Revisiting Vision-Language Features Adaptation and Inconsistency for Social Media Popularity Prediction
Not on the map. Why?
Abstract (arXiv)
Social media popularity (SMP) prediction is a complex task involving multi-modal data integration. While pre-trained vision-language models (VLMs) like CLIP have been widely adopted for this task, their effectiveness in capturing the unique characteristics of social media content remains unexplored. This paper critically examines the applicability of CLIP-based features in SMP prediction, focusing on the overlooked phenomenon of semantic inconsistency between images and text in social media posts. Through extensive analysis, we demonstrate that this inconsistency increases with post popularity, challenging the conventional use of VLM features. We provide a comprehensive investigation of semantic inconsistency across different popularity intervals and analyze the impact of VLM feature adaptation on SMP tasks. Our experiments reveal that incorporating inconsistency measures and adapted text features significantly improves model performance, achieving an SRC of 0.729 and an MAE of 1.227. These findings not only enhance SMP prediction accuracy but also provide crucial insights for developing more targeted approaches in social media analysis.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2024.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 3; 2026: 1.
4 papers.
- 2025DenseSR: Image Shadow Removal as Dense Predictioncited by 5
- 2025Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardizationcited by 2
- 2026OmniTrend: Content-Context Modeling for Scalable Social Popularity Predictioncited by 1
- 2025HyperFusion: Hierarchical Multimodal Ensemble Learning for Social Media Popularity Predictioncited by 0
- 2026OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction29 Apr 2026
- 2025Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization26 Jul 2025
- 2025DenseSR: Image Shadow Removal as Dense Prediction22 Jul 2025
- 2025HyperFusion: Hierarchical Multimodal Ensemble Learning for Social Media Popularity Prediction1 Jul 2025
Similar, not cited
Close in wording, no citation either way
- 2026Benchmarking Multi-Modal Graph-based Social Media Popularity Prediction
- 2025SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services
- 2025Large Language Model-Informed Feature Discovery Improves Prediction and Interpretation of Credibility Perceptions of Visual Content
- 2023A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge
- 2025Image-Text Relation Prediction for Multilingual Tweets
- 2025On VLMs for Diverse Tasks in Multimodal Meme Classification
- 2024Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People
- 2025Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models