Entity Extraction or product name extraction is a suitable premise for sentiment analysis. A sentiment discovers opinion of the customers on the product stated in the sentence. Extracting product names using the existing approaches from the customer’s reviews are not exact most of the time. Almost many existing approaches mainly lack in addressing the product name having multiple words or sequence of words (multi-word). When compared with single word named products, extracting opinion on multi-word named products are non-trivial task as customer use either full name or part of the product name (sub-word) in product reviews. Therefore, it is the foremost challenging task in sentiment analysis to recognize appropriate complete name of a specific product using the sub-word names. Secondly, the multi-word named products or sub-word named products may occur anywhere in the review sentences, the position of the product names cannot be predicted in advance. It may occur in the beginning, middle or at the end and also with any number of times. So, identifying the position of these product names is another key issue. Therefore, this research attempt to design a novel automated improved Context Information Weight (iCIW) approach to resolve the exiting issues. The iCIW assimilates the concept of lexicon and statistical approach. The proposed iCIW model is more suitable for document analysis related to medical reports, product details repository and political documents. The experimental result reveals that the proposed method performs very efficient than existing approaches in multi-word named product extraction. © School of Engineering, Taylor’s University.