# A Comparison of Human and ChatGPT Classification Performance on Complex Social Media Data

arXiv: https://arxiv.org/abs/2512.00673 · HTML: https://mlsanity.com/paper/2512.00673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Is GPT-3 a Good Data Annotator?](https://mlsanity.com/paper/2212.10450/) (2022)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation](https://mlsanity.com/paper/2211.02570/) (2022)
- [The Generative AI Paradox: "What It Can Create, It May Not Understand"](https://mlsanity.com/paper/2311.00059/) (2023)
- [Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering](https://mlsanity.com/paper/2303.05352/) (2023)
- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark](https://mlsanity.com/paper/2304.11085/) (2023)
- [Can Language Models Recognize Convincing Arguments?](https://mlsanity.com/paper/2404.00750/) (2024)
- [Cross-Partisan Discussions on YouTube: Conservatives Talk to Liberals but Liberals Don't Talk to Conservatives](https://mlsanity.com/paper/2104.05365/) (2021)
- [Discursive objection strategies in online comments: Developing a classification schema and validating its training](https://mlsanity.com/paper/2405.08142/) (2024)

## Abstract (arXiv)

Generative artificial intelligence tools, like ChatGPT, are an increasingly utilized resource among computational social scientists. Nevertheless, there remains space for improved understanding of the performance of ChatGPT in complex tasks such as classifying and annotating datasets containing nuanced language. Method. In this paper, we measure the performance of GPT-4 on one such task and compare results to human annotators. We investigate ChatGPT versions 3.5, 4, and 4o to examine performance given rapid changes in technological advancement of large language models. We craft four prompt styles as input and evaluate precision, recall, and F1 scores. Both quantitative and qualitative evaluations of results demonstrate that while including label definitions in prompts may help performance, overall GPT-4 has difficulty classifying nuanced language. Qualitative analysis reveals four specific findings. Our results suggest the use of ChatGPT in classification tasks involving nuanced language should be conducted with prudence.