Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs

By Rosie Jones, Kristina Lisa Klinkner. International Conference on Information and Knowledge Management, 2008

519 citations recorded by the source corpus.

Subfields: Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/3dd3e986fda5541a039239c8b5c705b030ecc73f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Discovering and understanding word level user intent in Web search queries (2015, background): “However, session segmentation of a query stream is an active area of research [37, 38] and is beyond the scope of this work.”
Analyzing and evaluating query reformulation strategies in web search logs (2009, background): “More recently, Jones and Klinkner [21] presented evidence that any temporal cutoff is arbitrary and detects session boundaries no better than a random cutoff time.”
Understanding PubMed® user search behavior through log analysis (2009, background): “A number of notable approaches to ‘identifying’ a session have included time based clustering and semantic analysis of shifts in topics (39,40).”
Towards Large-Scale Collaborative Planning: Answering High-Level Search Queries Using Human Computation (2011, background): “Second, search queries belonging to the same intent are often issued over a span of days or weeks, and interleaved with queries belonging to other intents, making the prediction task even more difficult (Jones and Klinkner 2008).”
When Social Influence Meets Item Inference (2015, background): “The considered periods of item inference and social influence are set differently according to [14] and [28], respectively.”
Modeling the impact of short- and long-term behavior on search personalization (2012, methodology): “Note that we chose to make a session distinction since sesssions have been commonly used as a proxy to identify task boundaries [15][17].”
Understanding Short-term Changes in Online Activity Sessions (2017, background): “In different studies sessions could refer to a set of actions to satisfy a single information need [4, 11], or more commonly, a period of time that includes consecutive actions without a long break [24, 7].”
#TwitterSearch: a comparison of microblog search and web search (2011, methodology): “Researchers have also used query logs to explore how search engines are used, revealing typical session behavior [15] and the prevalence of re-finding [28].”
Online Structured Prediction via Coactive Learning (2012, methodology): “As Figure 1 shows, we find that users provide accurate preferences across this sub- 2This was done manually, but can be automated with high accuracy (Jones & Klinkner, 2008).”
The query-flow graph: model and applications (2008, methodology): “The features we use aggregate, among other, information about the time difference in which the queries are submitted [12], textual similarity of the queries [13, 15], and the number of sessions in which they appear.”
Coactive Learning (2015, methodology): “(3) In this way, Coactive Learning covers settings where the user cannot manually optimize the argmax over the full Y (e.g. produce the best possible ranking in web search), or has difficulty expressing a bandit-style cardinal rating U(xt,yt) for yt in a consistent manner.”
Identifying Web Search Query Reformulation using Concept based Matching (2013, methodology): “Other work has proposed solutions for the query reformulation prediction problem or for the similar problem of task boundary identiﬁ-cation (Radlinski and Joachims, 2005; Jones and Klinkner, 2008).”