Recommender System Based On Extracted Data From Different Social Media. A Study Of Twitter And Linkedin

The number of social media users and the amount of available digital information on them is growing exponentially. This explosive rise in the accessible data on social media may cause confusion for users and leads to unpleasant experience since the overwhelming number of various choices makes finding the items of interest too difficult. As an effective solution, recommender systems are used to predict user's responses to existing options. Each social media site attempts to develop recommending algorithms as efficiently as possible based on the users' contributions. In addition, many studies have investigated various recommending and predicting approaches for a specific application. However, considering the relationships between different data provided by people on different social media sites and using them to produce new recommender systems were the subject of only a few studies. To fill this gap, the objective of this study is developing recommender systems which are connecting two social media together. We collected data from Twitter and LinkedIn accounts of some computer scientists and developed new recommender systems: a collaborative, a content-based and two hybrids, which relate computer scientists' skills, declared on their LinkedIn profile, to their Twitter's followings. Using this data, we can generate useful recommendations not possible within just one social site. We recommend new Twitter accounts to computer scientists based on their skills and interests; and also predict their skills based on the accounts they are following on Twitter. The precision and usefulness of these recommender and predicator algorithms are investigated using a real dataset of Twitter and LinkedIn profiles; then their performances are compared to each other in terms of accuracy and time consumption.