Table 18 Comparison of complaint classification models.

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

Model

Accuracy (%)

MAE

Latency (ms)

Naive Bayes

83.5

0.087

65

SVM (Linear)

87.1

0.069

78

TF-IDF + Rules

76.4

0.112

43

Unified Model (Proposed)

92.4

0.041

91

Back to article page