Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations

Abstract

Sarcasm detection and humor classification are inherently subtle problems, primarily due to their dependence on the contextual and non-verbal information. Furthermore, existing studies in these two topics are usually constrained in non-English languages such as Hindi, due to the unavailability of qualitative annotated datasets. In this work, we make two major contributions considering the above limitations: (1) we develop a Hindi-English code-mixed dataset, MaSaC 1 , for the multi-modal sarcasm detection and humor classification in conversational dialog, which to our knowledge is the first dataset of its kind; (2) we propose MSH-COMICS 2 , a novel attention-rich neural architecture for the utterance classification. We learn efficient utterance representation utilizing a hierarchical attention mechanism that attends to a small portion of the input sentence at a time. Further, we incorporate dialog-level contextual attention mechanism to leverage the dialog history for the multi-modal classification. We perform extensive experiments for both the tasks by varying multi-modal inputs and various submodules of MSH-COMICS. We also conduct comparative analysis against existing approaches. We observe that MSH-COMICS attains superior performance over the existing models by >1 F1-score point for the sarcasm detection and 10 F1-score points in humor classification. We diagnose our model and perform thorough analysis of the results to understand the superiority and pitfalls.

Cross Domain Hybrid Feature Fusion based Sarcastic Opinion Recognition Over E-Commerce Reviews Using Adversarial Transfer Learning

“…The performance gain can be still improved by removing the datasets contributing to domain losses. Bedi et al [8] proposed an attention based multi modality classification model for sarcasm classification in Hindi-English code mixed conversational dialog. Textual and acoustic features are extracted from the conversations.…”