SUMMARY:
This dataset collected through an online survey application and is still in progress.
It contains ratings of 334 users on 1610 movies and also some features of movies including: genres, casts, directors, movie year, movie production country.
Data are filtered by ONLY reliable users. (we performed some data consistensy check to find reliable answers)
The dataset contains 2834 casts and 1099 directors selected by users as their favorites. 
The data are contained in 4 files: userMovieRatings, userCastRatings, userDirectorRatings and userGenreRatings.
All ratings are binary (User selected(liked) a movie/feature or not ). 



USAGE LISENCE:
Neither the Politecnic University of Milan nor any of the researchers involved can guarantee the correctness of the data, its suitability for any particular purpose, or the validity of results based on the use of the data set. The data set may be used for any research purposes under the following conditions:

-The user may not redistribute the data without separate permission.
-The user may not use this information for any commercial or revenue-bearing purposes without first obtaining permission from Recsys members at the Politecnic University of Milan.

If you have any further questions or comments, please contact Mona Nasery by email: mona.nasery@polimi.it 



ACKNOWLEDGEMENTS:
Copy provided by Mona Nasery.
I would like to also thank Bruno Pistone and Raffaele Prunella for helping us to generate the dataset.



FILES CONTENTS AND DATA STRUCTURE:
userMovieRatings.csv
This file Contains the movies selected (liked) by reliable users (332 users and 1610 distinct movies). Each line of this file represents a movie liked by a user (user may like more than one movie), and has the following format:

userId,answer,movieName,ImdbId,ImdbRate,year,numVotes

userId: unique Id of each user.
answer: movies selected by users with the format "movieName_year", e.g., "Pulp Fiction_1994"
movieName: movie title
ImdbId: unique IMDB Id of movies
ImdbRate: overall rate of a movie 
year: movie year
numVotes: total number of ratings provided by Imdb users on movies

userCastRating.csv
It contains the casts explicitly selected (liked) by reliable users (335 users and 421 distinct casts). Each line of this file represents a cast liked by a user (user may like more than one cast), and has the following format:

workerId,starImdbID

workerId: unique Id of each user
starImdbID: unique IMDB Id of casts

userDirectorRatings.csv
 It contains the directors explicitly selected (liked) by reliable users (321 users and 299 distinct directors). Each line of this file represents a director liked by a user (user may like more than one director), and has the following format:

worker_Id, directorImdbID

worker_Id: unique Id of users
directorImdbID: unique IMDB Id of directors