A Survey on Mining Top-k Competitors from Large Unstructured Dataset Using k_means Clustering Algorithm and Sentiment Analysis Approach

Abstract

Along line of research has shown the vital significance of recognizing and observing company�s contestants. In the framework of this activity various questions are emerge like: In what way we formalize and measure the competitiveness between two items? Who are the most important competitors of a specified item? What are the various features of an item that act on competitiveness? Inspired by this issue, the advertising and administration group have concentrated on observational strategies for competitor distinguishing proof and in addition on techniques for examining known contenders. Surviving examination on the previous has concentrated on mining near articulations (e.g.one product is superior then other product) from the web or other documentary sources. Despite the fact that such articulations can without a doubt be indications of strength, they are truant in numerous spaces. By surveying the various papers, we found the conclusion of basic significance of the competitiveness between two items on the basis of market segments.