Irony in Emojis: A Comparative Study of Human and LLM Interpretation
This research addresses the gap in machine understanding of nuanced online communication, such as irony in emojis, which is important for improving LLM performance in social media contexts, though it appears incremental as it focuses on evaluating an existing model.
This study tackled the problem of interpreting irony in emojis, a challenge for Large Language Models (LLMs), by comparing GPT-4o's interpretations with human perceptions, revealing nuanced insights into its capabilities and highlighting the influence of demographic factors.
Emojis have become a universal language in online communication, often carrying nuanced and context-dependent meanings. Among these, irony poses a significant challenge for Large Language Models (LLMs) due to its inherent incongruity between appearance and intent. This study examines the ability of GPT-4o to interpret irony in emojis. By prompting GPT-4o to evaluate the likelihood of specific emojis being used to express irony on social media and comparing its interpretations with human perceptions, we aim to bridge the gap between machine and human understanding. Our findings reveal nuanced insights into GPT-4o's interpretive capabilities, highlighting areas of alignment with and divergence from human behavior. Additionally, this research underscores the importance of demographic factors, such as age and gender, in shaping emoji interpretation and evaluates how these factors influence GPT-4o's performance.