Summary of Iitk at Semeval-2024 Task 4: Hierarchical Embeddings For Detection Of Persuasion Techniques in Memes, by Shreenaga Chikoti and Shrey Mehta and Ashutosh Modi
IITK at SemEval-2024 Task 4: Hierarchical Embeddings for Detection of Persuasion Techniques in Memes
by Shreenaga Chikoti, Shrey Mehta, Ashutosh Modi
First submitted to arxiv on: 6 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 A machine learning-based approach is proposed to identify persuasion techniques in memes used in online disinformation campaigns. The goal is to detect causal oversimplification, name-calling, smear, and other rhetorical and psychological tactics employed by these memes. A SemEval 2024 task, “Multilingual Detection of Persuasion Technique in Memes,” consists of three sub-tasks: hierarchical multi-label classification using textual content, visual and textual content, or only binary classification based on the presence of persuasion techniques. The proposed ensemble combines Class Definition Prediction (CDP) and hyperbolic embeddings-based approaches to enhance meme classification accuracy and comprehensiveness. This results in a hierarchical F1-score of 0.60, 0.67, and 0.48 for the respective sub-tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper aims to help stop online disinformation by developing a system that can detect persuasive techniques in memes on social media. It uses special computer learning methods to analyze both text and images in the memes. This can help us understand how these memes work and how we can spot them more easily. |
Keywords
* Artificial intelligence * Classification * F1 score * Machine learning
