Modeling Optimal Switching Behavior

Smucker, Mark D.; Clarke, Charles L. A.

doi:10.1145/2854946.2854981

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By estimating the expected benet for each state, they were able to tell the user at which rank it is better to formulate a query (instead of going further down the result list). Similar to this, Smucker and Clarke [13] modelled the switching behaviour of users engaging with ranked lists which provide dierent levels of gain and show at what point it is optimal to 'switch'.…”

Section: Related Workmentioning

confidence: 92%

Personalised Search Time Prediction using Markov Chains

Tran

Maxwell

Fuhr

et al. 2017

Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval

View full text Add to dashboard Cite

For improving the eectiveness of Interactive Information Retrieval (IIR), a system should minimise the search time by guiding the user appropriately. As a prerequisite, in any search situation, the system must be able to estimate the time the user will need for nding the next relevant document. In this paper, we show how Markov models derived from search logs can be used for predicting search times, and describe a method for evaluating these predictions. For personalising the predictions based upon a few user events observed, we devise appropriate parameter estimation methods. Our experimental results show that by observing users for only 100 seconds, the personalised predictions are already signicantly better than global predictions.

show abstract

Section: Related Workmentioning

confidence: 92%

Personalised Search Time Prediction using Markov Chains

Tran

Maxwell

Fuhr

et al. 2017

Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval

View full text Add to dashboard Cite

show abstract

“…By considering the SERP as a whole, this provides a way to model abandonment within the search process, rather than assuming that a searcher will assess the first snippet specifically. This therefore marks a departure from assumptions encoded within many Information Retrieval (IR) models and measures, such as P @k, RBP [24], and INST [1,23,31]. The motivation for including this additional decision point stems from empirical research (i.e.…”

Section: Updating the Complex Searcher Modelmentioning

confidence: 99%

Information Scent, Searching and Stopping

Maxwell

Azzopardi

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Current models and measures of the Interactive Information Retrieval (IIR) process typically assume that a searcher will always examine the first snippet in a given Search Engine Results Page (SERP), and then with some probability or cutoff, he or she will stop examining snippets and/or documents in the ranked list (snippet level stopping). Prior work has however shown that searchers will form an initial impression of the SERP, and will often abandon a page without clicking on or inspecting in detail any snippets or documents. That is, the information scent affects their decision to continue. In this work, we examine whether considering the information scent of a page leads to better predictions of stopping behaviour. In a simulated analysis, grounded with data from a prior user study, we show that introducing a SERP level stopping strategy can improve the performance attained by simulated users, resulting in an increase in gain across most snippet level stopping strategies. When compared to actual search and stopping behaviour, incorporating SERP level stopping offers a closer approximation than without. These findings show that models and measures that naïvely assume snippets and documents in a ranked list are actually examined in detail are less accurate, and that modelling SERP level stopping is required to create more realistic models of the search process.

show abstract

“…[16,32] • should a user examine many documents and issue few queries, or vice versa? [2,4] In describing the different models, we will explore and explain how different parameters affect the decisions at play.…”

Section: Introduction and The Economics Of Searchmentioning

confidence: 99%

Building Cost-Benefit Models of Information Interactions

Azzopardi

2017

Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval

View full text Add to dashboard Cite

Modeling how people interact with search interfaces has been of particular interest and importance to the field of Interactive Information Retrieval. Recently, there has been a move to developing formal models of the interaction between the user and the system, whether it be to: (i) run a simulation, (ii) conduct an economic analysis, (iii) measure system performance, or (iv) simply to better understand the interactions and hypothesise about user behaviours. In such models, they consider the costs and the benefits that arise through the interaction with the interface/system and the information surfaced during the course of interaction. In this full day tutorial, we will focus on describing a series of cost (and benefit) models that have been proposed in the literature and how they have been applied in various scenarios. The tutorial will be structured into two parts. First, we will provide an overview of Decision Theory and Cost-Benefit Analysis techniques, and how they can and have be applied to a variety of Interactive Information Retrieval scenarios. For example, how do we reduce the cost browsing facets? how many results should we show per page? and how do we get users to pose longer queries? The second part of the day will be dedicated to building cost models where we will discuss different techniques to build and develop models from which one can draw testable hypotheses from. In this more practical session, we will also discuss how costs and benefits can be estimated, and how the models can help inform and guide experimentation. During the tutorial participants will be challenged to build cost models for a number of problems (or even bring their own problems to solve). We will then conclude with presentations of solutions followed by a summary and overview of challenges and future directions. This tutorial is aimed at participants wanting to know more about cost models and how they can be applied, interpreted and built in the context of information seeking, search and retrieval.

show abstract

Modeling Optimal Switching Behavior

Cited by 7 publications

References 15 publications

Personalised Search Time Prediction using Markov Chains

Personalised Search Time Prediction using Markov Chains

Information Scent, Searching and Stopping

Building Cost-Benefit Models of Information Interactions

Contact Info

Product

Resources

About