The rapid expansion of digital information across online platforms, research databases, and social media has created a significant challenge known as information overload, where users struggle to process large volumes of textual data efficiently. Automated text summarization has emerged as an effective solution that enables machines to condense lengthy documents into shorter, meaningful summaries while retaining essential information. This study presents the design and implementation of an Automated Text Summarizer using Natural Language Processing (NLP) techniques and transformer-based deep learning models. The proposed system utilizes state-of-theart architectures such as Text-To-Text Transfer Transformer (T5) and Bidirectional and AutoRegressive Transformer (BART) to generate abstractive summaries that capture the semantic meaning of the source text rather than simply extracting sentences. The system is implemented using the Hugging Face Transformers library with PyTorch as the deep learning framework, enabling efficient training and deployment of the models. Preprocessing techniques including tokenization, stop-word removal, and sentence segmentation are applied to improve input quality. The model is trained and fine-tuned on benchmark summarization datasets to improve contextual understanding and linguistic coherence. A userfriendly interface allows users to input long documents and obtainconcise summaries instantly. Experimental results demonstrate that transformerbased abstractive summarization models significantly improve summary quality compared with traditional extractive approaches. The system can be applied in various domains including education, journalism, legal documentation, and business analytics. Overall, the proposed solution contributes to efficient knowledge consumption by enabling automated extraction of meaningful insights from large textual datasets.
IJERST (Sat,) studied this question.