ANALSYING THE PARALLEL FUSION LOGIC AND FUSION K-MEANS (FKM) WITH LANGUAGE DOCUMENT

Text summarization is a method of retrieving information, and it very effective. approach techniques fall into two categories: abstract abstract. This white paper focuses on extraction so that the output application key sentence taken verbatim from original text without verbal modification. There are four main processes in this research. These preprocessing phase, scoring function, optimization by methods (logic fused K-Means), results. In study, seven features used to calculate score for each sentence. The core study compare reliability logic k-means optimizing aggregation results process. showed Fusion Logic outperformed K-Means had highest similarity human summarization, with percentage accuracy 48.25% 44% K-Means. It was %.33%. Accuracy improves additional compression 0.67% Method 3.5% Keywords: Language, Features, Scores Sentences, Logic, K–Means