In recent years, the volume of data submissions (E-Commerce data) in online on products, service, and organizations is increasing exponentially. This online data is abundantly unstructured; extracting knowledge from that huge volume of data is a non-trivial task. In recent years, extracting product names become a very popular approach and also one of the important methods in sentiment analysis. This product name extraction is very useful in E-commerce, because it helps in identifying people interest on products, generation of reviews' metadata and identification of product attributes, etc. The existing approaches in product name extraction are capable of extracting single word product names. However, the product names can be a sequence of words, which is also called multi-word product names that cannot be obtained automatically by the existing methods. In this paper, a combined approach of semi-supervised machine learning and improved C-value approach is proposed to discover the multi-word product names, ranking those product names and identifying a dominant product in review documents.