Actions Speak Louder than Words: Analyzing large-scale query logs to improve the research experience

Analyzing anonymized query and click-through logs leads to a better understanding of user behaviors and intentions, and provides opportunities to create an improved search experience. As a large-scale provider of SaaS services that returns search results against a single unified index, Serials Solutions is uniquely positioned to learn from the dataset of queries issued to its Summon® service by millions of users at hundreds of libraries around the world. In this paper, we describe the Relevance Metrics Framework that we use to analyze our query logs and provide examples of insights we have gained during development and implementation. We also highlight the ways our analysis is inspiring changes to the Summon® service to improve the academic research experience.