Recommendation of optimized information seeking process based on the similarity of user access behavior patterns

Jian Chen, Xiaokang Zhou, Qun Jin*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)


Differing from many studies of recommendation that provided the final results directly, our study focuses on providing an optimized process of information seeking to users. Based on process mining, we propose an integrated adaptive framework to support and facilitate individualized recommendation based on the gradual adaptation model that gradually adapts to a target user's transition of needs and behaviors of information access, including various search-related activities, over different time spans. In detail, successful information seeking processes are extracted from the information seeking histories of users. Furthermore, these successful information seeking processes are optimized as a series of action units to support the target users whose information access behavior patterns are similar to the reference users. Based on these, the optimized information seeking processes are navigated to the target users according to their transitions of interest focus. In addition to describing some definitions and measures introduced, we go further to present an optimized process recommendation model and show the system architecture. Finally, we discuss the simulation and scenario for the proposed system.

Original languageEnglish
Pages (from-to)1671-1681
Number of pages11
JournalPersonal and Ubiquitous Computing
Issue number8
Publication statusPublished - 2013 Dec


  • Behavior patterns
  • Information seeking process
  • Personalized recommendation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Science Applications
  • Management Science and Operations Research


Dive into the research topics of 'Recommendation of optimized information seeking process based on the similarity of user access behavior patterns'. Together they form a unique fingerprint.

Cite this