Two-Level Text Summarization with Sentiment Analysis for Multi-Document Summarization
Lavanya K C1, C. Sivamani2, Linnet Tomy3, Ann Rija Paul4
1Lavanya K C, PG Scholar, Sahrdaya College of Engineering and Technology, Thrissur, (Kerala), India.
2Dr. C.Sivamani, Assistant Professor in BMIE, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, (Tamil Nadu), India.
3Ms. Linnet Tomy, Assistant Professor in CSE, Sahrdaya College of Engineering and Technology, Thrissur, (Kerala), India.
4Mrs. Ann Rija Paul, Assistant Professor in CSE, Sahrdaya College of Engineering and Technology, Thrissur, (Kerala), India.
Manuscript received on 24 January 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 January 2019 | PP: 103-107 | Volume-7 Issue-6, March 2019 | Retrieval Number: E1928017519©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Text summarization is way of reducing the text content of a document without the losing any information. People are likely to look multiple documents on a single topic because a one document may not include all the major details. The abstract/summary of multiple documents connected to a text will conserve the effort and time. Automatic text summarization is one of the area of natural language processing. Sentiment analysis is a machine learning method in which machine study and inspect the sentiments, opinions, etc about reviews about movies or products. This is extremely hard summarize by human. effective data from the very large document. In this research, we propose a novel method for multiple document summarizations using extractive method of summarization and sentiment analysis from online sources. At first, various document’s URLs are fetched as input relate to a text and generate individual summaries. The sentiment analysis is tried on these generated separate summaries. The sentiment analysis says that whether these input documents have any dissimilar opinion about the topic. Lastly, a unique summary is generated from all these first level summaries. The performance of our proposed method evaluated by ROUGE metric.
Keywords: Text Summarization, Sentence Extraction, Sentiment Analysis, Natural Language Processing, ROUGE
Scope of the Article: Predictive Analysis