An Academic Social Network Friend Recommendation Algorithm Based on Decision Tree

With the rapid development of smart city services, social network plays a greater role in extensive areas with smart technology. How to use the smart technology to recommend friends from many users accurately and availably has been a research focus in the field of social recommendation. A friend recommendation algorithm based on Decision Tree with the background of the SCHOLAT, a large online academic social network site. The proposed algorithm translates the problem of friend recommendation into a prediction of binary-class. Firstly, the feature selection method, which the Relief and K-means algorithm are mainly applied, is used to remove the irrelevant and redundant features in the data preprocessing. After obtaining the effective features, we use a learning model to train the selected data. The Decision Tree method is introduced as a base classifier to predict the class of candidate user(recommendation or not recommendation). Secondly, combined with the AdaBoost enhanced algorithm, the results of Decision Tree classifier are weighted to adjusted for a better accurate result, which ultimately forms recommendation lists for the target users. Finally, the experimental results on the SCHOLAT for friend recommendation show that the effectiveness and practicability of the proposed algorithm.