Loading...

Cross-Lingual Sentiment Analysis of Persian Text Using Deep Learning

Mohayeji Nasrabadi, Hamid | 2019

396 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52715 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Ghasem-Sani, Gholamreza
  7. Abstract:
  8. One of the subfields of natural language processing is sentiment analysis. Generally, sentiment analysis, analyzes the positivity, or negativity of an opinion expressed in a sentence or document. Because each person's opinions have a huge impact on the decisions of other people and businesses, automatic analysis of texts has a particular importance; on which, extensive researches have been conducted in recent years. One of the common problems in sentiment analysis of some languages, including Persian, is the lack of proper resources in them. Cross-lingual sentiment analysis is one solution to this problem. In these methods, the goal is, through using the rich resources available in a source language, the models learned in this language to be transferred to a target language, with insufficient resources for direct learning. In this study, by using deep learning and generative adversarial networks, an unsupervised model is developed that, is able to transfer knowledge learned from English to Persian, and use it in the sentiment analysis of Persian language sentences. The input of the proposed model is a set of bilingual words embeddings; in produce of which, two sets of monolingual word embeddings have been combined, to provide a common representation for Persian and English vocabulary. The accuracy of the proposed model, with a 5-class confusion matrix, is 46.92%
  9. Keywords:
  10. Natural Language Processing ; Sentiment Analysis ; Deep Learning ; Generative Adversarial Networks

 Digital Object List

 Bookmark

No TOC