ConcertTweets: A Multi-Dimensional Data Set for Recommender Systems Research

In an effort to facilitate scientific research purposes and further enable collaborations among researchers in the data mining, machine learning, and computer science communities, we publicly release the ‘ConcertTweets’ data set.

‘ConcertTweets’ combines implicit and explicit user ratings with rich content as well as spatio-temporal contextual dimensions and social network data. The data set can be easily further enriched with additional dimensions and ratings. “ConcertTweets: A Multi-Dimensional Data Set for Recommender Systems Research” provides a detailed description of the data set.

The latest version of this data set contains 200,000 ratings from 50,492 users referring to 94,558 musical shows and concerts of 20,922 artists and bands. You can download the data set from here!

Earlier versions can be found here: http://pages.stern.nyu.edu/~padamopo/data/concertTweets/

If you use ‘ConcertTweets’ in your work, please cite the following paper:

Panagiotis Adamopoulos, Alexander Tuzhilin: Estimating the Value of Multi-Dimensional Data Sets in Context-based Recommender Systems. ACM Conference on Recommender Systems (RecSys 2014)