• SARVASIDDHI SRIDEVI
• L. SOWJANYA

In current days sentiment analysis is the domain which gained a lot of user’s attention towards it in gaining the users interest for taking any decision or purchase. The term sentiment is nothing but feedback or opinion about an product or post which is posted on the online web. As we all know that almost all users are mostly concentrated about online reviews for taking decision about new purchases or to follow any new trend, a lot of web sites are providing fake reviews by manipulating the product reviews based on his/her interest. This current paper try to develop new methods like semi-supervised and supervised text mining models in order to extract the features from online reviews and detect the fake online reviews based on the movies dataset. Here we attempt to apply the supervised learning on movies dataset, during which the admin attempt to collect a group of latest movies information and this may be viewed and rated by the top users. The user can able to give reviews based on multiple parameters like: Rate by Movie, Rate by Religion, Rate by the star ratings and lot more. Here we try to identify all the interesting movies as well as un-interesting movies from the set of movie reviews and try to give the detailed analysis for the end users who try to search about that movie.

Semi-Supervised Learning, Supervised Learning, Fake Users, Interesting Movies, Text Mining.

"Detection of Fake Online Reviews Using Semi Supervised and Supervised Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.g384-g394, June-2021, Available :http://www.jetir.org/papers/JETIR2106872.pdf

"Detection of Fake Online Reviews Using Semi Supervised and Supervised Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppg384-g394, June-2021, Available at : http://www.jetir.org/papers/JETIR2106872.pdf