Result Diversification in Event-Based Social Networks

Result diversification is an important aspect in query events, web-based search, facility location and other applications. To satisfy more users in event-based social networks (EBSNs), search result diversification in an event that covers as many user intents as possible. Most existing result diversification algorithms recognize an user may search for information by issuing the different query as much as possible. In this paper, we leverage many different users in a same event such that satisfy the maximum benefit of users, where users want to participate in an event that s/he did not know any users, for example, blind date, Greek and other activities. To solve this problem, we devise an effective greedy heuristic method and integrate simulated annealing techniques to optimize the algorithm performance. In particular, the Greedy algorithm is more effective but less efficient than Integrate Simulated Annealing in most cases. Finally, we conduct extensive experiments on real and synthetic datasets which verify the efficiency and effectiveness of our proposed algorithms.