When a Computer Cracks a Joke: Automated Generation of Humorous Headlines

TL;DR

This paper introduces a computational approach for generating humorous headlines from existing news titles, achieving a notable level of humor as judged by human evaluators, advancing automated news content creativity.

Contribution

The paper presents a novel system for automated humorous headline generation, moving beyond template-based methods to produce more creative and engaging titles.

Findings

36% of generated headlines are considered funny by humans

System outperforms template-based approaches in humor quality

Evaluations show promising potential for automated humor creation

Abstract

Automated news generation has become a major interest for new agencies in the past. Oftentimes headlines for such automatically generated news articles are unimaginative as they have been generated with ready-made templates. We present a computationally creative approach for headline generation that can generate humorous versions of existing headlines. We evaluate our system with human judges and compare the results to human authored humorous titles. The headlines produced by the system are considered funny 36\% of the time by human evaluators.