Big Data Summarization Using Novel Clustering Algorithm and Semantic Feature Approach

摘要

This paper proposes a big data (i.e., documents, texts) summarization method using proposed clustering and semantic features. This paper proposes a novel clustering algorithm which is used for big data summarization. The proposed system works in four phases and provides a modular implementation of multiple documents summarization. The experimental results using Iris dataset show that the proposed clustering algorithm performs better than K-means and K-medodis algorithm. The performance of big data (i.e., documents, texts) summarization is evaluated using Australian legal cases from the Federal Court of Australia (FCA) database. The experimental results demonstrate that the proposed method can summarize big data document superior as compared with existing systems.