Generalizable Sarcasm Detection Is Just Around The Corner, Of Course!

arXiv:2404.06357v1 Announce Type: new
Abstract: We tested the robustness of sarcasm detection models by examining their behavior when fine-tuned on four sarcasm datasets containing varying characteristics of sarcasm: label source (authors vs. third-party), domain (social media/online vs. offline conversations/dialogues), style (aggressive vs. humorous mocking). We tested their prediction performance on the same dataset (intra-dataset) and across different datasets (cross-dataset). For intra-dataset predictions, models consistently performed better when fine-tuned with third-party labels rather than with author labels. For cross-dataset predictions, most …

abstract arxiv authors behavior conversations course cs.cl datasets detection domain media mocking of course offline performance prediction robustness social social media style type