Pashto Sentiment Analysis Using Lexical Features
Uzair Kamal, Imran Siddiqi, Hammad Afzal, Ade Ismayani Rahman · 2016
Individuals use various platforms to express their opinion regarding products, services, political situations and other events. Knowing the opinion of people is very important for the concerned individuals and organizations in order to devise future strategies according to the wishes of people. The present research study focuses on extraction of opinion from digital-born Pashto text. The study involved the creation of multiple state-of-the-art classifiers by adapting methodology of message level task using sentiment analysis of Tweets'. In addition to this, word-sentiment lexicons with tokenization of sentences and translation of existing English lexicons were generated. The findings show that lexical features based Pashto sentiment analysis extracts sentiments with a high accuracy.