Sentiment Classification based on Linguistic Patterns in Citation Context

When citations occur, authors tend to express their emotions implicitly, which makes it difficult to identify the sentiment of citation context. However, authors will still use specific linguistic patterns to express their emotions in citation context. This article explores the linguistic patterns of emotional expression in citation context, and on this basis recognizes the sentimental polarity of citation context. Conditional random fields (CRF) model is introduced to annotate the logical relationship between syntactic structure and vocabularies in linguistic patterns. By analysing the effect of the generated CRF templates in classifying the subjective/ objective sentences and the positive/negative emotional polarity in citation context, the role of linguistic patterns in classifying the citation sentiment is discussed. Experimental results show that the CRF model based on linguistic patterns is superior to the commonly used support vector machine (SVM) model in both subjective/objective and emotional polarity classification tasks. In the SVM model, the contextual information of citation context is considered by introducing one deep learning model of Word2vec. It shows that extracting linguistic patterns from the citation context helps reflect the way in which an author organizes his/her language in expressing his/her emotions. Extracting these linguistic patterns helps improve the performance of sentiment classification of citation context.