Click Models for Web Search

Abstract

Synthesis Lectures on Information Concepts, Retrieval, and Services publishes short books on topics pertaining to information science and applications of technology to information discovery, production, distribution, and management. Potential topics include: data models, indexing theory and algorithms, classification, information architecture, information economics, privacy and identity, scholarly communication, bibliometrics and webometrics, personal information management, human information behavior, digital libraries, archives and preservation, cultural informatics, information retrieval evaluation, data fusion, relevance feedback, recommendation systems, question answering, natural language processing for retrieval, text summarization, multimedia retrieval, multilingual retrieval, and exploratory search. ABSTRACTWith the rapid growth of web search in recent years the problem of modeling its users has started to attract more and more attention of the information retrieval community. is has several motivations. By building a model of user behavior we are essentially developing a better understanding of a user, which ultimately helps us to deliver a better search experience. A model of user behavior can also be used as a predictive device for non-observed items such as document relevance, which makes it useful for improving search result ranking. Finally, in many situations experimenting with real users is just infeasible and hence user simulations based on accurate models play an essential role in understanding the implications of algorithmic changes to search engine results or presentation changes to the search engine result page.In this survey we summarize advances in modeling user click behavior on a web search engine result page. We present simple click models as well as more complex models aimed at capturing non-trivial user behavior patterns on modern search engine result pages. We discuss how these models compare to each other, what challenges they have, and what ways there are to address these challenges. We also study the problem of evaluating click models and discuss the main applications of click models.

A Neural Click Model for Web Search

“…Recently, many models have been proposed to explain or predict user behavior in web search; see [10] for an overview. These models, also called click models as the main observed user interaction with a search system concerns clicks, are used for click prediction and they may help in cases where we do not have real users to experiment with, or prefer not to experiment with real users for fear of hurting the user experience.…”

A Context-aware Time Model for Web Search

“…Existing work shows that the position of a result influences users' trust in the result's usefulness, which affects their decisions whether to click or not [13]. We allow for …”

“…Unfortunately, CTRs suffer from the so-called position bias effect, i.e., results presented at higher positions receive more clicks than results of similar quality presented at lower positions [15,27,28], which leads to suboptimal performance when using CTRs for ranking. To account for position bias, a large number of click models have been proposed [13].…”

“…Recently, many models have been proposed to explain and predict user clicks on search engine results [13]. While click events are the most widely logged form of user interaction, there are also other behavioral signals that need to be understood, interpreted and modeled, and that can be used for ranking or prediction purposes.…”

Context & Semantics in News & Web Search

“…Recently proposed metrics put more emphasis on how a user interacts with the search results, for example by modeling clicks from historical results [48]. One of the most important issues that these metrics address is the so-called position bias [110], i.e., users are more likely to inspect results higher in the ranked list.…”