How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements

TL;DR

This paper presents a novel approach to automatically identify humorous and unusual scientific papers by leveraging NLP techniques and a specially constructed dataset inspired by the Ig Nobel prize, demonstrating promising results.

Contribution

The work introduces a new task of detecting funny scientific papers and develops classifiers trained on a curated dataset, combining psychology, linguistics, and NLP insights.

Findings

Successfully identified potentially funny papers in a large dataset

Demonstrated the effectiveness of NLP-based classifiers for humor detection

Showed the utility of interdisciplinary approaches in computational humor

Abstract

Humor is an important social phenomenon, serving complex social and psychological functions. However, despite being studied for millennia humor is computationally not well understood, often considered an AI-complete problem. In this work, we introduce a novel setting in humor mining: automatically detecting funny and unusual scientific papers. We are inspired by the Ig Nobel prize, a satirical prize awarded annually to celebrate funny scientific achievements (example past winner: "Are cows more likely to lie down the longer they stand?"). This challenging task has unique characteristics that make it particularly suitable for automatic learning. We construct a dataset containing thousands of funny papers and use it to learn classifiers, combining findings from psychology and linguistics with recent advances in NLP. We use our models to identify potentially funny papers in a large dataset of over 630,000 articles. The results demonstrate the potential of our methods, and more broadly the utility of integrating state-of-the-art NLP methods with insights from more traditional disciplines.