Movie Recommendation using Sentiment Analysis and Ajax

Computer Science

Movie proposal in Web climate is fundamentally significant for Internet clients. It completes a thorough accumulation of client's inclinations, surveys, and feelings to help them find appropriate motion pictures advantageously. Be that as it may, it requires both exactness and practicality. To enhance the exactness and idealness of the movie recommender system, this paper proposes a movie suggestion structure based on a mixture suggestion model and slant investigation on the Web level. In the proposed process, we first build a starter suggestion list using a half-and-half suggestion technique. At that point, opinion examination is utilized to streamline the rundown. At last, the mixture recommender framework with opinion examination is executed. The half and half suggestion model with opinion investigation outflank the conventional models regarding different assessment standards. RS is a smart system that provides relevant information about the choices made by a user. It has two practical methods namely Collaborative filtering and Content-based filtering. There are certain disadvantages, such as the need for prior user background and preferences in order to execute the recommendation task. This paper combines the two listed methods that are Content-based filtering and Sentiment analysis. Our proposed technique makes it advantageous and quick for clients to acquire valuable film proposals. For the data set, we will be accessing the IMDB movie dataset from a website called Kaggle.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.