Teachers and students in the 21st century are shifting their attention from the classroom to digital education, aiming for meaningful, high-quality, and dynamic learning. With the introduction of digital learning, the educational system has undergone significant transformations. Some teachers/instructors, on the other hand, are still experiencing difficulties. For this reason, this research finds a solution named AAC integrated Big Data Analytics Framework (AACBDAF) for people with neural disorders in the English language. AAC-BDAF gathers all the linguistic data and categorizes it based on how frequently it is used. To input data, the AAC system uses eyeball tracking to display symbols and characters on a screen. To help the listener follow along, the selected option/word is converted into a text-to-speech paradigm. The detection algorithms of machine learning and deep learning are evaluated for word detection and suggest the convolutional neural network (CNN) support AACBDAF. According to simulation findings, the proposed AAC-BDAF recognizes phrases and predicts the word from their eye-gazing with higher accuracy of 98.63%.