Ranking is a canonical problem and learning to rank as semi-supervised machine learning is a challenging issue in current interactive web era. Undoubtedly, it is easier for humans to analyze and distinguish a set of reviews. Humans can easily assure that review is good and informative review, or it is bad and uninformative. Whereas, on the other end to rank these reviews is a troublesome task even for humans. Therefore, to create a computing method that can rank reviews is handled in our proposed method. Pairwise ranking approach is applied to rank reviews in semi-supervised learning method. Pairwise ranking approach looks at a pair of documents at a time in a loss function and predicts a relative ordering. The objective is not to determine the relevance score but to find which document is more relevant than other. This relevance is developed to judge the preference of one review over another. In semi-supervised learning method, mapping is constructed between input and output. This input-output pair in training model is used to learn the system.