Over the past few years, there has been a significant increase in the utilization of artificial intelligence (AI)-based educational applications in education. As pre-service teachers’ attitudes towards educational technology that utilizes AI have a potential impact on the learning outcomes of their future students, it is essential to know more about pre-service teachers’ acceptance of AI. The aims of this study are (1) to discover what factors determine pre-service teachers’ intentions to utilize AI-based educational applications and (2) to determine whether gender differences exist within determinants that affect those behavioral intentions. A sample of 452 pre-service teachers (325 female) participated in a survey at one German university. Based on a prominent technology acceptance model, structural equation modeling, measurement invariance, and multigroup analysis were carried out. The results demonstrated that eight out of nine hypotheses were supported; perceived ease of use (β = 0.297***) and perceived usefulness (β = 0.501***) were identified as primary factors predicting pre-service teachers’ intention to use AI. Furthermore, the latent mean differences results indicated that two constructs, AI anxiety (z = − 3.217**) and perceived enjoyment (z = 2.556*), were significantly different by gender. In addition, it is noteworthy that the paths from AI anxiety to perceived ease of use (p = 0.018*) and from perceived ease of use to perceived usefulness (p = 0.002**) are moderated by gender. This study confirms the determinants influencing the behavioral intention based on the Technology Acceptance Model 3 of German pre-service teachers to use AI-based applications in education. Furthermore, the results demonstrate how essential it is to address gender-specific aspects in teacher education because there is a high percentage of female pre-service teachers, in general. This study contributes to state of the art in AI-powered education and teacher education.

Reflective practice holds critical importance, for example, in higher education and teacher education, yet promoting students’ reflective skills has been a persistent challenge. The emergence of revolutionary artificial intelligence technologies, notably in machine learning and large language models, heralds potential breakthroughs in this domain. The current research on analyzing reflective writing hinges on sentence-level classification. Such an approach, however, may fall short of providing a holistic grasp of written reflection. Therefore, this study employs shallow machine learning algorithms and pre-trained language models, namely BERT, RoBERTa, BigBird, and Longformer, with the intention of enhancing the document-level classification accuracy of reflective writings. A dataset of 1,043 reflective writings was collected in a teacher education program at a German university (M = 251.38 words, SD = 143.08 words). Our findings indicated that BigBird and Longformer models significantly outperformed BERT and RoBERTa, achieving classification accuracies of 76.26% and 77.22%, respectively, with less than 60% accuracy observed in shallow machine learning models. The outcomes of this study contribute to refining document-level classification of reflective writings and have implications for augmenting automated feedback mechanisms in teacher education.

Reflective writing is a relevant aspect of pre-service teachers’ professionalization. Evaluating reflective writing in teacher education is demanding due to a shortage of resources. Hence, this study explores the practical possibilities of evaluating reflective writing using a mixed-methods approach to analyze reflective writing from 198 pre-service teachers at a German university. We used qualitative content analysis, computational linguistic approaches, and BERTopic. Results of qualitative content analysis results indicated primarily descriptive and low-level participants’ reflective writing. Next, computational linguistic analyses revealed that affective and cognitive terminology utilization differed across varying levels of reflection, with a higher frequency of such terms correlating with deeper levels of reflection. BERTopic results showed that reflective content mainly centered on learning materials and shifted toward affective and motivational themes related to higher levels of reflection. This study demonstrates that reflective writing can be evaluated across reflection levels and cognitive, affective, and thematic dimensions, combining qualitative content analysis, computational linguistic approaches, and BERTopic.

Nowadays, “being digital” has been largely realized, especially in education. The continuous renewal of Information and Communication Technology (ICT) and artificial intelligence (AI) has led to an educational revolution. Therefore, teaching and learning activities are no longer restricted by time, space, CE, and humans. As a result, future qualified teachers with high self-regulation competence and strong digital competence are in great need. However, research studies reveal that many teachers directly replicate traditional classrooms and fail to conduct virtual activities with possible digital resources and the application of AI. Confronted with such challenges, future teachers do often not accept AI and feel unprepared for future teaching. This chapter provides an overview of research theories, assessment techniques, and support instruments in related research areas.