一种融合相似网络的多主题域混合推荐算法

Multi topic domain hybrid recommendation algorithm fusing similarity network

针对基于社会化标签的推荐算法中面临的标签质量和数据稀疏性问题,提出了一种融合相似网络的多主题域混合推荐算法。通过划分主题域,将表达不同主题含义的资源及标签分开以解决标签多义性问题;通过建立标签的相似网络找到标签的同义词,然后利用这些同义词扩展用户和资源的标签偏好以解决标签同义词的问题和数据稀疏性的问题。最后结合用户自身的偏好信息和其相似邻居的偏好信息产生推荐。实验结果表明,该方法具有较好的效果。

For the issues of tag quality and data sparsity in tag-based recommendation algorithm,this paper proposed a multi topic domain hybrid recommendation algorithm fusing similarity network. First it separated resources and tags to different topic domains to solve the ambiguity problem of tags. Then it established similarity network to find the synonymous words of target tags,and used the synonymous words to extend users＇ and resources＇ interest. At last it combined the target user＇s own preference information and his neighbours＇ preference information to generate recommendation. Experimental results show that the approach has a better recommendation results.