Are Word Embedding-based Features Useful for Sarcasm Detection? — mentioned by daveguy

Sat, 15 Oct 2016 17:39:59 GMT

Looking at the paper here: https://arxiv.org/abs/1610.00883 Can anyone tell me what the P R and F "features" mean in table 2? They use F-score ( https://en.wikipedia.org/wiki/F1_score ) which doesn't take into account true negatives at all. Maybe not an issue since they are evaluating the same set of GoodReads quotes across all four. The unique features contribute to an F-Score improvement of around 1% with baselines in the 50-80% range. That doesn't seem to be a significant improvement and the F-Score is just a within-test percentage measure of how good the technique is at measuring…

Paper and discussion history. A mention is not an endorsement.

Are Word Embedding-based Features Useful for Sarcasm Detection? · HackerPapers discussions

Are Word Embedding-based Features Useful for Sarcasm Detection? — mentioned by daveguy