Towards a user-oriented adaptive system based on sentiment analysis from text

Sentiment analysis has known a big interest over recent years due to the expansion of data. It many applications in different fields such as marketing, psychology, human-computer interaction, eLearning, etc. There are forms sentiment analysis, namely facial expressions, speech, and text. This article is more interested from text it relatively new field still needs effort research. very important for fields, eLearning can be critical determining emotional state students therefore, putting place necessary interactions motivate engage complete their courses. In this article, we present methods that exist literature, beginning selection features or representation, until training prediction model using either supervised unsupervised learning algorithms although there been so much work done domain, improve performance do first need review approaches put on then try discuss improvements certain even proposing approaches.