Assessing and predicting vertical intent for web queries

Ke Zhou, Ronan Cummins, Martin Halvey, Mounia Lalmas, Joemon M. Jose

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

8 Citations (Scopus)

Abstract

Aggregating search results from a variety of heterogeneous sources, i.e. so-called verticals [1], such as news, image, video and blog, into a single interface has become a popular paradigm in web search. In this paper, we present the results of a user study that collected more than 1,500 assessments of vertical intent over 320 web topics. Firstly, we show that users prefer diverse vertical content for many queries and that the level of inter-assessor agreement for the task is fair [2]. Secondly, we propose a methodology to predict the vertical intent of a query using a search engine log by exploiting click-through data, and show that it outperforms traditional approaches.
Original languageEnglish
Title of host publicationAdvances in Information Retrieval
Subtitle of host publication34th European Conference on IR Research
EditorsRicardo Baeza-Yates, Arjen P. de Vries, Hugo Zaragoza, B. Barla Cambazoglu, Vanessa Murdock, Ronny Lempel, Fabrizio Silvestri
Place of PublicationHeidelberg
PublisherSpringer
Pages499-502
Number of pages4
ISBN (Print)9783642289965
DOIs
Publication statusPublished - 27 Mar 2012
Externally publishedYes
Event34th European conference on Advances in Information Retrieval - Barcelona, Spain
Duration: 1 Apr 20125 Apr 2012

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume7724
ISSN (Print)0302-9743

Conference

Conference34th European conference on Advances in Information Retrieval
Abbreviated titleECIR 2012
CountrySpain
CityBarcelona
Period1/04/125/04/12

Keywords

  • vertical intent
  • search interface
  • web search engines

Fingerprint Dive into the research topics of 'Assessing and predicting vertical intent for web queries'. Together they form a unique fingerprint.

Cite this