Abstract
The prevalence that people share their opinions on the products and services in their daily lives on the Internet has generated a large quantity of comment data, which contain great business value. As for comment sentences, they often contain several comment aspects and the sentiment on these aspects are different, which makes it meaningless to give an overall sentiment polarity of the sentence. In this paper, we introduce Attention-based Aspect-level Recurrent Convolutional Neural Network (AARCNN) to analyze the remarks at aspect-level. The model integrates attention mechanism and target information analysis, which enables the model to concentrate on the important parts of the sentence and to make full use of the target information. The model uses bidirectional LSTM (Bi-LSTM) to build the memory of the sentence, and then CNN is applied to extracting attention from memory to get the attentive sentence representation. The model uses aspect embedding to analyze the target information of the representation and finally the model outputs the sentiment polarity through a softmax layer. The model was tested on multi-language datasets, and demonstrated that it has better performance than conventional deep learning methods.
Highlights
Aspect-level sentiment classification, or aspect-based sentiment analysis (ABSA), is a fine-grained sentence analysis, which recognizes the aspects mentioned in the sentence and their corresponding sentiment polarity [1]
Conventional machine learning approaches have an obvious drawback that they treat the sentence as a bag of words and do not consider the sequence and the relationships between aspect terms and its corresponding opinion-indicating words, when the sentiment polarity is often determined by such sequence or relationships
We propose an attention-based aspect level model, Attention-based Aspect-level Recurrent Convolutional Neural Network (AARCNN), to analyze the sentiment polarity at the aspect level
Summary
Aspect-level sentiment classification, or aspect-based sentiment analysis (ABSA), is a fine-grained sentence analysis, which recognizes the aspects mentioned in the sentence and their corresponding sentiment polarity [1]. Conventional machine learning approaches have an obvious drawback that they treat the sentence as a bag of words and do not consider the sequence and the relationships between aspect terms and its corresponding opinion-indicating words, when the sentiment polarity is often determined by such sequence or relationships Another problem is that these models depend too much on the feature engineering and require a quantity of manual preprocessing, which stops them from being more efficient or accurate. The model incorporates attention mechanism and aspect information, and uses the important part of the comment sentence to analyze the sentiment polarity in the aspects. AAtttteennttiioonn DDiissccoovveerr MMoodduullee IInn aa ccoommmmeenntt sseenntteennccee,, oonnllyy aa ffeeww wwoorrddss ddoo ggoooodd ttoo aassppeecctt ddeetteeccttiioonn aanndd sseennttiimmeenntt ppoollaarriittyy jjuuddggeemmeenntt.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have