ProSarc detects sarcasm via temporal prosodic incongruity using dual encoders (Global Emotion and Temporal Prosody with BiLSTM+attention) and an incongruity analyzer, reporting F1=75.3 on MUStARD++, 62.9 on PodSarc, and 65.6 on MuSaG.
Amused: An attentive deep neural network for multi- modal sarcasm detection incorporating bi-modal data augmenta- tion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
An LLM-assisted annotation pipeline creates the PodSarc sarcastic speech dataset from podcasts and validates it via a collaborative gating detection model reaching 73.63% F1.
citing papers explorer
-
ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity
ProSarc detects sarcasm via temporal prosodic incongruity using dual encoders (Global Emotion and Temporal Prosody with BiLSTM+attention) and an incongruity analyzer, reporting F1=75.3 on MUStARD++, 62.9 on PodSarc, and 65.6 on MuSaG.
-
Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection
An LLM-assisted annotation pipeline creates the PodSarc sarcastic speech dataset from podcasts and validates it via a collaborative gating detection model reaching 73.63% F1.