International Journal of Computer Applications (0975 – 8887) Volume 94 – No 13, May 2014 42 Feature Ranking in Sentiment Analysis Maryam K. Jawadwala P.G. Student, Department of Computer Engineering, Thadomal Sahani Engineering College, Bandra, Mumbai, India Seema Kolkur Assistant professor, Department of Computer Engineering, Thadomal Sahani Engineering College, Bandra, Mumbai, India ABSTRACT With the rapid expansion of e-commerce over the past 15 years, more products are sold on the Web. More and more people are buying products online. In order to enhance customer shopping experience, it has become a common practice for online merchants to enable their customers to write reviews on products that they have purchased. Some popular products can get hundreds of reviews or more at some large merchant sites. Manual analysis of customer opinions is only possible to a certain extent and very time-consuming due to the multitude of contributions.From the e-commerce perspective, receiving consumer’s feedback can greatly improve its strategies in order to increase products of the sector. This research work will present feature wise sentiment analysis of customer review. The goal of feature level sentiment analysis is to produce a feature-based opinion summary of multiple reviews . With summaries of opinions and features of the product, people can make effective decisions in less time. Such mining can be helpful for competitive marketing. Feature extraction can be performed using two approaches. Rule-based algorithm and HAC algorithm. Feature ranking will be done using MAX opinionscore algorithm and opinion score obtained from SentiWordNet. Keywords Sentiment analysis, Opinion mining, Feature ranking, Natural language processing 1. INTRODUCTION Opinion Mining is a field of Web Content Mining that aims to find valuable information out of users opinions. Mining opinions on the web is a fairly new area, and its importance has grown significantly mainly due to the fast growth of e- commerce, blogs and forums. The World Wide Web has grown exponentially in recent years both in terms of size and diversity of the contents provided [1]. It has contributed a very large amount of data termed as user generated content. These new contents include customer reviews, blogs, and discussion forums which expresses customer satisfaction/dissatisfaction on the product and its features explicitly. Most of the time the customer does not directly indicate the choice in a straight forward manner but does so in sentences which contain the actual reviews along with lines which are general in nature and has nothing to do about the product or opinion. Such sentences are challenging due to many reasons like, user not writing the features explicitly, writing incorrect sentences, omitting punctuation marks and writing grammatical incorrect language [12]. As customer feedback influences other customer decisions about buying the product, these feedbacks have become an important source of information for businesses when developing marketing strategies and segmenting the customers. The difficulty lies in the fact that majority of the customer reviews are very long and their numbers are also very high which makes the process of distillation of knowledge a very difficult task. Most of the times a user will read a few reviews and will try to make a decision about the product. The chances that a user will end up taking a biased decision about the product are not ruled out. Similarly, manufacturers want to read the reviews to identify what elements of a product affect sales most and what are the features the customer likes or dislikes so that the manufacture can target on those areas. More importantly, the large number of reviews makes it hard for product manufacturers or business to keep track of customer’s opinions and sentiments on their products and services. There are many areas where sentiment analysis can be used as following [12]: 1) A company is interested in customer's perceptions about its products and the information may be used to improve products and identifying new marketing strategies. Sentiment Analysis is used to find these customers’ perception about product from the thousands of review. 2) Tourists want to know the best places or famous restaurants to visit. Sentiment analysis can be used to obtained relevant information for planning a trip. 3) By applying sentiment analysis we can detect the users opinion from the posted movie reviews on specialized sites. 1.1 Sentiment Classification There are three types of opinion mining approaches [8]. [1] Feature level or Phrase level In this, for the product, the particular features are classified and for those features, the comments or reviews are taken separately. [2] Sentence level In this, the comments or reviews are opinionated. The benefit of this approach is in this, the customer can come to know about so many different types of customer’s reviews. In this approach, it mainly differentiates between the subjective and objective information. The subjective information is the opinion, which can be negative or positive and the objective information is the fact. [3] Document level In this the whole document is written for the product, it is written by only one person. So, it is not as useful because the customer will come to know the review of only one customer. 2. DATA SOURCE User’s opinion is a major criterion for the improvement of the quality of services rendered and enhancement of the deliverables. Blogs, review sites, data and micro blogs