Analyzing Political Parody in Social Media

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4373–4384 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 4373 Analyzing Political Parody in Social Media Antonis Maronikolakis1∗† Danae S´anchez Villegas2∗ Daniel Preot¸iuc-Pietro3 Nikolaos Aletras2 1 Center for Information and Language Processing, LMU Munich, Germany 2 Computer Science Department, University of Sheffield, UK 3 Bloomberg antmarakis@cis.lmu.de, {dsanchezvillegas1, n.aletras}@sheffield.ac.uk dpreotiucpie@bloomberg.net Abstract Parody is a figurative device used to imitate an entity for comedic or critical purposes and represents a widespread phenomenon in so- cial media through many popular parody ac- counts. In this paper, we present the first com- putational study of parody. We introduce a new publicly available data set of tweets from real politicians and their corresponding parody ac- counts. We run a battery of supervised ma- chine learning models for automatically de- tecting parody tweets with an emphasis on ro- bustness by testing on tweets from accounts unseen in training, across different genders and across countries. Our results show that po- litical parody tweets can be predicted with an accuracy up to 90%. Finally, we identify the markers of parody through a linguistic analy- sis. Beyond research in linguistics and politi- cal communication, accurately and automati- cally detecting parody is important to improv- ing fact checking for journalists and analytics such as sentiment analysis through filtering out parodical utterances.1 1 Introduction Parody is a figurative device which is used to im- itate and ridicule a particular target (Rose, 1993) and has been studied in linguistics as a figura- tive trope distinct to irony and satire (Kreuz and Roberts, 1993; Rossen-Knill and Henry, 1997). Traditional forms of parody include editorial car- toons, sketches or articles pretending to have been authored by the parodied person.2 A new form ∗Equal contribution. †Work was done while at the University of Sheffield. 1Data is available here: https://archive.org/de tails/parody data acl20 2The ‘Kapou Opa’ column by K. Maniatis parodying Greek popular persons was a source of inspiration for this work - https://www.oneman.gr/originals/to -imerologio-karantinas-tou-dimitri-kouts oumpa/ of parody recently emerged in social media, and Twitter in particular, through accounts that im- personate public figures. Highfield (2016) defines parody accounts acting as: a known, real person, for obviously comedic purposes. There should be no risk of mistaking their tweets for their subject’s actual views; these accounts play with stereotypes of these figures or juxtapose their public image with a very different, behind-closed-doors per- sona. A very popular type of parody is political par- ody which plays an important role in public speech by offering irreverent interpretations of political personas (Hariman, 2008). Table 1 shows exam- ples of very popular (over 50k followers) and ac- tive (thousands of tweets sent) political parody ac- counts on Twitter. Sample tweets show how the style and topic of parody tweets are similar to those from the real accounts, which may pose is- sues to automatic classification. While closely related figurative devices such as irony and sarcasm have been extensively studied in computational linguistics (Wallace, 2015; Joshi …

Content truncated to 500 words