Enhancing English listening comprehension via AI - based adaptive learning platforms incorporating speech - to - text and predictive analytics

The research on the application of adaptive genetic algorithms and artificial intelligence in an English text analysis learning system (ETALS) focuses on two main areas: discourse analysis and cultural communication. The goal is to develop a system that enhances students' abilities to analyze and understand various English texts while fostering cultural awareness and effective communication skills. The study proposed the Adaptive Genetic Algorithm Optimized Descent K-Nearest Neighbor (AGAOD-KNN) to analyze the English speech to text analysis system. The dataset is collected and preprocessed by the normalization and feature extraction using the Linear Discriminant Analysis (LDA) and novelty using the AGAOD-KNN. The research advances the field of English language instruction by demonstrating the potential of computational methods for text analysis and cross-cultural communication. The study offers suggestions on how to use AGAOD-KNN to enhance learning process for discourse analysis and cross-cultural communication for language educators and system designers. The AGAOD-KNN algorithm and LDA feature extraction are responsible for the system's stellar performance in the setting of an English text analysis learning system, with metrics like 98.88% accuracy, 97.4% precision, 93.6% recall, 91.9% sensitivity and F1-score of 87.5%. The outcomes of the system are used to establish these measures. This work shows AGAOD-KNN can improve the English speech to text analysis System. ETALS armed with these computational methodologies can support language learners in building their discourse analysis abilities and intercultural communication competencies by automating and streamlining the text analysis process and offering individualized feedback.