NEUROSENT-PDI at SemEval-2018 Task 3: Understanding Irony in Social Networks Through a Multi-Domain Sentiment Model

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 512–519 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics NEUROSENT-PDI at SemEval-2018 Task 3: Understanding Irony in Social Networks Through a Multi-Domain Sentiment Model Mauro Dragoni Fondazione Bruno Kessler Via Sommarive 18 Povo, Trento, Italy dragoni@fbk.eu Abstract This paper describes the NeuroSent system that participated in SemEval 2018 Task 3. Our system takes a supervised approach that builds on neural networks and word embeddings. Word embeddings were built by starting from a repository of user generated reviews. Thus, they are specific for sentiment analysis tasks. Then, tweets are converted in the correspond- ing vector representation and given as input to the neural network with the aim of learning the different semantics contained in each emo- tion taken into account by the SemEval task. The output layer has been adapted based on the characteristics of each subtask. Prelimi- nary results obtained on the provided training set are encouraging for pursuing the investiga- tion into this direction. 1 Introduction Sentiment Analysis is a natural language process- ing (NLP) task (Dragoni et al., 2015a) which aims at classifying documents according to the opin- ion expressed about a given subject (Federici and Dragoni, 2016a,b). Many works available in the literature address the sentiment analysis problem without distinguishing specific information con- text of documents when sentiment models are built. The necessity of investigating this problem from a multi-domain perspective is led by the dif- ferent influence that a term might have in dif- ferent contexts. The idea of adapting terms po- larity to different domains emerged only in the last decade (Blitzer et al., 2007; Dragoni and Petrucci, 2017). Multi-domain sentiment analy- sis approaches discussed in the literature focus on building models for transferring information be- tween pairs of domains (Dragoni, 2015; Petrucci and Dragoni, 2015). While on the one hand such approaches allow to propagate specific domain in- formation to others, their drawback is the neces- sity of building new transfer models every time a new domain has to be analyzed. Thus, such ap- proaches do not have a great generalization capa- bility of analyzing texts, because transfer models are limited to the N domains used for building the models. The problem of detecting irony in text can be considered from a multi-domain perspective. The development of the social web has stimulated cre- ative and figurative language use like irony. This frequent use of irony on social media has im- portant implications for natural language process- ing tasks, which struggle to maintain high perfor- mance when applied to ironic text (Liu and Zhang, 2012; Maynard and Greenwood, 2014; Ghosh and Veale, 2016). Although different definitions of irony co-exist, it is often identified as a trope or figurative language use whose actual meaning dif- fers from what is literally enunciated. As such, modeling irony has a large potential for applica- tions in various research areas, including text min- ing, author profiling, detecting online harassment, and perhaps one of the most popular …

Content truncated to 500 words