Paper: Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification

ACL ID P14-2009
Title Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification. AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them. It consists of more than one composition functions, and we model the adaptive sen- timent propagations as distributions over these composition functions. The experi- mental studies illustrate that AdaRNN im- proves the baseline methods. Further- more, we introduce a manually annotated dataset for target-dependent Twitter senti- ment analysis.