Summary of Hate Speech Detection Using Cross-platform Social Media Data in English and German Language, by Gautam Kishore Shahi and Tim A. Majchrzak
Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language
by Gautam Kishore Shahi, Tim A. Majchrzak
First submitted to arxiv on: 2 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 The paper proposes a generalized model for detecting hate speech in bilingual texts, focusing on YouTube comments. The challenge lies in obtaining high-quality training data, which is costly to obtain. To address this issue, the study explores the value of additional training datasets from other platforms (e.g., Twitter and Gab) and factors such as content similarity, definition similarity, and common hate words to improve the performance of classification models. Results show that combining datasets from multiple platforms yields the best performance, achieving an F1-score of 0.74 for English YouTube comments and 0.68 for German YouTube comments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a big problem: how to spot hateful speech on the internet. Right now, there are many ways to detect hate speech, but they all need lots of training data, which is hard to get. The researchers thought about this problem and came up with an idea to use extra data from other places like Twitter and Gab to make their model better. They also looked at how similar the words are between different platforms and used that information to help their model work better. What they found was that using all this extra data helped their model do a much better job of spotting hate speech, especially for YouTube comments in English and German. |
Keywords
» Artificial intelligence » Classification » F1 score
