Attention Based LSTM for Target Dependent Sentiment Classification

No. 1: Thirty-First AAAI Conference On Artificial Intelligence

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 31

Student Abstract Track

We present an attention-based bidirectional LSTM approach to improve the target-dependent sentiment classification. Our method learns the alignment between the target entities and the most distinguishing features. We conduct extensive experiments on a real-life dataset. The experimental results show that our model achieves state-of-the-art results.

10.1609/aaai.v31i1.11061