Abstract
News articles regarding a political party, a political issue, a business house, or a particular product can be judged as the feeling of writers over a time. News article can also be treated as a form of public opinion as by reading those news articles; the public opinion is influenced relating to a particular topic. So that news article can be analyzed to extract the sentiment or for opinion mining by using different supervised learning models. This paper proposes the methods to extract opinion content from Odia news article available in portal and e-paper sites using supervised learning models. A total of 500 related news articles are collected from different newspapers manually. Out of that, 350 news articles are used from training the classifier and 150 news articles are used for testing the classifier. Those collected news articles are preprocessed and then vectorized with respect to tf–idf score which is calculated using unigram and bigram representation of data at document level passed to SVM, and the results are analyzed by calculating the accuracy and F1 score.
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 callDisclaimer: 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.
