Encoding syntactic representations with a neural network for sentiment collocation extraction

Abstract

Sentiment collocation refers to the collocation of a target word and a polarity word. Sentiment collocation extraction aims to extract the targets and their modifying polarity words by analyzing the relationships between them. This can be regarded as a basic sentiment analysis task and is relevant in many practical applications. Previous studies relied mainly on the syntactic path, which is used to connect the target word and the polarity word. To deeply exploit the semantic information of the syntactic path, we propose two types of syntactic representation, namely, relation embedding and subtree embedding, to capture the latent semantic features. Relation embedding is used to represent the latent semantics between targets and their corresponding polarity words, and subtree embedding is used to explore the rich syntactic information for each word on the path. To combine the two types of syntactic representations, a neural network is constructed. We use a recursive neural network (RNN) to model the subtree embeddings, and then the subtree embedding and the word embedding are combined as the enhanced word representation for each word in the syntactic path. Finally, a convolutional neural network (CNN) is adopted to integrate the two types of syntactic representations to extract the sentiment collocations from reviews. Our experiments were conducted on six types of reviews, which included product domains (such as cameras and phones) and service domains (such as hotels and restaurants). The experimental results show that our proposed method can accurately capture the latent semantic features hidden behind the syntactic paths that neither the common feature-based methods nor the syntactic-path-based method can handle, and, further, that it significantly outperforms numerous baselines and previous methods.

Research on Sentiment Classification Algorithms on Online Review

“…Convolutional Netural Network (CNN, for short) and Recurrent Neural Network (RNN, for short) have been proved to be effective models for effective classification tasks in the nonlinear system. In terms of the emotional classification of the text, some models of cyclic neural network and convolutional neural network are used to classify the emotions of the short text, and excellent results were obtained [16][17][18][19][20]. However, due to the gradient explosion problem of RNN model, LSTM and GRU models based on the RNN model are more commonly used models [21][22][23][24][25].…”

Sentiment analysis using deep learning approaches: an overview

“…In addition to the aforesaid tasks, Pozzi et al [1] consolidated other tasks including emotion detection suggested in 2005 [23], opinion spam detection instigated in 2008 [24], multi-lingual sentiment analysis initiated in 2009 [25], multi-modal sentiment analysis introduced in 2011 [26] and opinion summarization [20]. Furthermore, there are other tasks like sentiment dynamic tracking [27] popularized in 2012 and sentiment collocation [28] that involves the extraction of the targets and related opinion terms based on their correlation.…”

EWA-GBDT: A Novel Air Quality Prediction Model Combining Exponentially Weighted Averages and Gradient Boosting Decision Tree

“…[20] et al designed Friend++, a hybrid multi-individual recommendation model that integrates a weighted average method into the random walk framework by seamlessly employing social ties, behavior context, and personal information. References [21], [22] construct neural network models to mine deep information between features respectively from emotional analysis and semantics of social relationships.…”