VisIRR: A visual analytics system for information retrieval and recommendation for large-Scale document data

Jaegul Choo, K. I.M. Hannah, Edward Clarkson, L. I.U. Zhicheng, L. E.E. Changhyun, L. I. Fuxin, L. E.E. Hanseung, Ramakrishnan Kannan, Charles D. Stolper, John Stasko, Haesun Park

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this article, we present an interactive visual information retrieval and recommendation system, called VisIRR, for large-scale document discovery. VisIRR effectively combines the paradigms of (1) a passive pull through query processes for retrieval and (2) an active push that recommends items of potential interest to users based on their preferences. Equipped with an efficient dynamic query interface against a large-scale corpus, VisIRR organizes the retrieved documents into high-level topics and visualizes them in a 2D space, representing the relationships among the topics along with their keyword summary. In addition, based on interactive personalized preference feedback with regard to documents, VisIRR provides document recommendations from the entire corpus, which are beyond the retrieved sets. Such recommended documents are visualized in the same space as the retrieved documents, so that users can seamlessly analyze both existing and newly recommended ones. This article presents novel computational methods, which make these integrated representations and fast interactions possible for a large-scale document corpus. We illustrate how the system works by providing detailed usage scenarios. Additionally, we present preliminary user study results for evaluating the effectiveness of the system.

Original languageEnglish
Article number8
JournalACM Transactions on Knowledge Discovery from Data
Volume12
Issue number1
DOIs
Publication statusPublished - 2018 Feb 1

Fingerprint

Information retrieval systems
Recommender systems
Computational methods
Information retrieval
Feedback

Keywords

  • Clustering
  • Dimension reduction
  • Information retrieval
  • Recommendation
  • Topic modeling

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

VisIRR : A visual analytics system for information retrieval and recommendation for large-Scale document data. / Choo, Jaegul; Hannah, K. I.M.; Clarkson, Edward; Zhicheng, L. I.U.; Changhyun, L. E.E.; Fuxin, L. I.; Hanseung, L. E.E.; Kannan, Ramakrishnan; Stolper, Charles D.; Stasko, John; Park, Haesun.

In: ACM Transactions on Knowledge Discovery from Data, Vol. 12, No. 1, 8, 01.02.2018.

Research output: Contribution to journalArticle

Choo, J, Hannah, KIM, Clarkson, E, Zhicheng, LIU, Changhyun, LEE, Fuxin, LI, Hanseung, LEE, Kannan, R, Stolper, CD, Stasko, J & Park, H 2018, 'VisIRR: A visual analytics system for information retrieval and recommendation for large-Scale document data', ACM Transactions on Knowledge Discovery from Data, vol. 12, no. 1, 8. https://doi.org/10.1145/3070616
Choo, Jaegul ; Hannah, K. I.M. ; Clarkson, Edward ; Zhicheng, L. I.U. ; Changhyun, L. E.E. ; Fuxin, L. I. ; Hanseung, L. E.E. ; Kannan, Ramakrishnan ; Stolper, Charles D. ; Stasko, John ; Park, Haesun. / VisIRR : A visual analytics system for information retrieval and recommendation for large-Scale document data. In: ACM Transactions on Knowledge Discovery from Data. 2018 ; Vol. 12, No. 1.
@article{79cd4e6e9ea046169f1e694d526ab88b,
title = "VisIRR: A visual analytics system for information retrieval and recommendation for large-Scale document data",
abstract = "In this article, we present an interactive visual information retrieval and recommendation system, called VisIRR, for large-scale document discovery. VisIRR effectively combines the paradigms of (1) a passive pull through query processes for retrieval and (2) an active push that recommends items of potential interest to users based on their preferences. Equipped with an efficient dynamic query interface against a large-scale corpus, VisIRR organizes the retrieved documents into high-level topics and visualizes them in a 2D space, representing the relationships among the topics along with their keyword summary. In addition, based on interactive personalized preference feedback with regard to documents, VisIRR provides document recommendations from the entire corpus, which are beyond the retrieved sets. Such recommended documents are visualized in the same space as the retrieved documents, so that users can seamlessly analyze both existing and newly recommended ones. This article presents novel computational methods, which make these integrated representations and fast interactions possible for a large-scale document corpus. We illustrate how the system works by providing detailed usage scenarios. Additionally, we present preliminary user study results for evaluating the effectiveness of the system.",
keywords = "Clustering, Dimension reduction, Information retrieval, Recommendation, Topic modeling",
author = "Jaegul Choo and Hannah, {K. I.M.} and Edward Clarkson and Zhicheng, {L. I.U.} and Changhyun, {L. E.E.} and Fuxin, {L. I.} and Hanseung, {L. E.E.} and Ramakrishnan Kannan and Stolper, {Charles D.} and John Stasko and Haesun Park",
year = "2018",
month = "2",
day = "1",
doi = "10.1145/3070616",
language = "English",
volume = "12",
journal = "ACM Transactions on Knowledge Discovery from Data",
issn = "1556-4681",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - VisIRR

