CLARK at SemEval-2019 Task 3: Exploring the Role of Context to Identify Emotion in a Short Conversation

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 159–163 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 159 CLARK at SemEval-2019 Task 3: Exploring the Role of Context to Identify Emotion in a Short Conversation Joseph R. Cummings Northwestern University jcummings@u.northwestern.edu Jason R. Wilson Northwestern University jrw@northwestern.edu Abstract With text lacking valuable information avail- able in other modalities, context may provide useful information to better detect emotions. In this paper, we do a systematic exploration of the role of context in recognizing emotion in a conversation. We use a Na¨ıve Bayes model to show that inferring the mood of the con- versation before classifying individual utter- ances leads to better performance. Addition- ally, we find that using context while train- ing the model significantly decreases perfor- mance. Our approach has the additional bene- fit that its performance rivals a baseline LSTM model while requiring fewer resources. 1 Introduction Recognizing affect (emotional content) in text has been an ongoing research challenge for roughly 20 years. While earlier work focused on larger bodies of text, like movie reviews for sentiment analysis (Pang et al., 2002) or classifying mood in blog posts (Mishne et al., 2005), more recent work has looked at small bodies of text, particularly text from social media. With smaller bodies of text inherently having less information, current efforts are investigating how context may supplement the information. However, it is not yet clear how best to incorporate context. To this end, we explore how mood and emotion from previous messages may be used to better recognize emotions. Mood and emotion are generally regarded as two types of affect. Emotions are reactions and have a limited duration (Ortony et al., 1990; Schwarz and Clore, 2006). While emotions are dynamic and constantly changing, mood reflects a more persistent affect that can influence cogni- tive processes (Busemeyer et al., 2007), includ- ing how people recognize emotions (Schmid and Mast, 2010). For this work, we view mood as the affect present in the whole conversation and emo- tion as what is expressed in a given turn. Figure 1: Example of a three turn conversation Our goal is to take a short, online conversation (see Figure 1) and categorize the last utterance as happy, sad, angry, or others. In this paper, we present our model Conversational Lexical Affect Recognition Kit (CLARK), which is the result of a systematic exploration into how context may be used during the training and classification phases of a model to improve emotion recognition. To as- sess context we infer the mood of the conversation and the emotions of previous utterances. Although context would seem to be useful, providing addi- tional information, we find that is only beneficial during classification. Conversely, including con- text while training the model leads to significantly degraded performance. 2 Related Work There are several approaches to recognizing affect in a body of text. Many have used classification methods on a large body of text, such as movie reviews (Pang et …

Content truncated to 500 words