Evaluation of Learning Outcomes in Higher Education through the Integration of Interactive Mobile Technology and Big Data Analytics

With the rapid advancement of mobile Internet technology, interactive learning platforms, and big data analytics, they have become essential tools in modern higher education, particularly in the evaluation of learning outcomes. Traditional evaluation methods primarily rely on offline testing and questionnaire surveys, which often lack real-time adaptability, specificity, and multi-dimensional analysis, making it difficult to comprehensively reflect learners’ academic progress. Recent developments in big data technology and artificial intelligence have led researchers to explore data-driven approaches for evaluating learning outcomes. However, existing methodologies remain limited in feature selection, feature fusion, and model optimization, hindering their ability to fully capture learners’ behavioral features and academic performance. To address these limitations, a learning outcome evaluation model based on multi-semantic feature interaction and big data analytics was proposed. The model was designed with a feature embedding module, a multi-semantic feature interaction module, a two-dimensional squeeze-and-excitation module, and a feature fusion module to enhance evaluation accuracy and comprehensiveness. The feature embedding module extracts latent features by embedding multidimensional learner behavior data. The multi-semantic feature interaction module captures complex learning patterns by facilitating interactions among various features. The two-dimensional squeeze-and-excitation module optimizes feature representation, improving evaluation sensitivity. The feature fusion module integrates diverse features to enhance evaluation accuracy. Through these innovations, this study not only introduces a novel perspective for evaluating learning outcomes in higher education but also provides valuable insights for further research in educational technology.