Social bookmarking systems allow users to organise collections of resources on the Web in a collaborative fashion. The increasing popularity of these systems as well as first insights into their emergent semantics have made them relevant to disciplines like knowledge extraction and ontology learning. The problem of devising methods to measure the semantic relatedness between tags and characterizing it semantically is still largely open. Here we analyze three measures of tag relatedness: tag co-occurrence, cosine similarity of co-occurrence distributions, and FolkRank, an adaptation of the PageRank algorithm to folksonomies. Each measure is computed on tags from a large-scale dataset crawled from the social bookmarking system del.icio.us. To provide a semantic grounding of our findings, a connection to WordNet (a semantic lexicon for the English language) is established by mapping tags into synonym sets of WordNet, and applying there well-known metrics of semantic similarity. Our results clearly expose different characteristics of the selected measures of relatedness, making them applicable to different subtasks of knowledge extraction such as synonym detection or discovery of concept hierarchies.

Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender.

In Fig. 1 we show the number of registrations to Statphys 23 (full dots). Each point corresponds to one day and the deadline $T^*$=March 31 was the one corresponding to the early registration and abstract submission. We also plot the data corresponding to the a different conference (EP2DS 17) for which we have rescaled the total number of registration at its own $T^*$. The data of the two conferences are remarkably similar and are characterized by an initial linear behavior followed by a strong increase near $T^*$. This strong similarity suggests for a simple mechanism to describe the response of the people to a deadline and we propose have a simple model. The basic idea is that the pressure you have to register is proportional to the inverse of the remaining time to the deadline. This gives a probability, $p(t)$, to register at time $t$ that is $p(t)proptofrac1(T^*-t)$. From this the number of the registrations at time $t$ is: $$ N(t)=C0^T^*p(t)dt=A(N_tot)T^*T^*-t). nonumber$$ The logarithmic singularity at the end is regularized by discretizing the integral with an interval of one day and the constant $A(N_tot)$ is fixed by the total number of final registration $N_tot$. As one can see in Fig. 1 this simple model fits the observed behavior extremely well. This permits to predict the total number of registrations already from the initial slope. A result that could have some practical interest. The model only assumes that the probability to register is the same for the whole interval of the the remaining time. In this respect there is no real tendency to shift the registration towards the deadline. The increase of pressure is just due to the approaching of the deadline. This situation may appear curious because one could have expected a stronger pressure to postpone the payment towards the deadline. In this respect, however, one should notice that the data in Fig. 1 refer only to the registration and not to the payment of the fee which could have been done also at a late time.