Updis: A User-Assisted Projection Technique For Distance Information

Multidimensional projection techniques have become essential analytical tools. Typically, they map data from a high-dimensional space into a low-dimensional visual space, preserving distance or neighborhood structures on the produced layout. Despite the advances, with faster and highly precise techniques, existing methods still carry deficiencies that impair their use as exploratory tools. An example is the mismatching that can occur between what the user considers similar/dissimilar and what is conveyed by the visual representation. Recently, a class of projection techniques aims at addressing this limitation, allowing users to control the projection process by changing the distance relationships using small data samples. Among such methods, Local Affine Multidimensional Projection has proved to be the state-of-the-art regarding the effectiveness of user intervention. Although Local Affine Multidimensional Projection has attained a relative success, it is limited to certain application domains. Since it relies on feature vector representations with data instances described by vectors embedded into a Euclidean space, scenarios that offer only distance information or a distance function cannot be handled. In this article, we present a novel multidimensional projection technique, called User-assisted Projection Technique for Distance Information, which takes advantage of the solid mathematical framework provided by Local Affine Multidimensional Projection, adapting it to scenarios where only distance information or a distance function is available. The results show that User-assisted Projection Technique for Distance Information is as fast, accurate, robust, and flexible as the existing state-of-the-art techniques, enabling the application of the refined user control provided by Local Affine Multidimensional Projection on domains not previously covered. Its versatility is illustrated in an application that involves the organization of book collections that employs an external source of information for the recommendation of new readings.