Two-level text summarization from online news sources with sentiment analysis

People tend to read multiple news articles on a topic since a single article may not contain all important information. A summary of all the articles related to topic will save the time and energy. Text Summarization is a way of minimizing a textual document to a meaningful summary. In this research, an extractive-based approach is used to generate a two-level summary from online news articles. News topics covered include politics, sports health, science and movie reviews from Fox News from USA, NZ Herald from New Zealand, Hindustan Times from India, BBC from UK, etc. The first-level summary generates the summary of each article on all these topics. Sentiment Analysis is performed on the first-level summary to understand the variation in related news articles from different news agencies. The second-level summary generates the summary of the combined first-level summaries of two/three related articles on a topic. The ROUGE metric is used to evaluate the performance of summarization.