With the ever-growing volume of online information, recommender systems have been an effective strategy to overcome such information overload. The utility of recommender systems cannot be overstated, given its widespread adoption in many web applications, along with its potential impact to ameliorate many problems related to over-choice. Nowadays, people from all around the world use social media sites to share information. Twitter, for example, is a social network in which users send, read posts known as ‘tweets’ and interact with different communities. Users share their daily lives, post their opinions on everything such as brands and places. Social influence plays an important role in product marketing. However, it has rarely been considered in traditional recommender systems. In this paper, we present a new paradigm of e-commerce recommender systems, which can utilize information in social networks. In this study, we have combined sentiment analysis of twitter data with the collaborative filtering in order to increase system accuracy. The proposed system uses lexical approach to analyze sentiment. In order to design the recommender system, we have replaced the missing values of the ratings matrix with the averages of the ratings assigned to the items, to solve the sparsity and cold-start problems inherent in collaborative filtering. The results show that our proposed method improves CF performance. In this experiment we demonstrate how relevant social media can be for recommender systems.