Timeline for How to compute precision/recall for multiclass-multilabel classification?
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 3, 2013 at 1:22 | comment | added | Nikana Reklawyks | First link died | |
| Jan 28, 2012 at 14:11 | comment | added | Jack Tanner | @MaVe, sorry, no links. This is just from personal experience. You'll get there simply by thinking about what constitutes, say, a true positive and a false positive for your purposes. | |
| Jan 28, 2012 at 7:59 | comment | added | Vam | Ahmed: Thanks for the links! @JackTanner Would you perhaps have a reference for this (for the case of multi-class multi-label classification)? | |
| Jan 28, 2012 at 1:57 | comment | added | Jack Tanner | The key point is: there are multiple possible valid ways to compute these metrics (e.g., micro-F1 vs macro-F1) because there are multiple ways to define what is correct. This depends on your application and validity criteria. | |
| Jan 27, 2012 at 21:31 | history | answered | Ahmed Kotb | CC BY-SA 3.0 |