Proactive Information Retrieval by Capturing Search Intent from Primary Task Context

Markus Koskela, Petri Luukkonen, Tuukka Ruotsalo, Mats Sjöberg, Patrik Floréen

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

Sammanfattning

A significant fraction of information searches are motivated by the user's primary task. An ideal search engine would be able to use information captured from the primary task to proactively retrieve useful information. Previous work has shown that many information retrieval activities depend on the primary task in which the retrieved information is to be used, but fairly little research has been focusing on methods that automatically learn the informational intents from the primary task context. We study how the implicit primary task context can be used to model the user's search intent and to proactively retrieve relevant and useful information. Data comprising of logs from a user study, in which users are writing an essay, demonstrate that users' search intents can be captured from the task and relevant and useful information can be proactively retrieved. Data from simulations with several datasets of different complexity show that the proposed approach of using primary task context generalizes to a variety of data. Our findings have implications for the design of proactive search systems that can infer users' search intent implicitly by monitoring users' primary task activities.

Originalspråkengelska
Artikelnummer20
TidskriftACM Transactions on Interactive Intelligent Systems (TiiS)
Volym8
Utgåva3
Antal sidor25
ISSN2160-6455
DOI
StatusPublicerad - aug 2018
MoE-publikationstypA1 Tidskriftsartikel-refererad

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här

@article{c5f8c4c62e4443539212264085de2256,
title = "Proactive Information Retrieval by Capturing Search Intent from Primary Task Context",
abstract = "A significant fraction of information searches are motivated by the user's primary task. An ideal search engine would be able to use information captured from the primary task to proactively retrieve useful information. Previous work has shown that many information retrieval activities depend on the primary task in which the retrieved information is to be used, but fairly little research has been focusing on methods that automatically learn the informational intents from the primary task context. We study how the implicit primary task context can be used to model the user's search intent and to proactively retrieve relevant and useful information. Data comprising of logs from a user study, in which users are writing an essay, demonstrate that users' search intents can be captured from the task and relevant and useful information can be proactively retrieved. Data from simulations with several datasets of different complexity show that the proposed approach of using primary task context generalizes to a variety of data. Our findings have implications for the design of proactive search systems that can infer users' search intent implicitly by monitoring users' primary task activities.",
keywords = "113 Computer and information sciences, Task-based information retrieval, proactive search, user intent modeling, SEEKING, SYSTEM",
author = "Markus Koskela and Petri Luukkonen and Tuukka Ruotsalo and Mats Sj{\"o}berg and Patrik Flor{\'e}en",
year = "2018",
month = "8",
doi = "10.1145/3150975",
language = "English",
volume = "8",
journal = "ACM Transactions on Interactive Intelligent Systems (TiiS)",
issn = "2160-6455",
publisher = "ACM, Association for Computing Machinery",
number = "3",

}

Proactive Information Retrieval by Capturing Search Intent from Primary Task Context. / Koskela, Markus; Luukkonen, Petri; Ruotsalo, Tuukka; Sjöberg, Mats; Floréen, Patrik.

I: ACM Transactions on Interactive Intelligent Systems (TiiS), Vol. 8, Nr. 3, 20, 08.2018.

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

TY - JOUR

T1 - Proactive Information Retrieval by Capturing Search Intent from Primary Task Context

AU - Koskela, Markus

AU - Luukkonen, Petri

AU - Ruotsalo, Tuukka

AU - Sjöberg, Mats

AU - Floréen, Patrik

PY - 2018/8

Y1 - 2018/8

N2 - A significant fraction of information searches are motivated by the user's primary task. An ideal search engine would be able to use information captured from the primary task to proactively retrieve useful information. Previous work has shown that many information retrieval activities depend on the primary task in which the retrieved information is to be used, but fairly little research has been focusing on methods that automatically learn the informational intents from the primary task context. We study how the implicit primary task context can be used to model the user's search intent and to proactively retrieve relevant and useful information. Data comprising of logs from a user study, in which users are writing an essay, demonstrate that users' search intents can be captured from the task and relevant and useful information can be proactively retrieved. Data from simulations with several datasets of different complexity show that the proposed approach of using primary task context generalizes to a variety of data. Our findings have implications for the design of proactive search systems that can infer users' search intent implicitly by monitoring users' primary task activities.

AB - A significant fraction of information searches are motivated by the user's primary task. An ideal search engine would be able to use information captured from the primary task to proactively retrieve useful information. Previous work has shown that many information retrieval activities depend on the primary task in which the retrieved information is to be used, but fairly little research has been focusing on methods that automatically learn the informational intents from the primary task context. We study how the implicit primary task context can be used to model the user's search intent and to proactively retrieve relevant and useful information. Data comprising of logs from a user study, in which users are writing an essay, demonstrate that users' search intents can be captured from the task and relevant and useful information can be proactively retrieved. Data from simulations with several datasets of different complexity show that the proposed approach of using primary task context generalizes to a variety of data. Our findings have implications for the design of proactive search systems that can infer users' search intent implicitly by monitoring users' primary task activities.

KW - 113 Computer and information sciences

KW - Task-based information retrieval

KW - proactive search

KW - user intent modeling

KW - SEEKING

KW - SYSTEM

U2 - 10.1145/3150975

DO - 10.1145/3150975

M3 - Article

VL - 8

JO - ACM Transactions on Interactive Intelligent Systems (TiiS)

JF - ACM Transactions on Interactive Intelligent Systems (TiiS)

SN - 2160-6455

IS - 3

M1 - 20

ER -