Determining Event Outcomes: The Case of #fail

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4021–4033 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4021 Determining Event Outcomes: The Case of #fail Srikala Murugan, Dhivya Chinnappa⇤and Eduardo Blanco Human Intelligence and Language Technologies Lab University of North Texas {srikalamurugan,dhivyainfantchinnappa}@my.unt.edu,eduardo.blanco@unt.edu Abstract This paper targets the task of determining event outcomes in social media. We work with tweets containing either #cookingFail or #bakingFail, and show that many of the events described in them resulted in something edible. Tweets that contain images are more likely to result in edible albeit imperfect outcomes. Experimental results show that edibility is easier to predict than outcome quality. 1 Introduction While the definition of event is controver- sial (Casati and Varzi, 2020; Sprugnoli and Tonelli, 2016), there is general consensus that events occur (or happen, or take place) at a time and location. People share in social media a deluge of informa- tion including events they care about. These events range from mundane events such as eating or watch- ing TV to important life events such as getting mar- ried and graduating from college (Li et al., 2014). Twitter is one of the most popular social networks with 166 million daily active users (Twitter, 2020). An important property of events is whether they actually occurred. The literature has stud- ied this property under different terms, e.g., fac- tuality (Saur´ı and Pustejovsky, 2009; Lee et al., 2015) and veridicality (de Marneffe et al., 2012). Other related tasks have studied the level of com- mitment a speaker or writer has towards a propo- sition (Werner et al., 2015; Jiang and de Marneffe, 2019). Assessing the degree to which an event oc- curred or is believed to be true is critical to make inferences and information extraction. Even when an event is guaranteed to have occurred, however, it is not necessarily the case that the desired outcome came to fruition. For example, people make phone ⇤ Currently at Thomson Reuters.Work done while at University of North Texas. Figure 1: Tweet discussing a baking event. Despite the presence of the #BakingFail hashtag, the baking was not a complete failure. Indeed, it (most likely) resulted in something edible but visually unappealing. calls (presumably) to communicate with whoever they are calling. Making the call, however, does not guarantee that the communication took place— the recipient could have not picked up the phone. Some events have fairly clear desired outcomes even if they are not explicitly stated: people make phone calls to communicate, run in elections so that they are elected, etc. The desired outcomes of other events, however, are not so clear: people may plant a tree to help the environment, to provide privacy or shade, or so that it bears fruit. Like factuality, determining whether an event resulted in the desired outcome is a matter or de- gree and not a binary decision. In other words, events often do not result in perfect outcomes or complete failures. For example, a phone call may result in …

Content truncated to 500 words