Finding people, papers, and posts: Vertical search algorithms and evaluation

There is a growing diversity of information access applications. While general web search has been dominant in the past few decades, a wide variety of so-called vertical search tasks and applications have come to the fore. Vertical search is an often used term for search that targets specific content. Examples include YouTube video search, Facebook graph search, Spotify music recommendation, product search, expertise retrieval, and scientific literature search.
In a vertical search application, typically, some background knowledge is available about the context in which search is taking place. We may know something about the user population, about the tasks they wish to perform, about their information needs, and about the information objects in the collection we make available to them. This knowledge can inform adaptation of retrieval algorithms and evaluation methodology, to provide a better ranking of information objects, or to organize search results more effectively.
This dissertation showcases the need, as well as many opportunities, to leverage background knowledge in three vertical search scenarios: finding people, finding scientific papers, and finding microblog posts. Its five research chapters provide pointers on how background knowledge may be used to help understand user information needs, organize search results, evaluate retrieval algorithms, and automatically generate ground truth.