This research quantitatively examines how technology-mediated formative assessment techniques affect student learning outcomes in middle school education. The research investigates the correlation between instructors’ technology use, attitudes, and student performance in several academic disciplines using surveys and evaluations conducted with teachers and students. Results show strong positive connections between how often technology is used, the specific digital tools used, how effective technology-mediated formative assessment is judged to be, and the results of student learning. On the other hand, obstacles to implementation were shown to have a negative relationship with student accomplishment. The research emphasizes that technology-mediated formative assessment is more successful in some subjects, emphasizing the necessity to customize teaching methods for each subject’s requirements. The study revealed a positive correlation between student learning outcomes and the frequency of technology use, the types of digital tools used, and the perceived effectiveness of technology-mediated formative assessment. These results suggest ways to improve the use of technology and formative assessment in middle school instruction.

Recognizing the discipline category of the abstract text is of great significance for automatic text recommendation and knowledge mining. Therefore, this study obtained the abstract text of social science and natural science in the Web of Science 2010-2020, and used the machine learning model SVM and deep learning model TextCNN and SCI-BERT models constructed a discipline classification model. It was found that the SCI-BERT model had the best performance. The precision, recall, and F1 were 86.54%, 86.89%, and 86.71%, respectively, and the F1 is 6.61% and 4.05% higher than SVM and TextCNN. The construction of this model can effectively identify the discipline categories of abstracts, and provide effective support for automatic indexing of subjects.