Graph-Based Extractive Text Summarization Sentence Scoring Scheme for Big Data Applications

The recent advancements in big data and natural language processing (NLP) have necessitated proficient text mining (TM) schemes that can interpret analyze voluminous textual data. Text summarization (TS) acts as an essential pillar within recommendation engines. Despite the prevalent use of abstractive techniques TS, anticipated shift towards a graph-based extractive TS (ETS) scheme is becoming apparent. models, although simpler less resource-intensive, are key assessing reviews feedback on products or services. Nonetheless, current methodologies not fully resolved concerns surrounding complexity, adaptability, computational demands. Thus, we propose our scheme, GETS, utilizing model to forge connections among words sentences through statistical procedures. structure encompasses post-processing stage includes sentence clustering. Employing Apache Spark framework, designed for parallel execution, making it adaptable real-world applications. For evaluation, selected 500 documents from WikiHow Opinosis datasets, categorized them into five classes, applied recall-oriented understudying gisting evaluation (ROUGE) parameters comparison with measures ROUGE-1, 2, L. results include recall scores 0.3942, 0.0952, 0.3436 L, respectively (when using clustered approach). Through juxtaposition existing models such BERTEXT (with 3-gram, 4-gram) MATCHSUM, has demonstrated notable improvements, substantiating its applicability effectiveness scenarios.