Long time no see: the probability of reusing tags as a function of frequency and recency

In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory. This approach uses the frequency and recency of previous tag assignments to estimate the probability of reusing a particular tag. Using three real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike and Flickr, we show how incorporating a time-dependent component outperforms conventional "most popular tags" approaches and another existing and very effective but less theory-driven, time-dependent recommendation mechanism. By combining our approach with a simple resource-specific frequency analysis, our algorithm outperforms other well-established algorithms, such as FolkRank, Pairwise Interaction Tensor Factorization and Collaborative Filtering. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. We demonstrate how effective principles of information retrieval can be designed and implemented if human memory processes are taken into account.