الفهرس | Only 14 pages are availabe for public view |
Abstract Multilingual language models have decreased the barrier between languages, as it will help overcome many problems, such as sentiment analysis because the importance of this task is to make good decisions and customize products. Obtaining information from one language can help other languages generalize and understand a task more effectively. In this thesis, we propose a general method for sentiment analysis of data that includes data from many languages, which enables all applications to use sentiment analysis results in a language-blind or language-independent manner. We performed experiments on two language combinations (English and Arabic) for sentence-level sentiment classification and found that the model with the final setup after adding translations from one language to another and finetuning the multilingual language model for Twitter, was the best setup, achieving . and . f -score for English and Arabic, respectively. Our research focused on sarcasm detection, where we fine-tuned a multilingual model. The exciting outcome is a single model that performs well in both English and Arabic, showcasing effective cross-language capabilities for sarcasm identification. |