Review
Jul 2026
Joint aspect-based sentiment and overall rating prediction via a cross-modal transformer in user reviews
MMRP is proposed, an end-to-end multimodal multitask framework for jointly modeling ACSA and ORP from image-text reviews and demonstrates the effectiveness of jointly leveraging multimodal information for aspect-level and overall rating prediction in user reviews.
Xiaoning Wang, Rui Li, Yuxuan Guo et al.
· Knowledge and Information Sy... · 0 citations