LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Opinion mining on large scale data using sentiment analysis and k-means clustering

Photo by dawson2406 from unsplash

With the rapid growth of web technology and easy access of internet, online shopping has been increased. Now people express their opinions and share their experiences that greatly influence new… Click to show full abstract

With the rapid growth of web technology and easy access of internet, online shopping has been increased. Now people express their opinions and share their experiences that greatly influence new buyers for purchasing products, thereby generating large data sets. This large data is very helpful for analyzing customer preference, needs and its behavior toward a product. Companies face the challenge of analyzing this sheer amount of data to extract customer opinion. To address this challenge, in this paper, we performed sentiment analysis on the customer review real-world data at phrase level to find out customer preference by analyzing subjective expressions. Then we calculated the strength of sentiment word to find out the intensity of each expression and applied clustering for placing the words in various clusters based on their intensity. We also compared the results of our technique with star-ranking given on the same dataset and found the drastic change in our results. We also provide a visual representation of our results to provide a clear insight of customer preference and behavior to help decision makers for better decision making.

Keywords: customer preference; opinion; sentiment analysis; customer

Journal Title: Cluster Computing
Year Published: 2017

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.