Integrating a weighted-average method into the random walk framework to generate individual friend recommendations

Friend recommendation is a fundamental service in both social networks and practical applications, and is influenced by user behaviors such as interactions, interests, and activities. In this study, we first conduct in-depth investigations on factors that affect recommendation results. Next, we design Friend＋＋, a hybrid multi-individual recommendation model that integrates a weighted average method （WAM） into the random walk （RW） framework by seamlessly employing social ties, behavior context, and personal information. In Friend＋＋, the first plus signifies recommending a new friend through network features, while the second plus stands for using node features. To verify our method, we conduct experiments on three social datasets crawled from the Sina microblog system （Weibo）. Experimental results show that the proposed method significantly outperforms six baseline methods in terms of recall, precision, Fl-measure, and MAP. As a final step, we describe a case study that demonstrates the scalability and universality of our method. Through discussion, we reach a meaningful conclusion： although common interests are more important than user activities in making recommendations, user interactions may be the most important factor in finding the most appropriate potential friends.