Enhanced Feature-Based Automatic Text Summarization SystemUsingSupervised Technique

Abstract

In this work, we propose an efficient text summarization methodby ranking sentences according to their scores that use a combination of existing and improved sentence features.  Many works in the literature proposed improvements to text summarization but this field still needs more improvement. For this purpose, we propose improvements to Sentence position, Sentence length, and Key wordsentence features. Afterwards, we find the optimal combination between these features and some existing features such as Term frequency, Sentence centrality, Title similarity, and Upper case of word. By usingmachine learning techniques, mainly SVM, Naive Bayes and Decision Tree classifiersour paper evaluates two feature groups: a combination of seven features without any improvements,and the same seven features after making some improvements onSentence position, Sentence length, and Key word sentence features to enhance the performance of text summarization system.Experimental results showed that making enhancements on some features improved the accuracy.