Real-Time Text Classification and Summarization Model by Enhancing TF-IDF Extractive Summarization Method

The rapid growth of textual data across various platforms necessitates efficient real-time text classification and summarization methods. This paper presents a novel approach for developing a real-time text classification and summarization model that addresses the limitations of traditional methods, such as TFIDF, in extractive summarization. The proposed algorithm implemented advanced preprocessing techniques and a similarity matrix for enhanced pattern recognition, which leads to more accurate and contextually relevant summaries. Additionally, the model has integrated logistic regression that ensures the precise topic identification.