Application of Crawling Techniques and Natural Language Processing for the Analysis of Information Extracted from the Social Network Twitter
This work presents the development of a computational model driven to analyzeinformation obtained from Twitter social network. The method used to extract comments from Twitter is bases on the Rest and Streaming APIs and a web scraping tool. These comments are indexed and sent to a non-relational database that handles large volumes of information. The ability to extract information from the tools was verified by creating a corpus with Twitter comments for social analysis. It is concluded that it is possible to extract information from tweets by applying tools designed for crawling and natural language processing NLP.
Keywords - Crawling, Information extracting NLP, Twits.