Education System based on Pre- Training with Extracted Gap-Sentences for Abstractive Summarization Sequence-to-Sequence and Bidirectional Auto-Regressive Transformers

In present scenario, the traditional education system has criticized for its one-size-fits-all approach, failing to provide to individual students' needs. The advent of technology has brought about opportunities to revolutionize education that aims to investigate the feasibility of developing an education system by addressing the existing challenges that overreliance on technology, inadequate teacher training, unequal access to digital resources existing inequalities and academic challenges. To overcome those drawbacks, this paper proposed a robust educational system by harnessing effective methods. Initially, preprocessing techniques like tokenization, stop word removal, stemming, and lemmatization are applied to the data. The processed data is then fed into the Extended Technology Acceptance Model (ETAM), which extracts optimal attributes like academic performance and grades. Leveraging these extracted parameters to an education system for developing advanced text generation models, Pre-Training with Extracted Gap-Sentences for Abstractive Summarization Sequence- To-Sequence (PEGASUS) and Bidirectional and Auto-Regressive Transformers (BART). This proposed model enables the generation of high-quality educational content, facilitating personalized learning experiences by combining these cutting-edge techniques. The performance of proposed model Pegasus-BART evaluated with the various metrics such accuracy with value of (96.56%), Precision is (94.63%), Recall is (96.04%), and F1 score is (95.77%) respectively.