International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2015): 6.391 Volume 5 Issue 6, June 2016 www.ijsr.net Licensed Under Creative Commons Attribution CC BY An Approach towards Analysis of Microblogging with Twitter for Evaluating the Branding Trends Anil Ahir 1 , Santosh Tamboli 2 1 Mumbai University, Vidyalankar Institute of Technology, Mumbai, India 2 Assistant Professor, Vidyalankar Institute of Technology, Mumbai, India Abstract: In this project we report study results investigating tweets from various tweeter account holder as a micro-blogging their thoughts and ideas as a form of electronic word-of-mouth for distributing consumer sentiments concerning products. We investigated some micro-blog postings containing labeling comments, sentiments, and opinions. We examined the overall structure of these tweets the types of expressions, and the movement in positive or negative sentiment. We equated automated methods of classifying sentiment in these tweets with manual coding. By this approach we analyzed the range, frequency, timing, and content of tweets In examining tweets for structure and arrangement, the linguistic structure of tweets approximate the linguistic patterns of natural language expressions. We find that twitter is an online tool for customer word of mouth communications and discuss the implications for corporations using micro-blogging as part of their overall marketing strategy. Keywords: Branding, Tweets, polarity, Microblogging 1. Introduction Detecting and identifying the sentiments of the user/s of a particular brand or an event is becoming an important factor to consider when taking care of a large and a varied audience. A sentiment can be defined as an “Expression”. These sentiments define a brand or a products success within its users/ consumers. Thus, a timely sentiment checking can not only help the brand to address the needs of the consumers correctly but also save the brand. A timely step can save the brand. Identifying the pain area of a consumer is critical for the timely acknowledgement of events, like failures in service or defamation etc. that can affect the brands performance and image. An event can be said in both positive and negative statement. The event on any micro-blogging website can range from an appreciation for the quality or satisfaction from the consumable product, or it can be a negative remark like delay in delivery or irresponsible behavior towards a customer by a brand. While studying the remarks made, affecting a brands image, we consider actions/mentions in both the form positive and negative. This technique is the last line of defense when other approaches fail. The foremost challenge in identifying and detecting a positive or a negative remark is the fact that they can be caused by a vast set of events. While studying, researchers have pose number of interesting research problems like modeling, involving statistics and efficient data structure. Nevertheless researchers have not yet gain widespread adaption, as a number of challenges, like calibration and reducing number of false positive rate remain to be unsolved.[1] Figure 1: Cycle of Sentiment Analysis. Motivated by this, the problem of identifying the sentiments of the consumers correlated with a brand or product during a time interval. Sentiments of an entity reflects the goal of gaining the more information about the consumers perception which or without additional meta-data, is often meaningless for the analysis. Data mining techniques are used to identify anomalous behavior. Identified sentiments of a brand or a product by a consumer can be used for a number of applications, like implementing market strategy, user perception, brand loyalty or any event causing an outrage. 2. Problem Definition To identify an event during a time interval and address the events need to the consumer of the respective brand. The system contains three different phases. One is collecting the data set that will of the brands. Second phase consists of analyzing the tweets. Finally third phase is to apply score to find the prevailing sentiments. Paper ID: NOV164424 http://dx.doi.org/10.21275/v5i6.NOV164424 1074