LoyalTracker: Visualizing Loyalty Dynamics in Search Engines

LoyalTracker illustrates the dynamic loyalty variation of the customers using search engine A . Top and bottom show the same LoyalTracker that highlights two different flowing patterns of the customers (in orange) selected from a layer flow (top) and a branch flow (bottom) across multiple loyalty categories (layers) over time. The switching histogram on the top shows a visual summary of customer switching behavior.

The huge amount of user log data collected by search engine providers creates new opportunities to understand user loyalty and defection behavior at an unprecedented scale. However, this also poses a great challenge to analyze the behavior and glean insights into the complex, large data. In this paper, we introduce LoyalTracker, a visual analytics system to track user loyalty and switching behavior towards multiple search engines from the vast amount of user log data. We propose a new interactive visualization technique (flow view) based on a flow metaphor, which conveys a proper visual summary of the dynamics of user loyalty of thousands of users over time. Two other visualization techniques, a density map and a word cloud, are integrated to enable analysts to gain further insights into the patterns identified by the flow view. Case studies and the interview with domain experts are conducted to demonstrate the usefulness of our technique in understanding user loyalty and switching behavior in search engines.

LoyalTracker: Visualizing Loyalty Dynamics in Search Engines from VGTCommunity on Vimeo.

@article {YWu2014c,
author = {Conglei Shi and Yingcai Wu and Shixia Liu and Hong Zhou and Huamin Qu},
title = {{LoyalTracker}: Visualizing Loyalty Dynamics in Search Engines},
journal = {IEEE Transactions on Visualization and Computer Graphics (Proceedings of IEEE VAST 2014},
year = {2014},
volume = {20},
number = {12}
}

The authors sincerely thank Dr. Baining Guo with Microsoft Research Asia for his great support and encouragement for this project. The authors would like to thank Zehua Liu with Microsoft Search Technology Center Asia (STCA) for participating this project as a domain expert and providing valuable and constructive suggestion. The authors thank Amy Guo, Chris Xiao, GG Wu, and Shuang Peng with Microsoft STCA for participating the user evaluation of this project. The authors also wish to thank Aviz group in Inria, France, for their kind help on revising the paper and the anonymous reviewers for their valuable comments.