Abstract
The study is aimed at developing a text summarizer using clustering and anomalies detection with SVM classification. A text summarization approach is proposed which uses the SVM clustering algorithm. The proposed project can be used to summarize articles from fields as diverse as politics, sports, current affairs, finance and any other explanatory document. However, it does cause a trade-off between domain independence and a knowledge-based summary which would provide data in a form more easily understandable to the user. A bundle of libraries and software’s was utilized for proper text summary of alphanumeric entering.
KEYWORDS— Anomalies detection, SVM (support vector machine), clustering, text summarization, data mining