ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 600–606 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods Zhenghang Yin1, Feixiang Wang1, Man Lan1,2, Wenting Wang3 1Department of Computer Science and Technology, East China Normal University, Shanghai, P.R.China 2Shanghai Key Laboratory of Multidimensional Information Processing 3Alibaba Group {10142130151,51151201049}@stu.ecnu.edu.cn, mlan@cs.ecnu.edu.cn, nantiao.wwt@alibaba-inc.com Abstract The paper describes our submissions to task 3 in SemEval 2018. There are two subtasks: Subtask A is a binary classification task to de- termine whether a tweet is ironic, and Subtask B is a fine-grained classification task including four classes. To address them, we explored su- pervised machine learning method alone and in combination with neural networks. 1 Introduction Irony, also known as sarcasm, refers to the use of words and sentences, whose intended meanings contrary to their literal meanings. Modeling irony has a large potential for applications in various research areas, so SemEval2018-Task3 (Hee et al.) aims to classify irony into different classes. There are two subtasks. In subtask A, when giv- en a tweet, the classifier should predict whether the tweet is ironic or non-ironic, and in subtask B, the ironic class is further divided into another three categories, i.e., irony by Polarity contrast, by Situational and Other verbal irony. Polarity contrast irony represents the tweets containing an expression whose polarity (positive, negative) is inverted between the literal and the intended meaning. Situational irony stands for the ones which don’t contain explicit polarity contrast. However, the events or results described in them are contrary to the desired or expected common knowledge. Other verbal irony tweets also don’t contain any explicit polarity contrast, but they can’t be classified into the Situational irony. Finally, non-ironic contains instances which are clearly not ironic, or lack adequate context to be sure that they are ironic. In the remaining of the paper, section 2 describes our system in details. Section 3 reports datasets, experiments and results discussions. Finally, Section 4 concludes our work. 2 System Description In both subtasks we used supervised machine learning to model the irony in datasets. Moreover, we explored neural networks in subtask A. • In subtask A, we built a binary classification system to make predictions (see in 2.2.1). Then, we combine it with a Bi-LSTM neural networks(see in 2.2.2). • In subtask B, we used two machine learning systems to train and evaluate. 1. 4-class classification system: We made use of classifier directly itself to make 4-class predictions. 2. 4 binary-classification system: We de- signed a two-step system as follows: – Step 1 The entire problem was regarded as 4 binary-classification problems. Each tweet would be trained and evaluated within classes, and 4 confidence values4 would be returned. – Step 2 The classifier would allocate each tweet with a label gaining the highest confidence, and then made evaluation. 2.1 Feature Engineering 4 types of features were designed to extract effec- tive information …

Content truncated to 500 words