A Collaborative Recommend Algorithm Based on Bipartite Community
Figure 6
Results of different algorithms under some typical list lengths. (a), (b), (c), and (d) report the ranking accuracy, hitting rate, popularity, and diversity, respectively. The illustrations of RCBCR and UCBCR show the mean of all metrics UCBCR and RCBCR algorithms based on communities in Figure 4. And the illustrations of RCBCR (U) and UCBCR (U) show those results based on communities in Figure 5.