International Journal of Scientific & Engineering Research, Volume 6, Issue 10, October-2015 1345 ISSN 2229-5518 IJSER © 2015 http://www.ijser.org A Survey on Mining User Opinion from Texts and Emoticons Nasiya Najeeb 1 , Sangeetha Jamal 2 Abstract— Opinion mining is a type of natural language processing for tracking the mood of the public about a particular product or topic. Lots of people write their opinions in forums, micro blogging or review websites. This data is very useful for business companies, governments, and individuals, who want to track automatically attitudes and feelings in those sites. Today Social Network Sites (SNS) allows people to express their feelings and convey their emotions via texts as well as emoticons. Information in terms of texts are extracted and clustered into emotions and then classified into positive, negative and neutral. Today the most common approach followed by users is using emoticons along with texts. An emoticon is generally more likely to affect a sentence in which it occurs since it provides a better sentiment expression of a web user. Emoticons are of two types: textual emoticons and graphical emoticons. In this paper, we have described the different approaches used for mining opinion from both texts and emoticons to assist future research in this area. We have performed a systematic literature review process to conduct this survey. Keywords— Sentiment Analysis, Opinion Mining, Text-based sentiment analysis, Emoticon-based sentiment analysis. ——————————  —————————— 1 INTRODUCTION entiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language pro- cessing and is also widely studied in data mining, Web min- ing, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance in business and society as a whole. The growth in sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. Sentiment Analysis is a hotly discussed topic these days. Social networking sites have provided an easy and attrac- tive way to exchange ideas, opinions, attitudes and lots more. When people update their status it gives a picture of what’s going on in their mind. Individuals are always interested in others opinion about products, services, issues and event for finding best choices. So sentiment analysis is always suitable for decision making process. It is a natural phenomenon that good decision can be taken based on the opinion of others. Sentiment analysis is applicable in many areas like marketing products, politics, educational purposes etc. Today many of the social networking sites provide the fa- cility to express opinions using both text and emoticons which helps the public to produce their strong emotions. So there should be methods to mine sentiment from both text and emoticons. In this paper, we have performed a survey on Text- based sentiment analysis and Emoticon-based sentiment anal- ysis and the different methodologies used for this. ———————————————— 1. Nasiya Najeeb is currently pursuing masters degree program in Computer Science and Information System, Rajagiri School of Engineering and Technol- ogy ,Kochi,Kerala, India. E-mail: nasiya.nachu@gmail.com 2. Sangeetha Jamal is currently working as Asst. Professor in the Dept. of Computer Science and Engineering ,Rajagiri School of Engineering and Tech- nology ,Kochi, Kerala, India. The rest of this paper is organized as follows. Section 2 discusses the related works in this area, in section 3 we have discussed the methodology, section 4 gives an overview on text-based sentiment analysis, section 5 gives an overview on emoticon-based sentiment analysis, the different approaches used for both text-based and emoticon-based sentiment analy- sis are discussed in section 6 and finally we conclude in sec- tion 7. 2 RELATED WORKS Many researches have been done on both Text-based sen- timent analysis and Emoticon-based sentiment analysis. Past studies on Text-based sentiment analysis says that automatic detection of emotion in texts is becoming important from an applicative point of view [1]. By analyzing people's sentiment, the emotions of the public toward a particular issue can be observed, experimented and quantified [2].Today may web- sites also provides the facility for using emoticons. We define emoticons as visual cues used in texts to replace normal visual cues like smiling to express, stress, or disambiguate one's sen- timent [3]. Over the years, people have embraced the usage of so-called emoticons as an alternative to face-to-face visual cues in computer-mediated communication like virtual utterances of opinions. Using emoticons along with text helps to strengthen their opinion.Opinion can be collected from any person in the world through review sites, blogs, twitter etc. 3 METHODOLOGY In this survey, we have used a systematic review process. A. SEARCHING Some websites were used for searching. First we tried to search for relevant papers, journals and presentations. Relevant papers were identified using •IEEE Explore •ACM portal S IJSER