Loading...

Persian Aspect-based Sentiment Analysis Using Learning Methods

Sabeti, Behnam | 2015

419 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47495 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Ghassem Sani, Gholamreza
  7. Abstract:
  8. As digital content grows rapidly due to the internet, user reviews about different topics such as product quality can be used as a rich source to check and analyze product quality and performance. Automatic methods are being widely used to extract these information because of the massive amount of available resources. Sentiment analysis is one of the important fields in natural language processing, which uses a combination of learning and rule-based methods to extract subjective information out of documents. Aspect based sentiment analysis deals with sentiment analysis based on each aspect of the product. It consists of two main steps: first, aspects should be extracted from the reviews and then, user’s sentiment toward each aspect is analyzed. One of popular methods for sentiment analysis is to use a sentiment lexicon that associates each word with a sentiment polarity. In this project, a Persian sentiment lexicon has been developed using FarsNet ontology. Graph analysis has been employed in order to minimize the required hand-labeled words. A new method for aspect based sentiment analysis in Persian has then been developed. The proposed method consists of a learning stage followed by a rule-based system. Aspects are extracted using the conditional random fields method and then the sentiment lexicon developed earlier, is employed to analyze sentiment toward each aspect. The resulting system has been tested on the SentiPers sentiment corpus. According to the final evaluation results, Aspect extraction has a compelling performance of 73%, although sentiment analysis toward each aspect performs poorly due to informal structure of the input sentences
  9. Keywords:
  10. Natural Language Processing ; Machine Learning ; Ontology ; Conditional Random Fields (CRF) ; Data Mining ; Sentiment Analysis ; Sentiment Lexicon

 Digital Object List

 Bookmark

No TOC