In scientific research, it is often difficult to express information needs as simple keyword queries. We present a more natural way of searching for relevant scientific literature. Rather than a string of keywords, we define a query as a small set of papers deemed relevant to the research task at hand. By optimizing an objective function based on a fine-grained notion of influence between documents, our approach efficiently selects a set of highly relevant articles. Moreover, as scientists trust some authors more than others, results are personalized to individual preferences. In a user study, researchers found the papers recommended by our method to be more useful, trustworthy and diverse than those selected by popular alternatives, such as Google Scholar and a state-of-the-art topic modeling approach.

35 pages