The Internet is the largest source of information in the world. Search engines help people navigate the huge space of avail-able data in order to acquire new skills and knowledge. In this paper, we present an in-depth analysis of sessions in which people explicitly search for new knowledge on the Web based on the log files of a popular search engine. We investi-gate within-session and cross-session developments of exper-tise, focusing on how the language and search behavior of a user on a topic evolves over time. In this way, we identify those sessions and page visits that appear to significantly boost the learning process. Our experiments demonstrate a strong connection between clicks and several metrics re-lated to expertise. Based on models of the user and their specific context, we present a method capable of automati-cally predicting, with good accuracy, which clicks will lead to enhanced learning. Our findings provide insight into how search engines might better help users learn as they search.

Queries issued to a search engine are often under-specified or am-biguous. The user’s search context or background may provide information that disambiguates their information need in order to automatically predict and issue a more effective query. The disam-biguation can take place at different stages of the retrieval process. For instance, contextual query suggestions may be computed and recommended to users on the result page when appropriate, an ap-proach that does not require modifying the original query’s results. Alternatively, the search engine can attempt to provide efficient ac-cess to new relevant documents by injecting these documents di-rectly into search results based on the user’s context. In this paper, we explore these complementary approaches and how they might be combined. We first develop a general frame-work for mining context-sensitive query reformulations for query suggestion. We evaluate our context-sensitive suggestions against a state-of-the-art baseline using a click-based metric. The resulting query suggestions generated by our approach outperform the base-line by 13 % overall and by 16 % on an ambiguous query subset. While the query suggestions generated by our approach have higher quality than the existing baselines, we demonstrate that us-ing them naïvely for injecting new documents into search results can lead to inferior rankings. To remedy this issue, we develop a classifier that decides when to inject new search results using features based on suggestion quality and user context. We show that our context-sensitive result fusion approach (Corfu) improves retrieval quality for ambiguous queries by up to 2.92%. Our ap-proaches can efficiently scale to massive search logs, enabling a data-driven strategy that benefits from observing how users issue and reformulate queries in different contexts. 1.

The development of mobile technology and wearable activity monitors, making it possible for people to retrieve data about their daily activities, is presenting aspects of information seeking behaviour not covered well by previous research. The main objective of this paper is to consider how the new information seeking contexts evident in the use of self-tracking extend current understandings of the way people need, seek, share and use information. This paper reviews current trends in information retrieval system design, interactive information retrieval, and human information behaviour research as the foundation for a discussion about the way that new trends in information seeking contexts and human information behaviour can inform research. 1