Search results

Digital objects and metadata schemes

Distributional Semantics of Tags

Preprint submitted to Information Processing & Management Tags are a convenient way to label resources on the web. An interesting question is whether one can determine the semantic meaning of tags in the absence of some predefined formal structure like a thesaurus. Many authors have used the usage data for tags to find their emergent semantics. Here, we argue that the semantics of tags can be captured by comparing the contexts in which tags appear. We give an approach to operationalizing this idea by defining what we call paradigmatic similarity: computing co-occurrence distributions of tags with tags in the same context, and comparing tags using information theoretic similarity measures of these distributions, mostly the Jensen-Shannon divergence. In experiments with three different tagged data collections we study its behavior and compare it to other distance measures. For some tasks, like terminology mapping or clustering, the paradigmatic similarity seems to give better results than similarity measures based on the co-occurrence of the documents or other resources that the tags are associated to. We argue that paradigmatic similarity, is superior to other distance measures, if agreement on topics (as opposed to style, register or language etc.), is the most important criterion, and the main differences between the tagged elements in the data set correspond to different topics

Distributional Semantics of Tags

Preprint submitted to Information Processing & Management Tags are a convenient way to label resources on the web. An interesting question is whether one can determine the semantic meaning of tags in the absence of some predefined formal structure like a thesaurus. Many authors have used the usage data for tags to find their emergent semantics. Here, we argue that the semantics of tags can be captured by comparing the contexts in which tags appear. We give an approach to operationalizing this idea by defining what we call paradigmatic similarity: computing co-occurrence distributions of tags with tags in the same context, and comparing tags using information theoretic similarity measures of these distributions, mostly the Jensen-Shannon divergence. In experiments with three different tagged data collections we study its behavior and compare it to other distance measures. For some tasks, like terminology mapping or clustering, the paradigmatic similarity seems to give better results than similarity measures based on the co-occurrence of the documents or other resources that the tags are associated to. We argue that paradigmatic similarity, is superior to other distance measures, if agreement on topics (as opposed to style, register or language etc.), is the most important criterion, and the main differences between the tagged elements in the data set correspond to different topics

Exploring and exploiting and why we always end up with the Beatles

It is argued that pop music has long been locked up in the exploitation phase. Boring, more boring and even more boring seems to be the motto, and only extreme, as now boring monotonous hip hop from Chicago / London - called drill - in which "respect" is enforced by the real killing in quarrels between rival gangs, explores the border. For the rest, contemporary pop music is exploitation, until we learn to listen differently to the many talents that remain undiminished and we grant them the adventure of musical or scientific exploration.

Exploring and exploiting and why we always end up with the Beatles

It is argued that pop music has long been locked up in the exploitation phase. Boring, more boring and even more boring seems to be the motto, and only extreme, as now boring monotonous hip hop from Chicago / London - called drill - in which "respect" is enforced by the real killing in quarrels between rival gangs, explores the border. For the rest, contemporary pop music is exploitation, until we learn to listen differently to the many talents that remain undiminished and we grant them the adventure of musical or scientific exploration.

Rationality and indifference

Patients with damage in certain parts of the prefrontal cortex resemble Buridan’s Donkey, as this statement has been called. Both emotion, and free will to act are missing, while rationality is intact. Emotion seems to be the fuel for action, much more needed for survival than rationality, which, as we  ave seen, is also extremely fallible (attribution error and we also see causality where it is not).