BANN: A Framework for Aspect-Level Opinion Mining

Identifying and extracting opinions on social media has become very important in today's information-rich environment, since we need fast and concise information, diverse experiences, and knowledge from others to make decisions. Aspect-level opinion mining aims to find and aggregate opinions on opinion targets. Previous work has demonstrated that precise modeling of opinion targets within the surrounding context can improve performances. However, how to effectively and efficiently learn hidden word semantics and better represent targets and the context still needs to be further studied. In this paper, we propose bi-directional attention neural networks (BANN) for aspect-level opinion mining. This framework employs two bi-directional long short-term memory (LSTM) to learn opinion targets and the context respectively, followed by an attention mechanism that integrates hidden states learned from both the targets and context. We compare our model with six state-of-the-art baselines on two SemEval 2014 datasets. Experiment results reveal that our model outperforms the baseline methods on both datasets, which indicates the effectiveness of the model. Our work contributes to the improvement of state-of-the-art aspect-level opinion mining methods and offers a new approach to support people during the decision-making process based on opinion mining results.