Understanding Satirical Articles Using Common-Sense

Understanding Satirical Articles Using Common-Sense Dan Goldwasser Purdue University Department of Computer Science dgoldwas@purdue.edu Xiao Zhang Purdue University Department of Computer Science zhang923@purdue.edu Abstract Automatic satire detection is a subtle text clas- sification task, for machines and at times, even for humans. In this paper we argue that satire detection should be approached using common-sense inferences, rather than tradi- tional text classification methods. We present a highly structured latent variable model cap- turing the required inferences. The model ab- stracts over the specific entities appearing in the articles, grouping them into generalized categories, thus allowing the model to adapt to previously unseen situations. 1 Introduction Satire is a writing technique for passing criticism using humor, irony or exaggeration. It is often used in contemporary politics to ridicule individual politicians, political parties or society as a whole. We restrict ourselves in this paper to such politi- cal satire articles, broadly defined as articles whose purpose is not to report real events, but rather to mock their subject matter. Satirical writing often builds on real facts and expectations, pushed to ab- surdity to express humorous insights about the situ- ation. As a result, the difference between real and satirical articles can be subtle and often confusing to readers. With the recent rise of social media outlets, satirical articles have become increasingly popular and have famously fooled several leading news agencies1. These misinterpretations can often 1https://newrepublic.com/article/118013/ satire-news-websites-are-cashing-gullible- outraged-readers Vice President Joe Biden suddenly barged in, asking if anyone could “hook [him] up with a Dixie cup” of their urine. “C’mon, you gotta help me get some clean whiz. Shinseki, Donovan, I’m looking in your direction” said Biden. “Do you want to hit this?” a man asked President Barack Obama in a bar in Denver Tuesday night. The president laughed but didn’t indulge. It wasn’t the only time Obama was offered weed on his night out. Figure 1: Examples of real and satirical articles. Top: satirical news excerpt. Bottom: real news excerpt. be attributed to careless reading, as there is a clear line between unusual events finding their way to the news and satire, which intentionally places key po- litical figures in unlikely humorous scenarios. The two can be separated by carefully reading the arti- cles, exposing the satirical nature of the events de- scribed in such articles. In this paper we follow this intuition. We look into the satire detection task (Burfoot and Bald- win, 2009), predicting if a given news article is real or satirical, and suggest that this prediction task should be defined over common-sense inferences, rather than looking at it as a lexical text classifica- tion task (Pang and Lee, 2008; Burfoot and Bald- win, 2009), which bases the decision on word-level features. To further motivate this observation, consider the two excerpts in Figure 1. Both excerpts mention top-ranking politicians (the President and Vice Pres- ident) in a drug-related context, and contain infor- mal slang utterances, inappropriate for the subjects’ 537 Transactions of the Association for Computational Linguistics, vol. 4, …

Content truncated to 500 words