From Machu-Picchu to "rafting the urubamba river"

Anticipating information needs via the entity-query graph

Ilaria Bordino, Gianmarco Morales, Ingmar Weber, Francesco Bonchi

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

23 Citations (Scopus)

Abstract

We study the problem of anticipating user search needs, based on their browsing activity. Given the current web page p that a user is visiting we want to recommend a small and diverse set of search queries that are relevant to the content of p, but also non-obvious and serendipitous. We introduce a novel method that is based on the content of the page visited, rather than on past browsing patterns as in previous literature. Our content-based approach can be used even for previously unseen pages. We represent the topics of a page by the set of Wikipedia entities extracted from it. To obtain useful query suggestions for these entities, we exploit a novel graph model that we call EQGraph (Entity-Query Graph), containing entities, queries, and transitions between entities, between queries, as well as from entities to queries. We perform Personalized PageRank computation on such a graph to expand the set of entities extracted from a page into a richer set of entities, and to associate these entities with relevant query suggestions. We develop an efficient implementation to deal with large graph instances and suggest queries from a large and diverse pool. We perform a user study that shows that our method produces relevant and interesting recommendations, and outperforms an alternative method based on reverse IR.

Original languageEnglish
Title of host publicationWSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining
Pages275-284
Number of pages10
DOIs
Publication statusPublished - 28 Feb 2013
Event6th ACM International Conference on Web Search and Data Mining, WSDM 2013 - Rome, Italy
Duration: 4 Feb 20138 Feb 2013

Other

Other6th ACM International Conference on Web Search and Data Mining, WSDM 2013
CountryItaly
CityRome
Period4/2/138/2/13

Fingerprint

Websites
Rivers

Keywords

  • entity extraction
  • implicit search
  • query suggestions
  • serendipity

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Bordino, I., Morales, G., Weber, I., & Bonchi, F. (2013). From Machu-Picchu to "rafting the urubamba river": Anticipating information needs via the entity-query graph. In WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining (pp. 275-284) https://doi.org/10.1145/2433396.2433433

From Machu-Picchu to "rafting the urubamba river" : Anticipating information needs via the entity-query graph. / Bordino, Ilaria; Morales, Gianmarco; Weber, Ingmar; Bonchi, Francesco.

WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. p. 275-284.

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

Bordino, I, Morales, G, Weber, I & Bonchi, F 2013, From Machu-Picchu to "rafting the urubamba river": Anticipating information needs via the entity-query graph. in WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. pp. 275-284, 6th ACM International Conference on Web Search and Data Mining, WSDM 2013, Rome, Italy, 4/2/13. https://doi.org/10.1145/2433396.2433433
Bordino I, Morales G, Weber I, Bonchi F. From Machu-Picchu to "rafting the urubamba river": Anticipating information needs via the entity-query graph. In WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. p. 275-284 https://doi.org/10.1145/2433396.2433433
Bordino, Ilaria ; Morales, Gianmarco ; Weber, Ingmar ; Bonchi, Francesco. / From Machu-Picchu to "rafting the urubamba river" : Anticipating information needs via the entity-query graph. WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013. pp. 275-284
@inproceedings{9c86ec6460d24e97bebbf4f9bdb3bdd6,
title = "From Machu-Picchu to {"}rafting the urubamba river{"}: Anticipating information needs via the entity-query graph",
abstract = "We study the problem of anticipating user search needs, based on their browsing activity. Given the current web page p that a user is visiting we want to recommend a small and diverse set of search queries that are relevant to the content of p, but also non-obvious and serendipitous. We introduce a novel method that is based on the content of the page visited, rather than on past browsing patterns as in previous literature. Our content-based approach can be used even for previously unseen pages. We represent the topics of a page by the set of Wikipedia entities extracted from it. To obtain useful query suggestions for these entities, we exploit a novel graph model that we call EQGraph (Entity-Query Graph), containing entities, queries, and transitions between entities, between queries, as well as from entities to queries. We perform Personalized PageRank computation on such a graph to expand the set of entities extracted from a page into a richer set of entities, and to associate these entities with relevant query suggestions. We develop an efficient implementation to deal with large graph instances and suggest queries from a large and diverse pool. We perform a user study that shows that our method produces relevant and interesting recommendations, and outperforms an alternative method based on reverse IR.",
keywords = "entity extraction, implicit search, query suggestions, serendipity",
author = "Ilaria Bordino and Gianmarco Morales and Ingmar Weber and Francesco Bonchi",
year = "2013",
month = "2",
day = "28",
doi = "10.1145/2433396.2433433",
language = "English",
isbn = "9781450318693",
pages = "275--284",
booktitle = "WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - From Machu-Picchu to "rafting the urubamba river"

T2 - Anticipating information needs via the entity-query graph

AU - Bordino, Ilaria

AU - Morales, Gianmarco

AU - Weber, Ingmar

AU - Bonchi, Francesco

PY - 2013/2/28

Y1 - 2013/2/28

N2 - We study the problem of anticipating user search needs, based on their browsing activity. Given the current web page p that a user is visiting we want to recommend a small and diverse set of search queries that are relevant to the content of p, but also non-obvious and serendipitous. We introduce a novel method that is based on the content of the page visited, rather than on past browsing patterns as in previous literature. Our content-based approach can be used even for previously unseen pages. We represent the topics of a page by the set of Wikipedia entities extracted from it. To obtain useful query suggestions for these entities, we exploit a novel graph model that we call EQGraph (Entity-Query Graph), containing entities, queries, and transitions between entities, between queries, as well as from entities to queries. We perform Personalized PageRank computation on such a graph to expand the set of entities extracted from a page into a richer set of entities, and to associate these entities with relevant query suggestions. We develop an efficient implementation to deal with large graph instances and suggest queries from a large and diverse pool. We perform a user study that shows that our method produces relevant and interesting recommendations, and outperforms an alternative method based on reverse IR.

AB - We study the problem of anticipating user search needs, based on their browsing activity. Given the current web page p that a user is visiting we want to recommend a small and diverse set of search queries that are relevant to the content of p, but also non-obvious and serendipitous. We introduce a novel method that is based on the content of the page visited, rather than on past browsing patterns as in previous literature. Our content-based approach can be used even for previously unseen pages. We represent the topics of a page by the set of Wikipedia entities extracted from it. To obtain useful query suggestions for these entities, we exploit a novel graph model that we call EQGraph (Entity-Query Graph), containing entities, queries, and transitions between entities, between queries, as well as from entities to queries. We perform Personalized PageRank computation on such a graph to expand the set of entities extracted from a page into a richer set of entities, and to associate these entities with relevant query suggestions. We develop an efficient implementation to deal with large graph instances and suggest queries from a large and diverse pool. We perform a user study that shows that our method produces relevant and interesting recommendations, and outperforms an alternative method based on reverse IR.

KW - entity extraction

KW - implicit search

KW - query suggestions

KW - serendipity

UR - http://www.scopus.com/inward/record.url?scp=84874258712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874258712&partnerID=8YFLogxK

U2 - 10.1145/2433396.2433433

DO - 10.1145/2433396.2433433

M3 - Conference contribution

SN - 9781450318693

SP - 275

EP - 284

BT - WSDM 2013 - Proceedings of the 6th ACM International Conference on Web Search and Data Mining

ER -