Automatic Text Summarization and Keyword Extraction using Natural Language Processing

The process of gaining and absorbing the knowledge from various sources is a time-consuming process where people, mainly youth spend time surfing over the internet for relevant information. The proposed system mainly focuses on scraping the data from websites and providing the summary as well as keywords from the information extracted from various websites giving the user flexibility to select the website of their choice. The proposed system for the text summarization and keyword extraction undergoes a sequence of steps starting from data extraction from a website link, removal of outliers and irrelevant information, emphasizing on the importance of particular data extracted from the website and creating a summary of the extracted data. For the selection of relevant information from the extracted data, it is necessary to use natural language processing. The proposed project helps its users to reduce their surfing time and gives summary prepared from multiple website links and documents or keywords from a particular website or a document.