Summary of Classifying Human-generated and Ai-generated Election Claims in Social Media, by Alphaeus Dmonte et al.
Classifying Human-Generated and AI-Generated Election Claims in Social Media
by Alphaeus Dmonte, Marcos Zampieri, Kevin Lybarger, Massimiliano Albanese, Genya Coulter
First submitted to arxiv on: 24 Apr 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 This paper proposes a novel taxonomy for characterizing election-related claims on social media, with granular categories related to jurisdiction, equipment, processes, and the nature of claims. The authors introduce ElectAI, a benchmark dataset consisting of 9,900 tweets, each labeled as human- or AI-generated, along with the specific LLM variant that produced them. They annotate a subset of 1,550 tweets using the proposed taxonomy to capture the characteristics of election-related claims. To demonstrate the capabilities of Large Language Models (LLMs) in extracting taxonomy attributes and distinguish between human- and AI-generated posts, the authors train various machine learning models on ElectAI. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper is about how artificial intelligence can help us understand what’s true or false when people discuss politics on social media. Right now, some bad actors use these platforms to spread fake news to make people doubt the elections. The problem is getting worse because AI machines can create fake messages that look real. This paper creates a special way to categorize different types of claims about elections and tests it using 9,900 tweets. They also show how AI machines can be used to figure out if a tweet was written by a person or an AI machine. |
Keywords
» Artificial intelligence » Machine learning
