YNU-HPCC at SemEval-2018 Task 1: BiLSTM with Attention Based Sentiment Analysis for Affect in Tweets

Abstract

This paper describes the system we built as the YNU-HPCC team in the SemEval-2018 competition. As participants of Task 1, named Affect in Tweets, we implemented the sentiment system for all five subtasks in English and Spanish. All subtasks involved predicting emotion or sentiment intensity (regression and ordinal classification) and determining emotions (multi-label classification). Our system mainly applied the bidirectional long-short term memory (BiLSTM) model with an attention mechanism. We used BiLSTM in order to extract word information from both directions. The attention mechanism was used to find the contribution of each word to improving the scores. Furthermore, based on the BiLSTM with an attention mechanism, a few deep-learning algorithms were employed for different subtasks. For regression and ordinal classification tasks, we used domain adaptation and ensemble learning methods to leverage the base model, while a single base model was used for the multi-label task. Our system achieved very competitive results on the official leaderboard.