Evaluating a Visual Information Retrieval Interface: AspInquery at TREC-6

Abstract

We built two Information Retrieval systems that were targeted for the TREC-6 "aspect oriented" retrieval track. The systems were built to test the usefulness of different visualizations in an interactive IR setting--in particular, an "aspect window" for the chosen task, and a 3-D visualization of document inter-relationships. We studied 24 users of the system and report the usage of different user interface elements, whether experienced users outperformed novices, and whether spatial reasoning ability was a good predictor of effective use of 3-D. Much if not most usage of Information Retrieval (IR) is in an interactive setting, where an individual must use an IR system to obtain information that they need. But historically, most IR evaluations are based on comparing batch mode runs of IR systems on fixed corpora and measuring precision (the percentage of documents that are retrieved that are relevant) and recall (the percentage of relevant documents that are retrieved). IR systems were expensive and used primarily by trained professionals for a very specific task. With the explosion of information available, information retrieval, exploration and organization are becoming tasks that users of very diverse backgrounds are required to perform.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2005
Accession Number
ADA439396

Entities

People

  • Don Byrd
  • James Allan
  • Russell Swan

Organizations

  • University of Massachusetts Amherst

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Computer Science
  • Control Systems
  • Data Displays
  • Experimental Design
  • Graphical User Interface
  • Human-Machine Interaction
  • Information Retrieval
  • Precision
  • Standards
  • Statistical Analysis
  • Three Dimensional
  • User Interface
  • Visualizations
  • Web Browsers

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Information Retrieval