SNIF-ACT: A Cognitive Model of User Navigation on the World Wide Web

Abstract

We describe the development of a computational cognitive model that explains navigation behavior on the World Wide Web (WWW). The model, called SNIF-ACT (Scent-based Navigation and Information Foraging in the ACT cognitive architecture), is motivated by Information Foraging Theory (IFT), which quantifies the perceived relevance of a Web link to a user goal by a spreading activation mechanism. The model assumes that users evaluate links on a Web page sequentially, and decide to click on a link or to go back to the previous page by a Bayesian satisficing model (BSM) that adaptively evaluates and selects actions based on a combination of previous and current assessments of the relevance of link texts to information goals. The model was tested against data collected from novice users engaged in unfamiliar information-seeking tasks. SNIF-ACT 1.0 utilizes the measure of utility, called information scent, derived from IFT to predict rankings of links on different Web pages. The model was tested against a detailed set of protocol data collected from eight subjects as they engaged in two information-seeking tasks using the WWW. The model provided a good match to subjects link selections and decisions to leave a Web site, and thus provided support for the use of information scent as a psychological measure of the perceived relevance of link text to information goals. In SNIF-ACT 2.0, we include an adaptive link selection mechanism that sequentially evaluates links on a Web page according to their position. The mechanism was derived based on a rational analysis of link selection on a Web page. The mechanism allowed the model to dynamically update the evaluation of actions (e.g., to follow a link or leave a Web site) based on sequential assessments of link texts on a Web page, and to decide when to leave a page based on experiences with previous pages. SNIF-ACT 2.0 was validated on a data set obtained from 74 subjects. Monte Carlo simulations of the model showed that SNIF-ACT 2

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 03, 2007
Accession Number
ADA462156

Entities

People

  • Peter Pirolli
  • Wai-tat Fu

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy
  • Biomedical

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Cognition
  • Cognitive Science
  • Cognitive Systems Engineering
  • Computational Science
  • Data Sets
  • Databases
  • Human Behavior
  • Human-Computer Interaction
  • Information Retrieval
  • Information Science
  • Psychological Theory
  • Psychology
  • Random Variables
  • User Interface
  • Websites
  • World Wide Web

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Networking
  • Geospatial Intelligence and Artificial Intelligence Analytics

Technology Areas

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