E-LSTM at SemEval-2019 Task 3: Semantic and Sentimental Features Retention for Emotion Detection in Text

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 190–194 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 190 E-LSTM at SemEval-2019 Task 3: Semantic and Sentimental Features Retention for Emotion Detection in Text Harsh Patel Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar 201701021@daiict.ac.in Abstract This paper discusses the solution to the prob- lem statement of the SemEval19: EmoContext competition(Chatterjee et al., 2019b) which is ”Contextual Emotion Detection in Texts”. The paper includes the explanation of an architec- ture that I created by exploiting the embedding layers of Word2Vec and GloVe using LSTMs as memory unit cells which detects approxi- mate emotion of chats between two people in the English language provided in the textual form. The set of emotions on which the model was trained was Happy, Sad, Angry and Oth- ers. The paper also includes an analysis of different conventional machine learning algo- rithms in comparison to E-LSTM. 1 Introduction Emotions are the basic human quality that al- most every human possesses. According, to a re- cent study by Glasgow University1, human emo- tions can be divided into six basic classes which are happiness, sadness, anger, fear, surprise and disgust, surprise being the most difficult one as both positive and negative statements can lead to a sense of surprise. For example, the statement Your application for CSE branch in Stanford Uni- versity is accepted is positive and it leads to sur- prise whereas the statement Your brother met with an accident is a negative statement which all leads to a surprise. Problem Statement: Given a text for three turn conversation, classify the emotion of the text in the following four categories - Happy, Sad, Angry, Others. 1https://www.gla.ac.uk/news/ archiveofnews/2014/february/headline_ 306019_en.html 2WhatsApp is used as a messaging platform to illustrate the three turn conversation approach Figure 1. Example of three turn conversation2 Detecting human emotions only from the text is very difficult as the emotions are a combination of the situation and the facial expressions of a per- son(Cowie et al., 2001). So, merely classifying it from the conversation is not a very accurate way. In this paper, I have proposed an extended approach to the original model(Chatterjee et al., 2019a) which combines deep learning along with some techniques used in Natural Language Pro- cessing(NLP) using semantic and embedding ap- proach (Franco-Salvador et al., 2018; Shivhare and Khethawat, 2012) called as ”Emotion LSTM” or E-LSTM to detect emotions in the provided training set. The E-LSTM is a combination of both count-based and predictive techniques which are widely used in Natural Language Processing. 2 Approach My approach in solving the given problem state- ment was to maintain the semantic and sentimental relationship among the words(Gupta et al., 2017). So, as shown in Figure 2, I modeled the archi- tecture such that the lower part contains the em- beddings for sentiment analysis whereas the up- per part contains the embeddings for maintain- ing a semantic relationship. The embeddings are then passed onto a network of …

Content truncated to 500 words