Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Facial Embedding
arXiv:2303.01781 · doi:10.1007/978-3-031-26438-2_25
Abstract
Internet memes are characterised by the interspersing of text amongst visual elements. State-of-the-art multimodal meme classifiers do not account for the relative positions of these elements across the two modalities, despite the latent meaning associated with where text and visual elements are placed. Against two meme sentiment classification datasets, we systematically show performance gains from incorporating the spatial position of visual objects, faces, and text clusters extracted from memes. In addition, we also present facial embedding as an impactful enhancement to image representation in a multimodal meme classifier. Finally, we show that incorporating this spatial information allows our fully automated approaches to outperform their corresponding baselines that rely on additional human validation of OCR-extracted text.
Published as chapter in ISBN:978-3-031-26438-2
References in corpus (4)
- Learning Transferable Visual Models From Natural Language Supervision
- Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution
- Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysis
- BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer