Online product reviews have greater impact on influence both product sales through consumer decision making and quality enhancement using business firms. Due to the advanced growth in the Internet usage in day to day lifetime and e-shopping, the quantity of product reviewers are exponentially increased. The massive amount of continuously generating data is treated as a major issue for business people and end user. A study reported that almost 87% of consumers make decisions of buying a product after reading a minimum of 10 reviews. Online product reviews are a kind of structure less data containing both positive and negative influences over customers. Hence, it is essential to validate the quality of the product reviews and undergo proper classification as either positive or negative. By keeping this intention, this paper aims to develop an efficient classification model for online product reviews using Gradient Tree Boosting (GTB) classifier. The proposed classification model is tested using a benchmark dataset from Twitter. Based on the experimental results, it is evident that the GTB based classification model exhibit superior results over the existing model interms of various measures such as accuracy, sensitivity, specificity, F-score and kappa value.