Customer Review Analysis by Hybrid Unsupervised Learning Applying Weight on Priority Data Md. Shah Jalal Jamil 1 , Forhad An Naim 2 , Bulbul Ahamed 3 , and Mohammad Nurul Huda 4 1 United International University, Dhaka, Bangladesh mjalal162017@mscse.uiu.ac.bd 2 United International University, Dhaka, Bangladesh forhad.naim.mithun@gmail.com 3 Sonargaon University, Dhaka, Bangladesh bulbul2767@gmail.com 4 United International University, Dhaka, Bangladesh mnh@cse.uiu.ac.bd Abstract. The This paper describes a method which deals with assurance of E- commerce product quality by analyzing the customer reviews using unsuper- vised machine learning algorithms. The increasing E-commerce business in- volves people more engaging in online shopping though the assurance of the product quality is a big concern. For quality products, people now depend on the other customers’ reviews such as comments, emotions, hash tags, etc. The purpose of this study is to automatically extract the polarity of reviews in Bang- la as positive or negative sentiment conducted by customers to unleash online product quality. Here, we have tried to implement several unsupervised ma- chine learning techniques for clustering the customers’ reviews such as K- Means, Density-Based Spatial (DBSCAN), Mean Shift, Agglomerative, ensem- ble approach combined with different clustering, etc. It is observed from the experiments that the proposed method provides 98% accuracy for the experi- mental corpus by employing PWWA (Priority Word Weight Assignment) in da- ta processing stage and an ensemble clustering algorithm, K-Means and Ag- glomerative Hierarchical approach, in post processing stage. Keywords: Bangla Reviews, Unsupervised Learning, Sentiment Analysis, E- commerce, Text Mining. 1 Introduction In recent years online shopping is popularizing day by day. An estimation of 1.79 billion people buys digital goods worldwide in 2018. The forecast says the number of online buyers will increase by over 2.14 billion in 2021 [1]. But online merchant sometimes fails to maintain the quality of digital goods. As a result, E-commerce customer becomes deceived. They don’t have an option to check products before unpacking since they have been purchasing over the internet. So, they have to return