Xavier Ochoa

TL;DR: A set of scalable quality metrics for metadata based on the Bruce & Hillman framework for metadata quality control is presented and it is found that several metrics, especially Text Information Content, correlate well with human evaluation and that the average of all the metrics are roughly as effective as people to flag low-quality instances.

TL;DR: In this article, the authors conducted a detailed quantitative study of the publication process of learning objects in repositories and found that the amount of learning object is distributed among repositories according to a power law and the repositories mostly grow linearly.

TL;DR: Results indicate that LADA enables expert advisers to evaluate significantly more scenarios, especially for high advising difficulty cases with students that failed many courses, in a not-significantly different amount of time.

TL;DR: An exploratory evaluation of the metrics shows that even the simplest ones provide statistically significant improvement in the ranking order over the most common algorithmic relevance metric.