Abstract

The aim is to build a system that takes the source text as an input and the result will be a summery which contains sentences preserve the main theme of the source. We use a statistical approach to solve the problem of Arabic text summarization. Many researches which study Arabic text summarization problem focus on how writers of articles write, here we make a system take the advantage of how readers of an article read and make comments on article. Our approach assign scores for each segment of an article depending on the location of the sentences, the size of each sentence and term frequency on the article and comments of readers. Our system tested by 100 human evaluators, We gave each evaluator a copy of the summary produced by our system, with a question about the connectivity of ideas and sentences in and asked them to evaluate the summary. We asked them to answer by rejected, not-related, satisfactory, good, accepted, to test our approach which focus on readers' comments to summarize articles.

Keywords:

Comment relatedness, extract , term frequency , text summarization,

References

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.