Can We Group Similar Amazon Reviews: A Case Study with Different Clustering Algorithms

The amount of unstructured text data available is growing exponentially due to the proliferation of digital information such as emails, text messages, blogs, social media posts, and product reviews. For users of e-commerce websites such as Amazon, navigating thousands of reviews before buying a product can be a daunting task. Unsupervised machine learning techniques can be used to automatically analyze preprocessed data from these websites in order to provide consumers with an improved user experience before purchasing a product. In this work, we leverage two flat clustering algorithms on Amazon review data: K-means and Peak-searching to perform clustering of product reviews based on topic. The experimental results show that K-means clustering performs better than Peak-searching clustering in terms of grouping similar reviews based on topics.