OpenTable data with multi-criteria ratings

With the development of recommender systems (RSs), several promising systems have emerged, such as context-aware RS, multi-criteria RS, and group RS. Multi-criteria recommender systems (MCRSs) are designed to provide personalized recommendations by considering user preferences in multiple attributes or criteria simultaneously. Unlike traditional RSs that typically focus on a single rating, these systems help users make more informed decisions by considering their diverse preferences and needs across various dimensions. In this article, we release the OpenTable data set which was crawled from OpenTable.com. The data set can be considered as a benchmark data set for multi-criteria recommendations.

Special Notes

- While working on web crawling for OpenTable.com, we found that HTML resources contained users' nickname instead of UserIDs. Occasionally, anonymous reviews used a default username, such as "Unknown user." To assign UserIDs, we treated the combination of username and city as a unique user. However, for entries with the default "Unknown user" username, we assigned the same ID. This explains why you might see multiple entries with the same <user, item> pair but different ratings.

- We provide the opentable_cleaned.csv file, where we removed duplicated entries and only include the last entry associated with the unique <user, item> pair in the data set.

The data set can be used for both traditional recommendations and multi-criteria recommendations. If you use this data set in your publications, please refer to the following data publication:

@article{zheng2024opentabledata,
title = {OpenTable data with multi-criteria ratings},
author={Zheng, Yong},
journal={arXiv preprint arXiv:2501.03072},
year={2024}
}

@data{zheng2024opentable,
doi = {10.21227/8avw-yk62},
url = {https://dx.doi.org/10.21227/8avw-yk62},
author = {Zheng, Yong},
publisher = {IEEE Dataport},
title = {OpenTable data with multi-criteria ratings},
year = {in IEEE Dataport, 2024}
}