Summary of A Two-model Approach For Humour Style Recognition, by Mary Ogbuka Kenneth et al.
A Two-Model Approach for Humour Style Recognition
by Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat
First submitted to arxiv on: 9 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The proposed research addresses the lack of established datasets and machine learning models for humour style recognition by presenting a new text dataset comprising 1463 instances across four styles (self-enhancing, self-deprecating, affiliative, and aggressive) and non-humorous text. The study employs various computational methods, including classic machine learning classifiers, text embedding models, and DistilBERT, to establish baseline performance. Additionally, the researchers propose a two-model approach to enhance humour style recognition, particularly in distinguishing between affiliative and aggressive styles. The method demonstrates an 11.61% improvement in f1-score for affiliative humour classification, with consistent improvements in the 14 models tested. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about recognizing different types of humor in text messages and social media posts. It’s important because understanding humor can help us understand how people communicate and how it affects our mental health. The researchers created a big dataset of text messages that are funny or not funny, and they used special computer programs to see if they could tell which kind of humor was being used. They found some ways to make the computer better at recognizing humor, especially when it’s nice and friendly rather than mean-spirited. |
Keywords
» Artificial intelligence » Classification » Embedding » F1 score » Machine learning
