Bringing the Associative Ability to Social Tag Recommendation

摘要

Social tagging systems, which allow users to freely annotate online resources with tags, become popular in the Web 2.0 era. In order to ease the annotation process, research on social tag recommendation has drawn much attention in recent years. Modeling the social tagging behavior could better reflect the nature of this issue and improve the result of recommendation. In this paper, we proposed a novel approach for bringing the associative ability to model the social tagging behavior and then to enhance the performance of automatic tag recommendation. To simulate human tagging process, our approach ranks the candidate tags on a weighted digraph built by the semantic relationships among meaningful words in the summary and the corresponding tags for a given resource. The semantic relationships are learnt via a word alignment model in statistical machine translation on large datasets. Experiments on real world datasets demonstrate that our method is effective, robust and language-independent compared with the state-of-the-art methods.