Emotion classification on youtube comments using word embedding

Youtube is one of the most popular video sharing platform in Indonesia. A person can react to a video by commenting on the video. A comment may contain an emotion that can be identified automatically. In this study, we conducted experiments on emotion classification on Indonesian Youtube comments. A corpus containing 8,115 Youtube comments is collected and manually labelled using 6 basic emotion label (happy, sad, angry, surprised, disgust, fear) and one neutral label. Word embedding is a popular technique in NLP, and have been used in many classification tasks. Word embedding is a representation of a word, not a document, and there are many methods to use word embedding in a text classification task. Here, we compared many methods for using word embedding in a classification task, namely average word vector, average word vector with TF-IDF, paragraph vector, and by using Convolutional Neural Network (CNN) algorithm. We also study the effect of the parameters used to train the word embedding. We compare the performance of the classification with a baseline, which was previously state-of-the-art, SVM with Unigram TF-IDF. The experiments showed that the best performance is achieved by using word embedding with CNN method with accuracy of 76.2%, which is an improvement from the baseline.