EAGER: Modeling and Visualization of Latent Communities

点击翻译按钮获取中文摘要

In many areas of human professional and social life, people tend to form more or less clearly defined communities. The main problem of these hidden or latent communities is that they are really hard to discover since the borders of these communities cut through various professional and organizational borders. The modern social Web, however, provides a huge volume of alternative data sources for discovering latent communities. The goal of this proposal is to explore a range of promising approaches that can be used to elicit latent communities from various kinds of data about individuals available in the modern social Web and deliver the results for human thinking and interactive exploration through interactive visualizations. The visualization provided will allow humans explore and manipulate the results delivered by the new algorithms. This will deliver results that are produced by the joint power of human and artificial intelligence. In the course of the project, the team will build several data sets combining data of several social Web systems and use these data sets to develop, evaluate, and compare several elicitation and visualization approaches. The work will advance the research on latent communities, community and user modeling, and interactive social visualization. At the same time, the work will constitute one of the first attempts to use a variety of social Web data and a variety of approaches for community modeling. To increase the broader impact of the project, the researcher will apply the latent community knowledge to several practical tasks, such as identifying proper academic mentors and forming coherent collaboration groups. They will also engage a number of students in the research advancing their training into this emerging field.