Sentiment Analysis

Opinions in natural language are mostly expressed in very complex manner. This makes very difficult for computer to completely understand a document written in a language. Sentiment analysis(opinion mining) refers to use of natural language processing to systematically identify, extract, quantify, and study these opinions. Since huge amount of information is available in on-line documents, obtaining some valuable information from these documents such as sentiments or opinions people express about a specific object is a task that attracts attention. Finding opinion sources, extracting related sentences, reading and summarizing and organizing them into usable form is an extremely challenging task for a human. In my project, I developed a document-level sentiment analysis system to overcome this challenge by using words in a document, their frequencies and part-of-speech(POS) tags.