Extensive use of emoticons such as :) :-) ;) :D :( in the "social media" have drawn attentions of researchers for using them widely in sentiment analysis and other "Natural Language Processing (NLP)" tasks as features entries of sentiment lexicons or to "machine learning algorithms". Although emoticons are a common and strong sign of expression of feelings/sentiments in social platforms, the relation between expression of sentiments and emoticons is not always clear & hence both must be included to draw nearly exact sentiment. Therefore, any such algorithm that deals with expressing the sentiment must take emoticons into account but one has to be extremely careful with the emoticons that are to be considered. In this work we first analyzed & observed the emoticons that are frequently being used in Twitter dataset records, these emoticons were then analyzed for their appearance in texts within the twitter datasets and later we examined the relations among the nature of the sentiment & emoticon used, and also the contexts in which the emoticons are used. Several analysis were then performed to analyze the effect of emoticons on tweets using machine learning techniques. Finally, the overall performance analysis of the classifier was computed using the confusion matrix.