A Framework for Sentiment Analysis in Persian
Mohammad Ehsan Basiri, Ahmad Reza Naghsh Nilchi, Nasser Ghassem-Aghaee · Open Transactions on Information Processing · 2014
Sentiment Analysis aims at extracting peoples sentiment, opinion, and appraisal from their comments in social websites. Most research efforts in the area of sentiment analysis have concentrated on English and few works considered the problem of Persian sentiment analysis. Persian is spoken by more than a hundred million speakers around the world and is the official language of Iran, Tajikistan, and Afghanistan. Persian is a challenging language for sentiment analysis and there are few resources and tools available for Persian text processing. Therefore, in the current study we first devise a Persian polarity lexicon which is a list of words associated with their sentiment polarity. Then, we review common challenges of Persian language processing such as misspelling, word spacing, stemming, and use of informal words and propose effective solutions for them. Finally, we assess the performance of the proposed method in classifying the polarity of online cell phone reviews. The results show the superiority of our approach compared to the state-of-the-art supervised machine learning methods. Furthermore, our method is more computationally efficient than existing supervised methods.