位置社交网络中区域多样性增强推荐算法

A Region Diversity Enhancement Recommendation Algorithm Based on Location-based Social Networks

针对基于协同过滤算法的top-N推荐列表中往往能够获得离用户较近且感兴趣的地点,但这些地点所属区域比较单一,提供的服务功能类似,甚至出现推荐列表中所有地点属于同一区域,无法增强用户体检的问题,提出了一种新的推荐方法,在保证推荐列表准确率的前提下,通过调节区域的权重来提高推荐地点的多样性.实验证明,该方法不仅具有较低的时间复杂度和高度的可扩展性,而且与其他方法相比能够获得更好的推荐效果.

The existing location recommendation top-N based on the collaborative filtering algorithm can obtain what the users are interested in,but when users are far away from their residence,the recommend effect falls sharply; the main reason is that recommended spots are closer to their permanent residence,which results in regional single and lack of diversity.In this study,we propose a novel method which can adjust the weight of location clusters to enhance the diversity levels of their own recommendation lists with little decrease in accuracy.Experiments show that this methods has a very low computational time complexity and highly scalable,and outperforms other methods.