jester — Jester joke ratings (1999-2003)
- Description
A bipartite network of users and the jokes they rated in Jester, an online joke recommender system developed by K. Goldberg and collaborators at the University of California, Berkeley. This is Jester's Dataset 1, with over 4.1 million ratings of 100 jokes by 73,421 anonymous users, collected between April 1999 and May 2003. Users rated jokes with a continuous slider, and each rating is a real value between -10 and +10. Each edge connects a user to a joke they rated. The data were released in three parts: two of users who rated 36 or more jokes (24,983 and 23,500 users), and one of users who rated between 15 and 35 jokes (24,938 users). Almost all users rated the ten jokes 5, 7, 8, 13, 15, 16, 17, 18, 19 and 20, which were used as the "gauge set" of the Eigentaste recommendation algorithm.
The network has the following properties:
- Nodes:
is_joke, whether the node is a joke (otherwise it is a user);joke_id, the number of the joke (1 to 100; -1 for users);text, the text of the joke (with the HTML markup removed);part, the part of the data set the user comes from (1, 2 or 3; -1 for jokes). - Edges:
weight, the rating, between -10 and +10 (higher values for funnier jokes), with two decimal places.
- Nodes:
- Tags
- Economic Preferences Weighted Metadata
- Citation
-
- K. Goldberg, T. Roeder, D. Gupta, C. Perkins, "Eigentaste: A Constant Time Collaborative Filtering Algorithm." Information Retrieval 4(2), 133-151 (2001) 10.1023/A:1011419012209 Sci-Hub
- Upstream URL [Errno 111] Connection refused
- https://eigentaste.berkeley.edu/dataset/
- Upstream license
- Freely available for research use when acknowledged, https://eigentaste.berkeley.edu/dataset/
- Networks
-
Tip: hover over a column header for a description.
Column legend
- $\left<k\right>$
- Mean degree
- $\sigma_k$
- Standard deviation of the degrees
- $\lambda_h$
- Largest eigenvalue of the Hashimoto (non-backtracking) matrix
- $\tau$
- Random walk mixing time
- $r$
- Degree assortativity
- $c$
- Global clustering coefficient
- $\oslash$
- (Pseudo-) diameter
- $S$
- Relative size of the largest component
- NPs
- Node properties
- EPs
- Edge properties
- Ridiculograms*
-