Standard

Knowing the Unknown : Visualising Consumption Blind-Spots in Recommender System. / Tintarev, Nava; Rostami, Shahin; Smyth, Barry.

SAC '18 : Proceedings of the 33rd Annual ACM Symposium on Applied Computing . New York : Association for Computer Machinery, 2018. p. 1396-1399 .

Research output: Scientific - peer-reviewConference contribution

Harvard

Tintarev, N, Rostami, S & Smyth, B 2018, Knowing the Unknown: Visualising Consumption Blind-Spots in Recommender System. in SAC '18 : Proceedings of the 33rd Annual ACM Symposium on Applied Computing . Association for Computer Machinery, New York, pp. 1396-1399 , SAC 2018, Pau, France, 9/04/18. DOI: 10.1145/3167132.3167419

APA

Tintarev, N., Rostami, S., & Smyth, B. (2018). Knowing the Unknown: Visualising Consumption Blind-Spots in Recommender System. In SAC '18 : Proceedings of the 33rd Annual ACM Symposium on Applied Computing (pp. 1396-1399 ). New York: Association for Computer Machinery. DOI: 10.1145/3167132.3167419

Vancouver

Tintarev N, Rostami S, Smyth B. Knowing the Unknown: Visualising Consumption Blind-Spots in Recommender System. In SAC '18 : Proceedings of the 33rd Annual ACM Symposium on Applied Computing . New York: Association for Computer Machinery. 2018. p. 1396-1399 . Available from, DOI: 10.1145/3167132.3167419

Author

Tintarev, Nava ; Rostami, Shahin ; Smyth, Barry. / Knowing the Unknown : Visualising Consumption Blind-Spots in Recommender System. SAC '18 : Proceedings of the 33rd Annual ACM Symposium on Applied Computing . New York : Association for Computer Machinery, 2018. pp. 1396-1399

BibTeX

@inbook{61c0f406450646b6ae772d11dd36f1fc,
title = "Knowing the Unknown: Visualising Consumption Blind-Spots in Recommender System",
abstract = "In this paper we consider how to help users to better understand their consumption profiles by examining two approaches to visualising user profiles - chord diagrams, and bar charts - aimed at revealing to users those regions of the recommendation space that are unknown to them, i.e. blind-spots. Both visualisations do this by connecting profile preferences with a filtered recommendation space. We compare and contrast the two visualisations in a live user study (n = 70). The results suggest that, although users can understand both visualisations, chord diagrams are particularly effective in helping users to identify blind-spots, while simpler bar charts are better for conveying what was already known in a profile. Evaluating the understandability of blind-spot visualizations is a first step toward using visual explanations to help address a criticism of recommender systems: that personalising information creates filter bubbles.",
keywords = "Visualisation, Recommender Systems, Filter Bubble, Chord Diagram",
author = "Nava Tintarev and Shahin Rostami and Barry Smyth",
year = "2018",
doi = "10.1145/3167132.3167419",
isbn = "978-1-4503-5191-1",
pages = "1396--1399",
booktitle = "SAC '18",
publisher = "Association for Computer Machinery",

}

RIS

TY - CHAP

T1 - Knowing the Unknown

T2 - Visualising Consumption Blind-Spots in Recommender System

AU - Tintarev,Nava

AU - Rostami,Shahin

AU - Smyth,Barry

PY - 2018

Y1 - 2018

N2 - In this paper we consider how to help users to better understand their consumption profiles by examining two approaches to visualising user profiles - chord diagrams, and bar charts - aimed at revealing to users those regions of the recommendation space that are unknown to them, i.e. blind-spots. Both visualisations do this by connecting profile preferences with a filtered recommendation space. We compare and contrast the two visualisations in a live user study (n = 70). The results suggest that, although users can understand both visualisations, chord diagrams are particularly effective in helping users to identify blind-spots, while simpler bar charts are better for conveying what was already known in a profile. Evaluating the understandability of blind-spot visualizations is a first step toward using visual explanations to help address a criticism of recommender systems: that personalising information creates filter bubbles.

AB - In this paper we consider how to help users to better understand their consumption profiles by examining two approaches to visualising user profiles - chord diagrams, and bar charts - aimed at revealing to users those regions of the recommendation space that are unknown to them, i.e. blind-spots. Both visualisations do this by connecting profile preferences with a filtered recommendation space. We compare and contrast the two visualisations in a live user study (n = 70). The results suggest that, although users can understand both visualisations, chord diagrams are particularly effective in helping users to identify blind-spots, while simpler bar charts are better for conveying what was already known in a profile. Evaluating the understandability of blind-spot visualizations is a first step toward using visual explanations to help address a criticism of recommender systems: that personalising information creates filter bubbles.

KW - Visualisation

KW - Recommender Systems

KW - Filter Bubble

KW - Chord Diagram

U2 - 10.1145/3167132.3167419

DO - 10.1145/3167132.3167419

M3 - Conference contribution

SN - 978-1-4503-5191-1

SP - 1396

EP - 1399

BT - SAC '18

PB - Association for Computer Machinery

ER -

ID: 32310990