Online customer reviews have become electronic word of mouth for the current generations. The product reviews play an important role in customer‘s purchase decision making process. However, there are thousands of reviews constantly being posted for online products on e-commerce websites. It is very difficult for buyers to read all the reviews before purchase decisions. Review helpfulness is attracting increasing attention of practitioners and academics. It helps in reducing risks and uncertainty faced by users in online shopping. In this dissertation, three solutions are proposed to develop an effective model for review helpfulness prediction. i.e. 1) Influences of discrete emotions embedded in review text on review helpfulness are investigated, 2) Review helpfulness as a function of linguistic, psychological, summary language, and reviewer features is examined, and 3) Significant product, review and reviewer characteristics are explored to determine the review helpfulness. For discrete emotions, an algorithm is presented that extracts four positive and four negative discrete emotions from review text using National Research Council (NRC) emotion lexicon. An effective helpfulness prediction model is build using deep neural network. The findings reveal that Trust, Joy and Anticipation (positive emotions); Anxiety and Sadness (negative emotions) are most influential emotion dimensions and have greater impact on perceived helpfulness. Secondly, the utility of linguistic, psychological, summary language and reviewer characteristics are investigated and an effective review helpfulness prediction model is constructed using stochastic gradient boosting algorithm. The results reveal that reviewer helpfulness per day and syllables in review text strongly relates to review helpfulness. Moreover, the number of space, aux verb, drives words in review text and productivity score of a reviewer are also effective predictors of review helpfulness. Thirdly, influences of important variables by exploring not only the review content indicators but also significant indicators of reviewer and product that contribute to review helpfulness are explored. The influence of product type (search and experience goods) on review helpfulness is also examined and reviews of search goods show strong relationship to review helpfulness. The findings indicate that polarity of review title, sentiment and polarity of review text and cosine similarity between review text and product title effectively contribute to the helpfulness of online reviews.