关键词: 特定方面情感分析, 情感依赖, 记忆网络, 多头注意力机制, 门控循环单元

Abstract:

When predicting the emotional polarity of a specific aspect， there is a problem of only depending on a single aspect item and ignoring the emotional dependence between aspect items in the same sentence， a Multi-layer Multi-hop Memory network with Aspect Item and Context Representation （AICR-M³net） was proposed. Firstly， the position weighting information was fused by Bi-directional Gated Recurrent Unit （Bi-GRU）， and the hidden layer output was used as the input of the mixed context coding layer to obtain a context representation with higher semantic relevance to the context. Then， Multi-layer Multi-hop Memory Networks （M³net） was introduced to match aspect words and context many times and word by word to generate aspect word vectors of specific context. At the same time， the emotional dependence between specific aspect item and other aspect items in the sentence was modeled to guide the generation of context vector of specific aspect item. Experimental results on Restaurant， Laptop and Twitter datasets show that the proposed model has the classification accuracy improved by 1.34， 3.05 and 2.02 percentage points respectively， and the F1 score increased by 3.90， 3.78 and 2.94 percentage points respectively， compared with AOA-MultiACIA （Attention-Over-Attention Multi-layer Aspect-Context Interactive Attention）. The above verifies that the proposed model can deal with the mixed information with multiple aspects in context more effectively， and has certain advantages in dealing with the sentiment classification task in specific aspects.

Key words: aspect-specific sentiment analysis, emotional dependence, Memory Network (MN), Multi-Head Attention (MHA) mechanism, Gated Recurrent Unit (GRU)