notesum.ai

Published at October 21

AMPLE: Emotion-Aware Multimodal Fusion Prompt Learning for Fake News Detection

cs.CL

cs.AI

cs.CY

cs.LG

Released Date: October 21, 2024

Authors: Xiaoman Xu¹, Xiangrun Li¹, Taihang Wang¹, Ye Jiang¹

Aff.: ¹College of Information Science and Technology, Qingdao University of Science and Technology, China

Arxiv: https://arxiv.org/abs/2410.15591v1

Refer to caption

PolitiFact	few-shot(F1/Acc)					data-rich
PolitiFact	2	4	8	16	50	data-rich
LDA-HAN	0.37/0.39	0.42/0.43	0.44/0.47	0.48/0.52	0.61/0.63	0.70/0.74
T-BERT	0.43/0.50	0.45/0.57	0.50/0.54	0.50/0.54	0.69/0.69	0.71/0.75
SAFE	0.19/0.19	0.21/0.21	0.29/0.27	0.33/0.49	0.46/0.56	0.64/0.65
RIVF	0.35/0.48	0.43/0.51	0.42/0.48	0.40/0.47	0.43/0.49	0.43/0.45
Spotfake	0.37/0.49	0.46/0.52	0.47/0.54	0.56/0.59	0.73/0.73	0.71/0.73
CAFE	0.30/0.39	0.37/0.47	0.45/0.46	0.47/0.49	0.52/0.61	0.67/0.67
FTRB	0.46/0.52	0.51/0.63	0.60/0.63	0.68 /0.70	0.77/0.81	0.79/0.84
P&A	0.49/0.58	0.57/0.62	0.61/0.63	0.62/0.64	0.57/0.61	0.63/0.66
SAMPLE	0.47/0.56	0.56/0.61	0.62/0.66	0.67/0.70	0.81/0.82	0.80/0.81
AMPLE	0.66/0.67	0.65/0.67	0.70/0.71	0.77/0.78	0.80/0.80	0.90/0.90
GossipCop	few-shot(F1/Acc)					data-rich
GossipCop	2	4	8	16	100	data-rich
LDA-HAN	0.18/0.21	0.20/0.25	0.28/0.30	0.34/0.40	0.49/0.45	0.54/0.60
T-BERT	0.38/0.48	0.38/0.57	0.45/0.66	0.45/0.71	0.52/0.61	0.61/0.74
SAFE	0.26/0.31	0.33/0.41	0.40/0.45	0.41/0.45	0.44/0.51	0.55/0.64
RIVF	0.24/0.29	0.24/0.29	0.24/0.29	0.27/0.31	0.29/0.31	0.51/0.61
Spotfake	0.23/0.28	0.22/0.28	0.23/0.28	0.32/0.34	0.48/0.49	0.43/0.73
CAFE	0.41/0.42	0.42/0.52	0.46/0.48	0.47/0.56	0.50/0.61	0.59/0.72
FTRB	0.39/0.41	0.33/0.46	0.44/0.60	0.48/0.63	0.52/0.64	0.63/0.69
P&A	0.44/0.52	0.36/0.50	0.33/0.50	0.61/0.65	0.58/0.59	0.73/0.71
SAMPLE	0.47/0.54	0.47 /0.56	0.52 /0.54	0.54/0.60	0.58/0.62	0.64/0.73
AMPLE	0.47/0.55	0.50/0.57	0.53/0.64	0.54/0.65	0.60/0.66	0.80/0.85