Automatic text summarization is essential for knowledge extraction and text classification. It provides the solution to the issue of data and information overloading. The volume of text data accessible has risen significantly in recent years from several sources. A large amount of text contains a variety of detail and insights that must be effectively documented. Text Summarization is the act of shrinking a text while maintaining the information values and transforming them into concise summaries that state the document's key objective. The proposed model extraction-driven text summarization entails extracting high-ranking sentences from a document based on term and phrase attributes and combining them to provide a description. The Fuzzy inference engine is used to model the document's summary and calculated by the relative value of the sentences in the document. The semantic approach to utilizing Latent Semantic Processing is explored, and the Fuzzy logic Extraction approach for text summarization. The proposed system suggested system has an average recall of 44.51, an average precision of 90.83, and an f-measure of 67.66. Our proposed summarizer's overall enhanced recall, precision, and f-measure efficiency than the fuzzy-based summarizer.