skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data

Abstract

In this paper, 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. Finally, we present preliminary user study results for evaluating the effectiveness of the system.

Authors:
 [1];  [2];  [2];  [3];  [4];  [5];  [4]; ORCiD logo [6];  [7];  [2];  [2]
  1. Korea University, Seoul (South Korea)
  2. Georgia Inst. of Technology, Atlanta, GA (United States)
  3. Adobe Research, Seattle, WA (United States)
  4. Google Inc., Mountain View, CA (United States)
  5. Oregon State University, Corvallis, OR (United States)
  6. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  7. Southwestern University, Georgetown, TX (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1426558
Grant/Contract Number:
AC05-00OR22725
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
ACM Transactions on Knowledge Discovery from Data
Additional Journal Information:
Journal Volume: 12; Journal Issue: 1; Journal ID: ISSN 1556-4681
Publisher:
Association for Computing Machinery
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 96 KNOWLEDGE MANAGEMENT AND PRESERVATION

Citation Formats

Choo, Jaegul, Kim, Hannah, Clarkson, Edward, Liu, Zhicheng, Lee, Changhyun, Li, Fuxin, Lee, Hanseung, Kannan, Ramakrishnan, Stolper, Charles D., Stasko, John, and Park, Haesun. VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data. United States: N. p., 2018. Web. doi:10.1145/3070616.
Choo, Jaegul, Kim, Hannah, Clarkson, Edward, Liu, Zhicheng, Lee, Changhyun, Li, Fuxin, Lee, Hanseung, Kannan, Ramakrishnan, Stolper, Charles D., Stasko, John, & Park, Haesun. VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data. United States. doi:10.1145/3070616.
Choo, Jaegul, Kim, Hannah, Clarkson, Edward, Liu, Zhicheng, Lee, Changhyun, Li, Fuxin, Lee, Hanseung, Kannan, Ramakrishnan, Stolper, Charles D., Stasko, John, and Park, Haesun. Wed . "VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data". United States. doi:10.1145/3070616.
@article{osti_1426558,
title = {VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data},
author = {Choo, Jaegul and Kim, Hannah and Clarkson, Edward and Liu, Zhicheng and Lee, Changhyun and Li, Fuxin and Lee, Hanseung and Kannan, Ramakrishnan and Stolper, Charles D. and Stasko, John and Park, Haesun},
abstractNote = {In this paper, 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. Finally, we present preliminary user study results for evaluating the effectiveness of the system.},
doi = {10.1145/3070616},
journal = {ACM Transactions on Knowledge Discovery from Data},
number = 1,
volume = 12,
place = {United States},
year = {Wed Jan 31 00:00:00 EST 2018},
month = {Wed Jan 31 00:00:00 EST 2018}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on January 31, 2019
Publisher's Version of Record

Save / Share: