Table 10 Baseline comparison for sentiment-derived urgency prediction.

From: A zero-shot LLM framework for multimodal grievance classification, urgency scoring, and abuse detection in civic feedback systems

Model

MAE

Spearman \(\rho\)

Latency (ms)

RoBERTa-sentiment

0.036

0.83

94

XLM-R-base-sentiment

0.034

0.85

102

VADER (Proposed)

0.041

0.87

5

Back to article page