Text based sentiment analysis

One of the most important parts of running business successfully is analyzing customer's opinion and sentiments[1]. In this paper, the paragraph of sentences given by the customer is accepted and after extracting each and every word, they are checked with the stored (database has been maintained here) parts of speech, articles and negative words. After checking against the database, CFG is used to validate proper formation of the sentences. Each sentences are delimited by `.' or `?' or `!'. Emotions[2] are detected as - positive, negative or neutral sentence. There are 3 types of cases-1. If the paragraph contains more positive sentences than negative, then overall result will be positive. 2. If the number of negative sentence is greater than positive sentence, then the overall result is negative. 3. If there are same numbers of positive and negative sentences in the input paragraph, then the result is neutral and if a sentence has been entered that is a normal statement neither positive nor negative, that will be also considered as neutral.