Intentradar: search user interface that anticipates user's search intents

Tuukka Ruotsalo; Jaakko Peltonen; Manuel J. A. Eugster; Dorota Glowacka; Aki Reijonen; Giulio Jacucci; Petri Myllymäki; Samuel Kaski

doi:10.1145/2559206.2574807

Intentradar: search user interface that anticipates user's search intents

Tuukka Ruotsalo, Jaakko Peltonen, Manuel J. A. Eugster, Dorota Glowacka, Aki Reijonen, Giulio Jacucci, Petri Myllymäki, Samuel Kaski

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce IntentRadar, an interactive search user interface that anticipates user's search intents by estimating them from user interaction. The estimated intents are represented as keywords and visualized on a radial layout that organizes the keywords as directions in the information space. IntentRadar assists users to direct their search by allowing to target relevance feedback on keywords by manipulating the position of the keywords on the radar. The system then learns and visualizes improved estimates of intents and retrieves documents corresponding to the present search intent estimate. IntentRadar has been shown to significantly improve users' task performance and the quality of retrieved information without compromising task execution time.

Original language	English
Title of host publication	CHI Conference on Human Factors in Computing Systems, CHI'14, Toronto, ON, Canada - April 26 - May 01, 2014, Extended Abstracts
Pages	455-458
Number of pages	4
DOIs	https://doi.org/10.1145/2559206.2574807
Publication status	Published - 2014

Access to Document

10.1145/2559206.2574807

http://dl.acm.org/citation.cfm?doid=2559206.2574807

Cite this

Ruotsalo, T., Peltonen, J., Eugster, M. J. A., Glowacka, D., Reijonen, A., Jacucci, G., Myllymäki, P., & Kaski, S. (2014). Intentradar: search user interface that anticipates user's search intents. In CHI Conference on Human Factors in Computing Systems, CHI'14, Toronto, ON, Canada - April 26 - May 01, 2014, Extended Abstracts (pp. 455-458) https://doi.org/10.1145/2559206.2574807

@inproceedings{bfbb97ef4ce04d758dfad8e6b6a35e90,

title = "Intentradar: search user interface that anticipates user's search intents",

abstract = "We introduce IntentRadar, an interactive search user interface that anticipates user's search intents by estimating them from user interaction. The estimated intents are represented as keywords and visualized on a radial layout that organizes the keywords as directions in the information space. IntentRadar assists users to direct their search by allowing to target relevance feedback on keywords by manipulating the position of the keywords on the radar. The system then learns and visualizes improved estimates of intents and retrieves documents corresponding to the present search intent estimate. IntentRadar has been shown to significantly improve users' task performance and the quality of retrieved information without compromising task execution time.",

author = "Tuukka Ruotsalo and Jaakko Peltonen and Eugster, {Manuel J. A.} and Dorota Glowacka and Aki Reijonen and Giulio Jacucci and Petri Myllym{\"a}ki and Samuel Kaski",

year = "2014",

doi = "10.1145/2559206.2574807",

language = "English",

pages = "455--458",

booktitle = "CHI Conference on Human Factors in Computing Systems, CHI'14, Toronto, ON, Canada - April 26 - May 01, 2014, Extended Abstracts",

}

Intentradar: search user interface that anticipates user's search intents. / Ruotsalo, Tuukka; Peltonen, Jaakko; Eugster, Manuel J. A. et al.
CHI Conference on Human Factors in Computing Systems, CHI'14, Toronto, ON, Canada - April 26 - May 01, 2014, Extended Abstracts. 2014. p. 455-458.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Intentradar: search user interface that anticipates user's search intents

AU - Ruotsalo, Tuukka

AU - Peltonen, Jaakko

AU - Eugster, Manuel J. A.

AU - Glowacka, Dorota

AU - Reijonen, Aki

AU - Jacucci, Giulio

AU - Myllymäki, Petri

AU - Kaski, Samuel

PY - 2014

Y1 - 2014

N2 - We introduce IntentRadar, an interactive search user interface that anticipates user's search intents by estimating them from user interaction. The estimated intents are represented as keywords and visualized on a radial layout that organizes the keywords as directions in the information space. IntentRadar assists users to direct their search by allowing to target relevance feedback on keywords by manipulating the position of the keywords on the radar. The system then learns and visualizes improved estimates of intents and retrieves documents corresponding to the present search intent estimate. IntentRadar has been shown to significantly improve users' task performance and the quality of retrieved information without compromising task execution time.

AB - We introduce IntentRadar, an interactive search user interface that anticipates user's search intents by estimating them from user interaction. The estimated intents are represented as keywords and visualized on a radial layout that organizes the keywords as directions in the information space. IntentRadar assists users to direct their search by allowing to target relevance feedback on keywords by manipulating the position of the keywords on the radar. The system then learns and visualizes improved estimates of intents and retrieves documents corresponding to the present search intent estimate. IntentRadar has been shown to significantly improve users' task performance and the quality of retrieved information without compromising task execution time.

UR - https://youtu.be/zOoFNpF6eFk

U2 - 10.1145/2559206.2574807

DO - 10.1145/2559206.2574807

M3 - Conference contribution

SP - 455

EP - 458

BT - CHI Conference on Human Factors in Computing Systems, CHI'14, Toronto, ON, Canada - April 26 - May 01, 2014, Extended Abstracts

ER -

Intentradar: search user interface that anticipates user's search intents

Abstract

Access to Document

Other files and links

Fingerprint

Cite this