Saved in:
Bibliographic Details
Main Authors: Xiao, Luwei, Mao, Rui, Zhao, Shuai, Lin, Qika, Jia, Yanhao, He, Liang, Cambria, Erik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908332138168320
author Xiao, Luwei
Mao, Rui
Zhao, Shuai
Lin, Qika
Jia, Yanhao
He, Liang
Cambria, Erik
author_facet Xiao, Luwei
Mao, Rui
Zhao, Shuai
Lin, Qika
Jia, Yanhao
He, Liang
Cambria, Erik
contents Multimodal aspect-based sentiment classification (MASC) is an emerging task due to an increase in user-generated multimodal content on social platforms, aimed at predicting sentiment polarity toward specific aspect targets (i.e., entities or attributes explicitly mentioned in text-image pairs). Despite extensive efforts and significant achievements in existing MASC, substantial gaps remain in understanding fine-grained visual content and the cognitive rationales derived from semantic content and impressions (cognitive interpretations of emotions evoked by image content). In this study, we present Chimera: a cognitive and aesthetic sentiment causality understanding framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations). Specifically, this framework first incorporates visual patch features for patch-word alignment. Meanwhile, it extracts coarse-grained visual features (e.g., overall image representation) and fine-grained visual regions (e.g., aspect-related regions) and translates them into corresponding textual descriptions (e.g., facial, aesthetic). Finally, we leverage the sentimental causes and impressions generated by a large language model (LLM) to enhance the model's awareness of sentimental cues evoked by semantic content and affective-cognitive resonance. Experimental results on standard MASC datasets demonstrate the effectiveness of the proposed model, which also exhibits greater flexibility to MASC compared to LLMs such as GPT-4o. We have publicly released the complete implementation and dataset at https://github.com/Xillv/Chimera
format Preprint
id arxiv_https___arxiv_org_abs_2504_15848
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis
Xiao, Luwei
Mao, Rui
Zhao, Shuai
Lin, Qika
Jia, Yanhao
He, Liang
Cambria, Erik
Computation and Language
Multimodal aspect-based sentiment classification (MASC) is an emerging task due to an increase in user-generated multimodal content on social platforms, aimed at predicting sentiment polarity toward specific aspect targets (i.e., entities or attributes explicitly mentioned in text-image pairs). Despite extensive efforts and significant achievements in existing MASC, substantial gaps remain in understanding fine-grained visual content and the cognitive rationales derived from semantic content and impressions (cognitive interpretations of emotions evoked by image content). In this study, we present Chimera: a cognitive and aesthetic sentiment causality understanding framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations). Specifically, this framework first incorporates visual patch features for patch-word alignment. Meanwhile, it extracts coarse-grained visual features (e.g., overall image representation) and fine-grained visual regions (e.g., aspect-related regions) and translates them into corresponding textual descriptions (e.g., facial, aesthetic). Finally, we leverage the sentimental causes and impressions generated by a large language model (LLM) to enhance the model's awareness of sentimental cues evoked by semantic content and affective-cognitive resonance. Experimental results on standard MASC datasets demonstrate the effectiveness of the proposed model, which also exhibits greater flexibility to MASC compared to LLMs such as GPT-4o. We have publicly released the complete implementation and dataset at https://github.com/Xillv/Chimera
title Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2504.15848