Summary of Toxic Memes: a Survey Of Computational Perspectives on the Detection and Explanation Of Meme Toxicities, by Delfina Sol Martinez Pandiani et al.
Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities
by Delfina Sol Martinez Pandiani, Erik Tjong Kim Sang, Davide Ceolin
First submitted to arxiv on: 11 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses the growing issue of toxic internet memes by conducting a comprehensive survey of computational analyses on these topics. The authors employ the PRISMA methodology to systematically extend previous research, analyzing 158 works focused on content-based toxic meme analysis. Key findings include the identification of over 30 datasets used in this field and the introduction of a new taxonomy for categorizing meme toxicity types. The paper also highlights the expansion of computational tasks beyond simple binary classification, indicating a shift towards nuanced understanding of toxicity. Additionally, it notes the importance of cross-modal reasoning, integrating expert knowledge, and handling low-resource languages. Furthermore, the authors discuss the rising use of Large Language Models (LLMs) and generative AI for detecting and generating toxic memes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how computers can analyze internet memes that are harmful or offensive. The researchers looked at many studies on this topic and found some patterns and trends. They identified a lot of different datasets used in these studies, which helps us understand what makes a meme “toxic”. They also created a new way to group types of toxic memes together. The paper says that computers are getting better at understanding what makes a meme toxic, but there is still more work to do. It’s like trying to figure out why someone might think something is funny or not. |
Keywords
» Artificial intelligence » Classification
