Movie rating based on multilingual reviews

OData support
Supervisor:
Dr. Dudás Ákos
Department of Automation and Applied Informatics

The worldwide communication provided by the internet is applicable for crowds to share their opinions about various products, for example movies. In many case, simple scores are defining people’s interests about movies, this way they are influenced by personal experiments of other users instead of concrete opinions that are confirmed in the review. To handle this problem it would be useful to calculate these scores by an unified scoring algorithm, which takes only written opinions into consideration. With the tools of text mining, it is possible to analyze and evaluate texts to automatically assign scores to the reviews.

With the increasing number of movies and series, the datasets of opinion sharing webistes are growing too. To manage this huge amount of data, it is recommended to use BigData techniques to properly utilize the resources of the host system.

The purpose of this paper is to make a research on the topic of text mining and sentiment analysis to create an algorithm that BigData systems can use as an unified scoring system for classifying movie reviews based on only concrete opinions, ignoring personal feelings that are not confirmed in the review.

Downloads

Please sign in to download the files of this thesis.