# A Deep Multi-Level Attentive network for Multimodal Sentiment Analysis

arXiv: https://arxiv.org/abs/2012.08256 · HTML: https://mlsanity.com/paper/2012.08256/

## Key facts

- Cited by 6 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [A Survey on Multi-modal Summarization](https://mlsanity.com/paper/2109.05199/) (2021)
- [A Comprehensive Review of Visual-Textual Sentiment Analysis from Social Media Networks](https://mlsanity.com/paper/2207.02160/) (2022)
- [ClickGuard: A Trustworthy Adaptive Fusion Framework for Clickbait Detection](https://mlsanity.com/paper/2604.07272/) (2026)
- [Robust Fuzzy Multi-view Learning under View Conflict](https://mlsanity.com/paper/2605.24475/) (2026)

## Abstract (arXiv)

Multimodal sentiment analysis has attracted increasing attention with broad application prospects. The existing methods focuses on single modality, which fails to capture the social media content for multiple modalities. Moreover, in multi-modal learning, most of the works have focused on simply combining the two modalities, without exploring the complicated correlations between them. This resulted in dissatisfying performance for multimodal sentiment classification. Motivated by the status quo, we propose a Deep Multi-Level Attentive network, which exploits the correlation between image and text modalities to improve multimodal learning. Specifically, we generate the bi-attentive visual map along the spatial and channel dimensions to magnify CNNs representation power. Then we model the correlation between the image regions and semantics of the word by extracting the textual features related to the bi-attentive visual features by applying semantic attention. Finally, self-attention is employed to automatically fetch the sentiment-rich multimodal features for the classification. We conduct extensive evaluations on four real-world datasets, namely, MVSA-Single, MVSA-Multiple, Flickr, and Getty Images, which verifies the superiority of our method.