Abstract
Dimensional sentiment analysis aims to recognize continuous numerical values in multiple dimensions such as the valence-arousal (VA) space. Compared to the categorical approach that focuses on sentiment classification such as binary classification (i.e., positive and negative), the dimensional approach can provide a more fine-grained sentiment analysis. This article proposes a tree-structured regional CNN-LSTM model consisting of two parts: regional CNN and LSTM to predict the VA ratings of texts. Unlike a conventional CNN which considers a whole text as input, the proposed regional CNN uses a part of the text as a region, dividing an input text into several regions such that the useful affective information in each region can be extracted and weighted according to their contribution to the VA prediction. Such regional information is sequentially integrated across regions using LSTM for VA prediction. By combining the regional CNN and LSTM, both local (regional) information within sentences and long-distance dependencies across sentences can be considered in the prediction process. To further improve performance, a region division strategy is proposed to discover task-relevant phrases and clauses to incorporate structured information into VA prediction. Experimental results on different corpora show that the proposed method outperforms lexicon-, regression-, conventional NN and other structured NN methods proposed in previous studies.
Highlights
S ENTIMENT analysis refers to the use of computational linguistics to analyze, process, induce and deduce subjective texts with affective information [1]–[5]
This study proposes a regional convolutional neural networks (CNN)-long short-term memory (LSTM) model consisting of two parts, regional CNN and LSTM, to predict the VA ratings of texts
The procedure for using a tree-structured regional CNNLSTM model for VA prediction consists of two parts: the regional CNN-LSTM model and a regional division strategy
Summary
S ENTIMENT analysis refers to the use of computational linguistics to analyze, process, induce and deduce subjective texts with affective information [1]–[5]. The most commonly used approach is based on the valence-arousal space proposed by Russell et al [16], which can accurately represent the affective state in a 2-dimentional continuous space In this space, the dimension of valence refers to the degree of positive and negative sentiment, whereas the dimension of arousal refers to the degree of calm and excitement. CNN uses a convolutional kernel to extract local n-gram features and max-pooling to select the most salient features for prediction This often misses valuable information present in multiple facts within a very long sentence, and may fail to capture long-distance dependency. To capture both local and long-distance information, an LSTM layer can be combined with a CNN layer to form a CNN-LSTM model Such NN-based and word embedding methods have not been well explored for dimensional sentiment analysis.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE/ACM Transactions on Audio, Speech, and Language Processing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
