Author ORCID Identifier

https://orcid.org/0000-0001-8262-2476

Document Type

Conference Paper

Disciplines

1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences

Publication Details

https://link.springer.com/chapter/10.1007/978-3-031-26438-2_25#citeas

https://doi.org/10.1007/978-3-031-26438-2_25

Hazman, M., McKeever, S., Griffith, J. (2023). Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Face Embedding. In: Longo, L., O’Reilly, R. (eds) Artificial Intelligence and Cognitive Science. AICS 2022. Communications in Computer and Information Science, vol 1662. Springer, Cham.

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.

DOI

https://doi.org/10.1007/978-3-031-26438-2_25

Funder

Science Foundation Ireland Centre for Research Training in Digitally-Enhanced Reality (d-real) under Grant No. 18/CRT/6224.

Creative Commons License

Creative Commons Attribution-Share Alike 4.0 International License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.


Share

COinS