The RecSys Challenge 2020 will be organized by Politecnico di Bari, Free University of Bozen-Bolzano, TU Wien, University of Colorado, Boulder, and Universidade Federal de Campina Grande, and sponsored by Twitter. The challenge focuses on a real-world task of tweet engagement prediction in a dynamic environment. The goal is to predict the probability for different types of engagement (Favourite, Reply, Retweet and Quote Tweet) of a target user for a set of tweets, based on heterogeneous input data.
(dataset coming soon)
Twitter will release a large public dataset of ~200M public tweets, obtained by subsampling within ~2 weeks, that contains engagement features, user features, and tweet features.
A strong point of this challenge are the recent regulations on data protection and privacy, hence the challenge data set will be GDPR compliant: if a user deletes a tweet, or their data from Twitter, the dataset will be updated accordingly within 24 hours. Therefore, for every change in the dataset, the evaluation of the submissions will be re-done, and the leaderboard will be updated with the re-calculated metrics.
Participation for this challenge is subject to the acceptance of these Terms & Conditions
Note: the timeline is subject to slight modifications.
|March 2, 2020||
Dataset Release & RecSys Challenge Starts
Training and validation datasets released
|June 1, 2020||Test Dataset Release|
|June 7, 2020||RecSys Challenge ends|
|June 15, 2020||Announcement of the final leaderboard and winners Paper submission for RecSys Challenge Workshop|
|End of June||Paper Submission Due|
|Mid July||Paper Acceptance Notifications|
|September 22-26, 2020||Workshop taking place as part of the ACM RecSys conference in Rio de Janeiro, Brazil.|