@article {5288, title = {Spherical microaggregation: Anonymizing sparse vector spaces}, journal = {Computers \& Security}, volume = {49}, year = {2015}, pages = {17}, publisher = {Elsevier}, chapter = {28}, abstract = {Abstract Unstructured texts are a very popular data type and still widely unexplored in the privacy preserving data mining field. We consider the problem of providing public information about a set of confidential documents. To that end we have developed a method to protect a Vector Space Model (VSM), to make it public even if the documents it represents are private. This method is inspired by microaggregation, a popular protection method from statistical disclosure control, and adapted to work with sparse and high dimensional data sets.}, keywords = {anonymization, data mining, sparse data, vector space}, url = {http://www.sciencedirect.com/science/article/pii/S0167404814001679}, author = {Daniel Abril and Guillermo Navarro-Arribas and Vicen{\c c} Torra} }