Abstract: In the times, wherever technology is at the forefront of each business, there has been AN overload of information and knowledge. Thus, a recommendation system comes in handy to manage this massive volume of knowledge and separate out the helpful info that is quick and relevant to the user’s alternative. This paper describes AN approach to a moving picture suggestion system victimization circular function Similarity to recommend similar movies supported by the one chosen by the user. though the present recommendation systems get the work done, it doesn't justify if the moving picture is value defrayment time on. to reinforce the user expertise, this method performs sentiment analysis on the reviews of the moving picture chosen victimization machine learning. 2 of the supervised machine learning algorithms Naïve Bayes (NB) Classifier and Support Vector Machine (SVM) Classifier are accustomed increase the accuracy an deficiency. This paper conjointly offers a comparison between NB and SVM on the premise of parameters like Accuracy, Precision, Recall, and F1 Score. The accuracy score of SVM came dead set be ninety-eight.63% whereas the accuracy score of NB is 97.33%. Thus, SVM outweighs NB and proves to be a stronger-suited Sentiment Analysis.
Keywords: Trigonometric function, similarity picture recommendation, Naïve mathematician, Sentiment analysis , Support vector machine.
|
DOI:
10.17148/IJARCCE.2022.111150