T2 - A visual analytics system for information retrieval and recommendation for large-Scale document data

AU - Choo, Jaegul

AU - Hannah, K. I.M.

AU - Clarkson, Edward

AU - Zhicheng, L. I.U.

AU - Changhyun, L. E.E.

AU - Fuxin, L. I.

AU - Hanseung, L. E.E.

AU - Kannan, Ramakrishnan

AU - Stolper, Charles D.

AU - Stasko, John

AU - Park, Haesun

PY - 2018/2/1

Y1 - 2018/2/1

N2 - In this article, we present an interactive visual information retrieval and recommendation system, called VisIRR, for large-scale document discovery. VisIRR effectively combines the paradigms of (1) a passive pull through query processes for retrieval and (2) an active push that recommends items of potential interest to users based on their preferences. Equipped with an efficient dynamic query interface against a large-scale corpus, VisIRR organizes the retrieved documents into high-level topics and visualizes them in a 2D space, representing the relationships among the topics along with their keyword summary. In addition, based on interactive personalized preference feedback with regard to documents, VisIRR provides document recommendations from the entire corpus, which are beyond the retrieved sets. Such recommended documents are visualized in the same space as the retrieved documents, so that users can seamlessly analyze both existing and newly recommended ones. This article presents novel computational methods, which make these integrated representations and fast interactions possible for a large-scale document corpus. We illustrate how the system works by providing detailed usage scenarios. Additionally, we present preliminary user study results for evaluating the effectiveness of the system.

AB - In this article, we present an interactive visual information retrieval and recommendation system, called VisIRR, for large-scale document discovery. VisIRR effectively combines the paradigms of (1) a passive pull through query processes for retrieval and (2) an active push that recommends items of potential interest to users based on their preferences. Equipped with an efficient dynamic query interface against a large-scale corpus, VisIRR organizes the retrieved documents into high-level topics and visualizes them in a 2D space, representing the relationships among the topics along with their keyword summary. In addition, based on interactive personalized preference feedback with regard to documents, VisIRR provides document recommendations from the entire corpus, which are beyond the retrieved sets. Such recommended documents are visualized in the same space as the retrieved documents, so that users can seamlessly analyze both existing and newly recommended ones. This article presents novel computational methods, which make these integrated representations and fast interactions possible for a large-scale document corpus. We illustrate how the system works by providing detailed usage scenarios. Additionally, we present preliminary user study results for evaluating the effectiveness of the system.

KW - Clustering

KW - Dimension reduction

KW - Information retrieval

KW - Recommendation

KW - Topic modeling

UR - http://www.scopus.com/inward/record.url?scp=85042531976&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042531976&partnerID=8YFLogxK

U2 - 10.1145/3070616

DO - 10.1145/3070616

M3 - Article

AN - SCOPUS:85042531976

VL - 12

JO - ACM Transactions on Knowledge Discovery from Data

JF - ACM Transactions on Knowledge Discovery from Data

SN - 1556-4681

IS - 1

M1 - 8

ER -