ValenTO at SemEval-2018 Task 3: Exploring the Role of Affective Content for Detecting Irony in English Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 643–648 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics ValenTO at SemEval-2018 Task 3: Exploring the Role of Affective Content for Detecting Irony in English Tweets Delia Iraz´u Hern´andez Far´ıas Inst. Nacional de Astrof´ısica, ´Optica y Electr´onica (INAOE) Mexico dirazuherfa@hotmail.com Viviana Patti Dip. di Informatica University of Turin Italy patti@di.unito.it Paolo Rosso PRHLT Research Center Universitat Polit`ecnica de Val`encia Spain prosso@dsic.upv.es Abstract In this paper we describe the system used by the ValenTO team in the shared task on Irony Detection in English Tweets at SemEval 2018. The system takes as starting point emotIDM, an irony detection model that explores the use of affective features based on a wide range of lexical resources available for English, reflect- ing different facets of affect. We experimented with different settings, by exploiting different classifiers and features, and participated both to the binary irony detection task and to the task devoted to distinguish among different types of irony. We report on the results ob- tained by our system both in a constrained set- ting and unconstrained setting, where we ex- plored the impact of using additional data in the training phase, such as corpora annotated for the presence of irony or sarcasm from the state of the art. Overall, the performance of our system seems to validate the important role that affective information has for identifying ironic content in Twitter. 1 Introduction People use social media platforms as a forum to share and express themselves by using the lan- guage in creative ways and employing figurative language devices such as irony to achieve differ- ent communication purposes. Irony is closely as- sociated with the indirect expression of feelings, emotions and evaluations, and detecting the pres- ence of irony in social media texts is considered a challenge for research in computational linguis- tics, also for the impact on sentiment analysis, where irony detection is important to avoid mis- interpreting the polarity of ironic statements. Broadly speaking, under the umbrella term of irony two main concepts are covered: verbal irony and situational irony. Verbal irony is commonly defined as a figure of speech where the speaker in- tends to communicate the opposite of what is liter- ally said (Sperber and Wilson, 1986). Situational irony, instead refers to a contradictory or unex- pected outcome of events (Lucariello, 2014). In Twitter we can find many examples both of ver- bal irony and of posts where users describe as- pects of an ironic situation. Most of the proposed approaches to the automatic detection of irony in social media (Riloff et al., 2013; Buschmeier et al., 2014; Pt´aˇcek et al., 2014)take advantage of lexical factors such as n-grams, punctuation marks, among others. Information related to af- fect has been also exploited (Reyes et al., 2013; Barbieri et al., 2014; Hern´andez Far´ıas et al., 2015). Other scholars proposed methods exploit- ing the context surrounding an ironic utterance (Wallace et al., 2015; Karoui et al., 2015). Re- cently, …

Content truncated to 500 words