Group A; 1127 pre-test and 1111 post-test tokens from Group B; and 1101 pre-test and 1173 post-test tokens from Group C). It was found that the TM-based learning analytics intervention significantly enhanced the students’ keyword selection in submitted definitions (t Yuen = –6.37, p < .001, δR AKP = –1.03, CI95% = –2.10, –.74) and the association of relevant terms (with post-test Jaccard values ranging from .217 to .917) compared to the other teaching approaches. This study therefore offers empirical evidence that TM-based learning analytics can be an effective pedagogical tool that promotes an enhanced learning of abstract concepts in the education of teachers. The results underscore the value of TM-based educational technology in optimizing conceptual learning and resource efficiency in higher education settings.