"Harvesting movie ratings from structured data in social media" by Simon Dooms and Luc Martens with Ching-man Au Yeung as coordinator

Public movie rating datasets, like MovieLens or Netflix, have long been popular and widely used in the recommmender systems domain for comparison and experimentation. More and more however these datasets are becoming outdated and fail to incorporate new and relevant items. In our work, we tap into the vast availability of social media and construct a new movie rating dataset ‘MovieTweetings’ based on public and well-structured tweets. New data is added on a daily basis, which guarantees the MovieTweetings dataset to always incorporate ratings on the newest and most relevant movies.

Sign In

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.