Sentiment Representation Research Articles

A quantum-inspired sentiment representation model for twitter sentiment analysis

Sentiment analysis aims to capture the diverse sentiment information expressed by authors in given natural language texts, and it has been a core research topic in many artificial intelligence areas. The existing machine-learning-based sentiment analysis approaches generally focus on employing popular textual feature representation methods, e.g., term frequency-inverse document frequency (tf-idf), n-gram features, and word embeddings, to construct vector representations of documents. These approaches can model rich syntactic and semantic information, but they largely fail to capture the sentiment information that is central to sentiment analysis. To address this issue, we propose a quantum-inspired sentiment representation (QSR) model. This model can not only represent the semantic content of documents but also capture the sentiment information. Specifically, since adjectives and adverbs are good indicators of subjective expression, this model first extracts sentiment phrases that match the designed sentiment patterns based on adjectives and adverbs. Then, both single words and sentiment phrases in the documents are modeled as a collection of projectors, which are finally encapsulated in density matrices through maximum likelihood estimation. These density matrices successfully integrate the sentiment information into the representations of documents. Extensive experiments are conducted on two widely used Twitter datasets, which are the Obama-McCain Debate (OMD) dataset and the Sentiment140 Twitter dataset. The experimental results show that our model significantly outperforms a number of state-of-the-art baselines and demonstrate the effectiveness of the QSR model for sentiment analysis.

Augmented sentiment representation by learning context information

Identifying sentiment polarity of a document is a building block of sentiment analysis and natural language processing tasks, and it aims to automate the prediction of a user’s sentiment orientation in the document about a product, on assumption that the document expresses a sentiment on a single product. In general, supervised machine learning models like support vector machine and recently fast-growing deep neural networks method have been extensively used as a sentiment learning approach. Although some neural network-based models learn text features without feature engineering, most of them only focus on extracting semantic representations from single words and rarely consider the contexts attributed to the correlation between words and sentences. In this paper, we propose a novel neural network model to capture the context information from texts. Our model builds a hybrid neural network model using convolutional neural networks and long short-term memory for word context extraction and document representation, respectively. On this basis, user’s and product’s information can be incorporated into the model. The experimental results show the competitive performance of our model, compared to all state-of-the-art methods.

Learning Sentiment-Specific Word Embedding via Global Sentiment Representation

Context-based word embedding learning approaches can model rich semantic and syntactic information. However, it is problematic for sentiment analysis because the words with similar contexts but opposite sentiment polarities, such as good and bad, are mapped into close word vectors in the embedding space. Recently, some sentiment embedding learning methods have been proposed, but most of them are designed to work well on sentence-level texts. Directly applying those models to document-level texts often leads to unsatisfied results. To address this issue, we present a sentiment-specific word embedding learning architecture that utilizes local context informationas well as global sentiment representation. The architecture is applicable for both sentence-level and document-level texts. We take global sentiment representation as a simple average of word embeddings in the text, and use a corruption strategy as a sentiment-dependent regularization. Extensive experiments conducted on several benchmark datasets demonstrate that the proposed architecture outperforms the state-of-the-art methods for sentiment classification.