作者: Mohammed N. Al-Kabi , Nawaf A. Abdulla , Mahmoud Al-Ayyoub
DOI: 10.1109/ICITST.2013.6750168
关键词:
摘要: The problem of automatically extracting opinions and emotions from textual data have gained a lot interest recently. Unfortunately, most studies on Sentiment Analysis (SA) focus mainly the English language, whereas considering other important wide-spread languages such as Arabic are few. Moreover, publicly-available datasets seldom found Web. In this work, labeled dataset reviews/comments is collected social networking website (Yahoo!-Maktoob). A detailed analysis different aspects reviews' length, numbers likes/dislikes, polarity distribution used presented. Finally, to test popular classifiers commonly for SA.