I am looking for a data set for building a recommender system that takes into account contextual aspect-level ratings.

For example, a data set from Tripadvisor would be great if it contained "traveler type" (like business or family) and "time of year" (like Jun-Aug) (as contexts) as well as aspect-level ratings (like "Rooms" and "Cleanliness" and so on).

What I want to check is, if recommendation accuracy can be improved by incorporating contextual aspect-level ratings as I expect recommendations to be more accurate in this case than when e.g. only aspect-level ratings/only context/just overall ratings is/are used.

Any other data set from any other domain in which the approach would be useful is appreciated, too. It would be a plus, if the data set also contained text-based reviews.

Thank you for your time!

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy