Social media is defined as a web based and mobile based Internet application which allows us to communicate with others. This yields to creation, access and exchange of the large user generated data which is easily accessible for everyone who want to do research in that area. Before social media we access blogs, news feeds, wikis all give the unstructured type of data which we access from the web.
Nowadays, people prefer electronic media and internet generated reviews for taking any sort of decisions. Sentimental Analysis helps to know about the real opinion of different people regarding specific product, company, movies, news, any object and their attributes. It includes number of different branches like natural language processing, machine learning, text mining etc. By using these techniques and models, data is classified in the form of news articles, blogs, tweets, online reviews etc. into the positive, negative or neutral sentiments. Facebook is a kind of micro-blogging social networking site consisting of billions of users in these days. we have used R studio environment that offers number of packages to analyse data, graphics designing etc. However, R language is mostly used for the statistical problems.
K-Nearest neighbour classifiers are defined by their characteristic of classifying unlabelled examples by assigning them the class of the most similar labelled examples. Despite the simplicity of this idea, nearest neighbour methods are extremely powerful. They have been used successfully for: • Computer vision applications, including optical character recognition and facial recognition in both still images and video • Predicting whether a person enjoys a movie which he/she has been recommended (as in the Netflix challenge) • Identifying patterns in genetic data, for use in detecting specific proteins or diseases
Human vision is more sensitive to colour than Gray levels. Therefore, colour image processing is important, although it requires more memory to store and longer execution times to process. There are different colour models, and each one is suitable for some application. In the RGB model, a colour image is expressed in terms of the intensities of its red, green, and blue components. In the HSI model, the intensity component is separated from the colour components.
The data scientists at big mart have collected sales data of 2013 for a number of products across 10 stores in different cities. In this study they have analysed the attributes of each product and store and then build a model which finds out the sale of each product at a particular store.