The Implementation of Automatic Text Summarization Technology is essential for extracting knowledge and classifying text, offering a potential remedy for the issue of information overload. The availability of vast amounts of text data from various sources has significantly increased in recent years. Within this extensive corpus of text lies a plethora of details and insights that need to be efficiently condensed for practical use. Document summarization involves the condensation of text while retaining its informational essence. Summarization processes sift through the most pertinent segments of a text, transforming them into succinct summaries that encapsulate the document's primary purpose. Extraction-driven text summarization involves selecting sentences of utmost significance based on term and phrase attributes and consolidating them to form a summary, a process often facilitated by the Fuzzy inference engine. The effectiveness of a document's summary is determined by the relative importance of its constituent sentences. This article explores the semantic approach to text summarization through Latent Semantic Processing, as well as the Fuzzy logic Extraction method. Comparative analysis reveals that our proposed summarizer outperforms the fuzzy-based summarizer, boasting higher average recall (44.51 vs. 42.87), average precision (90.83 vs. 87.24), and f-measure (67.66 vs. 65.23). This enhancement in summarization capabilities contributes to the generation of high-quality summaries, thereby saving valuable time for readers.