Answers are grounded in this paper and cite their sources.
Explores effectiveness of multimodal approach for personality classification in social media users, suggesting improved accuracy over existing methods.
The rise of social media has amplified activities like uploading and downloading text and images, making it challenging to monitor and analyze the vast amount of data. Automatically studying user behavior from shared images and text is complex, which motivated us to develop a novel method for personality trait identification. Current methods typically depend on a single modality, such as text, images, or video, and fail to leverage the multimodal nature of data available on social media. In this paper, we introduce a multimodal approach that integrates features from various image types (e.g., uploaded images, banners, profile pictures) and textual content (e.g., posted text, text within images, image descriptions) to classify social media images based on the Big Five Factors (BFF) of Personality Traits. Our model uses gradients in the frequency domain to detect focused image regions through a combination of quad trees and CNNs. Color features are extracted using a blend of a color synergy model and median cut clustering, while textual features are derived from a sentence inference model combining fuzzy vectors and CNNs. These features are fused using a Fully Connected Neural Network (FCNN) for personality trait classification. Experimental results on our dataset and two benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in classification accuracy.
No takes yet. Share an insight, caveat, or question.
Biswas et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: