Social Recommendation Data
- 1. University of California San Diego
Description
Description
The Social Recommendation Data captures ratings and social (trust) relationships collected by Julian McAuley's lab (University California San Diego): user reviews and trust networks from LibraryThing (a book review website) and Epinions (a general consumer review platform). It includes anonymized user IDs, item ratings, review text, helpfulness votes, flags, and price-paid metadata, available as two separate datasets: LibraryThing (73,882 users, 337,561 items, 979,053 ratings, 120,536 social relations) and Epinions (116,260 users, 41,269 items, 181,394 ratings, 181,304 social relations).
Please cite the following if you use the data:
SPMC: Socially-aware personalized Markov chains for sparse sequential recommendation
Chenwei Cai, Ruining He, Julian McAuley
IJCAI, 2017Improving latent factor models via personalized feature projection for one-class recommendation
Tong Zhao, Julian McAuley, Irwin King
CIKM, 2015
DOI: https://doi.org/10.1145/2806416.2806511
Details
| Resource type | Open dataset |
| Title | Social Recommendation Data |
| Creators |
|
| Publisher | University of California San Diego |
| Year of publication | 2017 |
| Research fields | Economics Psychology Sociology Political Science Economic & Social History Communication Sciences Educational Research Business Administration Other |
| Size | 660 MB |
| Formats | Tape Archive (TAR) (.tar) GZip Compressed Archive (.gz) |
| External resource | https://cseweb.ucsd.edu/~jmcauley/datasets.html#social_data |
Additional details
Related works
- Is cited by
- Journal article: 10.1007/s13278-021-00850-z (DOI)
- Is described by
- Conference paper: 10.1145/2806416.2806511 (DOI)
- Conference paper: https://www.ijcai.org/proceedings/2017/0204.pdf (URL)