Enhancing personalized search by mining and modeling task behavior

Abstract

Personalized search systems tailor search results to the current user intent using historic search interactions. This relies on being able to find pertinent information in that user's search history, which can be challenging for unseen queries and for new search scenarios. Building richer models of users' current and historic search tasks can help improve the likelihood of finding relevant content and enhance the relevance and coverage of personalization methods. The task-based approach can be applied to the current user's search history, or as we focus on here, all users' search histories as so-called "groupization" (a variant of personalization whereby other users' profiles can be used to personalize the search experience). We describe a method whereby we mine historic search-engine logs to find other users performing similar tasks to the current user and leverage their on-task behavior to identify Web pages to promote in the current ranking. We investigate the effectiveness of this approach versus query-based matching and finding related historic activity from the current user (i.e., group versus individual). As part of our studies we also explore the use of the on-task behavior of particular user cohorts, such as people who are expert in the topic currently being searched, rather than all other users. Our approach yields promising gains in retrieval performance, and has direct implications for improving personalization in search systems.

Temporal Latent Topic User Profiles for Search Personalisation

“…The user interests could be long-term [6,8,14,16] or short-term [18,19]. Longterm interests, in the context of IR systems, are stable interests that can be exhibited for a long time in the user's search history.…”

“…As one of the key components in advanced search engines (e.g., Google and Bing), Search Personalisation has attracted increasing attention [1,9,12,15,16,19]. The personalisation is expected to improve the usefulness of search algorithms.…”

“…Normally, one of the most common approaches is to represent the profile with the main topics discussed in documents which the user has previously clicked on [1,8,11,16,19]. The topics of a document are often obtained from a humangenerated online ontology, such as the Open Directory Project (ODP) [1,11,19].…”

“…The topics of a document are often obtained from a humangenerated online ontology, such as the Open Directory Project (ODP) [1,11,19]. This approach has a limitation that many topics may not appear in the ontology.…”

“…We note that the three profiles represent the user interest in different time scales (from short-term to long-term). In order to extract topics from the relevant documents, we employ the same approach proposed in [16] that utilises a topic modelling method (i.e., LDA [2]) to automatically derive latent topics instead of using a human-generated ontology as in [1,11,19].…”