Predicting IMDb Ratings of Pre-release Movies with Factorization Machines Using Social Media

Cizmeci B., Öğüdücü Ş.

3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia And Herzegovina, 20 - 23 September 2018, pp.173-178 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Sarajevo
  • Country: Bosnia And Herzegovina
  • Page Numbers: pp.173-178
  • Istanbul Technical University Affiliated: Yes


The film industry has always been a very important sector in the global market. Therefore, it is very important to maximize the profit by predicting the movie success before its release. Although several studies have been done in this field, it is still needed to improve the prediction performance and collect more data. This study aims to explore the use of Factorization Machines approach in order to predict movie success by predicting IMDb ratings for newly released movies using social media data and compare it to current studies. Also, a framework has been developed in order to gather the movie data from different sources including social media. Comparison of the Factorization Machines to the current models shows that there are promising results.