Abstract
It is claimed that online news holds valuable contents of information to some extent; as a matter of fact, it reflects the polarity of investigators from time to time. Especially, such information in the stock market outlines an event usually hold on to unobserved effects, e.g. law problem, which might not be immediately and completely price-revealed. Instead of traditional pure price-based indicators, this paper is to apply some sentiment technical indicators at hand into working out a news-based box through the fuzzy design. It pays to notice that the sentiment indicators automatically come out from the contents of online news. It comes out a weight on keywords in text through a combination of natural language processing techniques and membership functions together. For example, given a topic of target firm, the box collects news and mines patterns and then infers the degree of sentiment. To examine the feasibility of such concept, an experiment is built to test the rate of accuracy, using the data fully quoted on the online news took place for 3 month long. It results that the proposed fuzzy inference algorithm achieve 88% rate of accuracy in inferring the polarity of the whole news. This method is also feasible for the other languages, e.g. English and Japanese.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advancements in Computing Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
