Results
These are the final results for the 2009 ECML PKDD Discovery Challenge. The links underlying the id point to the respective (zipped) result file. The format of the files is described on the evaluation page.
Please note that only submissions with an appropriate paper and talk/poster presentation made it into the final ranking.
Task 1
final rank | id | f1m | submission (PDF) |
---|---|---|---|
1 | 30478 | 0.18740 | Tag Sources for Recommendation in Collaborative Tagging Systems Marek Lipczak, Yeming Hu, Yael Kollet, and Evangelos Milios |
2 | 43396 | 0.18001 | Content- and Graph-based Tag Recommendation: Two Variations Johannes Mrosek, Stefan Bussmann, Hendrik Albers, Kai Posdziech, Benedikt Hengefeld, Nils Opperman, Stefan Robert, and Gerrit Spira |
3 | 45839 | 0.17975 | A Weighting Scheme for Tag Recommendation in Social Bookmarking Systems Sanghun Ju and Kyu-Baek Hwang |
4 | 76565 | 0.14151 | 22 |
5 | 20418 | 0.14018 | 15 |
6 | 29723 | 0.13547 | 11 |
7 | 19964 | 0.13242 | 17 |
8 | 11472 | 0.11886 | 14 |
9 | 93716 | 0.11787 | 26 |
10 | 16379 | 0.11612 | 18 |
11 | 12192 | 0.10799 | 27 |
12 | 90756 | 0.09808 | 06 |
13 | 13849 | 0.07411 | 25 |
14 | 30678 | 0.06978 | 20 |
15 | 33067 | 0.05283 | 24 |
16 | 98142 | 0.04603 | 04 |
Task 2
final rank | id | f1m | submission (PDF) |
---|---|---|---|
1 | 79768 | 0.35594 | Factor Models for Tag Recommendation in BibSonomy Steffen Rendle and Lars Schmidt-Thieme |
2 | 80999 | 0.33185 | Relational Classification for Personalized Tag Recommendation Leandro Balby Marinho, Christine Preisach, and Lars Schmidt-Thieme |
3 | 30478 | 0.32461 | Tag Sources for Recommendation in Collaborative Tagging Systems Marek Lipczak, Yeming Hu, Yael Kollet, and Evangelos Milios |
4 | 76565 | 0.32230 | A Tag Recommendation System based on contents Ning Zhang, Yuan Zhang, and Jie Tang |
5 | 45839 | 0.32039 | 05 |
6 | 56390 | 0.31396 | 10 |
7 | 16379 | 0.31368 | 18 |
8 | 11472 | 0.30751 | 14 |
9 | 93716 | 0.30651 | 26 |
10 | 13849 | 0.30566 | 25 |
11 | 18945 | 0.29521 | 08 |
12 | 30678 | 0.26253 | 20 |
13 | 90756 | 0.25770 | 06 |
Task 3
For the online task we have set up a special evaluation page containing more details. Some of the diagrams and tables are explained in our paper Testing and Evaluating Tag Recommenders in a Live System.