2019/09/30 by Kia Dashtipour, Mandar Gogate, Dashtipour, Kia +9
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Sentiment Analysis and Opinion Mining #Text and Document Classification Technologies
paper · pdf · doi:10.48550/arxiv.1909.13568
openalex publication_date 2019/09/30 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Social media hold valuable, vast and unstructured information on public\nopinion that can be utilized to improve products and services. The automatic\nanalysis of such data, however, requires a deep understanding of natural\nlanguage. Current sentiment analysis approaches are mainly based on word\nco-occurrence frequencies, which are inadequate in most practical cases. In\nthis work, we propose a novel hybrid framework for concept-level sentiment\nanalysis in Persian language, that integrates linguistic rules and deep\nlearning to optimize polarity detection. When a pattern is triggered, the\nframework allows sentiments to flow from words to concepts based on symbolic\ndependency relations. When no pattern is triggered, the framework switches to\nits subsymbolic counterpart and leverages deep neural networks (DNN) to perform\nthe classification. The proposed framework outperforms state-of-the-art\napproaches (including support vector machine, and logistic regression) and DNN\nclassifiers (long short-term memory, and Convolutional Neural Networks) with a\nmargin of 10-15% and 3-4% respectively, using benchmark Persian product and\nhotel reviews corpora.\n