Sentient Companion – That Helps in Education

Dyslexia is a common learning difference that affects the ability to read, spell, and decode language efficiently, often creating significant barriers to academic success. One of the major challenges for students with dyslexia is processing large volumes of written information, which can lead to cognitive overload, reduced comprehension, and a lack of confidence in learning. To address these issues, this project presents the development of an intelligent Text Summarization Tool specifically designed for students with dyslexia. The tool utilizes advanced Natural Language Processing (NLP) techniques, including extractive and abstractive summarization models, to convert lengthy and complex textual content into concise, coherent summaries that retain essential meaning and context. What differentiates this summarizer is its focus on accessibility and user-centric design for dyslexic learners. The system integrates features such as adjustable text size, line spacing, and contrast; the use of dyslexia-friendly fonts like Open Dyslexic; simplified sentence structures; and integrated text- to-speech capabilities that allow users to listen to the summary. Furthermore, the tool allows users to customize the summarization level, providing flexibility based on individual reading ability or learning level. This hybrid approach-combining linguistic simplification, multimodal support, and user personalization-aims to reduce cognitive strain, increase reading speed, and improve comprehension. Early usability testing indicates a positive impact on user engagement and learning outcomes. Ultimately, this solution promotes inclusive education by empowering students with dyslexia to interact with academic content more independently and effectively, fostering confidence and academic growth. The text data online is increasing massively; hence, producing a summarized text document is essential. We can create the summarization of multiple text documents either manually or automatically. A manual approach may be tedious and a time- consuming process. The resulting composition may not be accurate when processing lengthy articles; hence the second approach, i.e., the automated summary generation process, is essential. Training machine learning models using these processes makes space and time-efficient summary generation possible. There are two widely used methods to generates summaries, namely, Extractive summarization and abstractive summarization. The extractive technique scans the original document to find the relevant sentences and extracts only that information from it. The abstractive summarization technique interprets the original text before generating the summary. This process is more complicated, and transformer architecture-based pre trained models are used for comparing the text & developing the outline. This research analysis uses the BBC news dataset to evaluate and compare the results obtained from the machine learning models.