TF-IDF Vectorization and Clustering for Extractive Text Summarization

Abstract

Extractive document summarization is a vital technique for condensing large volumes of text while retaining key information. This research introduces a dynamic feature space mapping approach to enhance extractive document summarization, aiming to succinctly encapsulate key information from extensive text volumes. The proposed method involves extracting various document properties like term frequency, sentence length, and position to comprehensively describe content. By employing a mapping function, these features are projected into a dynamic feature space, enhancing summarization efficiency and feature clarity. Clustering similar phrases in this space facilitates easier sentence grouping, aiding summary creation. Leveraging TF-IDF vectorization, the most representative phrases are chosen from each cluster based on importance and diversity. This process culminates in generating a high-quality document summary quickly and systematically. The dynamic mapping method streamlines sentence grouping, systematically capturing essential document attributes. This approach addresses challenges in extractive summarization, contributing significantly to automated text summarization. Its applicability spans domains requiring rapid extraction of information from vast textual data.