Abstract
How do humans analyze the sentiments embedded in text? When attempting to analyze a text, humans construct a “scene” in their minds through imagination based on the text, generating a vague image. They then synthesize the text and the mental image to derive the final analysis result. However, current sentiment analysis models lack such imagination; they can only analyze based on existing information in the text, which limits their classification accuracy. To address this issue, we propose the SceEmoNet model. This model endows text classification models with imagination through Stable diffusion, enabling the model to generate corresponding visual scenes from input text, thus introducing a new modality of visual information. We then use the Contrastive Language-Image Pre-training (CLIP) model, a multimodal feature extraction model, to extract aligned features from different modalities, preventing significant feature differences caused by data heterogeneity. Finally, we fuse information from different modalities using late fusion to obtain the final classification result. Experiments on six datasets with different classification tasks show improvements of 9.57%, 3.87%, 3.63%, 3.14%, 0.77%, and 0.28%, respectively. Additionally, we set up experiments to deeply analyze the model’s advantages and limitations, providing a new technical path for follow-up research.
Funding Information
  • Doctoral Research Foundation of Xinjiang Normal University (XJNUZBS2404, XJEDU2025P068)
  • Scientific Research Projects of Basic Scientific Research Business Expenses for Universities in Xinjiang Uygur Autonomous Region (XJNUZBS2404, XJEDU2025P068)
  • Talent Projects of the Third Batch of the “Tianchi Talent” Introduction Plan in Xinjiang Uygur Autonomous Region (XJNUZBS2404, XJEDU2025P068)

This publication has 42 references indexed in Scilit: