Overcoming the Imbalance Between Tag Recommendation Approaches and Real-World Folksonomy Structures with Cognitive-Inspired Algorithms
This work addresses a domain-specific problem for social tagging systems, offering an incremental improvement by adapting algorithms to sparse folksonomies.
The paper tackles the imbalance between tag recommendation algorithms designed for dense folksonomies and the sparse structures of real-world social tagging systems, showing that cognitive-inspired algorithms based on the ACT-R architecture can help address this issue.
In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).