Biomedical Text Summarization Based on the Itemset Mining Approach

Abstract

The expanding amount of text-based biomedical information has prompted mining valuable or intriguing frequent patterns (words/terms) from extremely massive content, which is still a very challenging task. In the chapter, the authors have conceived a practical methodology for text mining dependent on the frequent item sets. This chapter presents a strategy utilizing item set mining graph-based summarization for summing up biomedical literature. They address the difficulties of recognizing important subjects or concepts in the given biomedical document text and display the relations between the strings by choosing the high pertinent lines from biomedical literature using apriori itemset mining algorithm. This method utilizes essential criteria to distinguish the significant concepts, events, for example, the fundamental subjects of the input record. These sentences are determined as exceptionally educational, applicable, and chosen to create the final summary.