Analyzing visual scanpaths on the Web using the mean shift procedure and T-pattern detection: a bottom-up approach

ABSTRACT

Scanpaths are mainly analyzed in a top-down approach, with the use of a priori areas of interest (AOI). When comparing scanpaths, different approaches and techniques can be used. Some authors use the Levenshtein distance, combined with a clustering method so as to uncover patterns of visual exploration. More recently, the T-pattern technique has been used to analyze both the temporal and the spatial aspects of the scanpaths. The aim of this study is to explore the feasibility of an analysis of scanpaths based solely on a bottom-up approach, i.e., by defining the AOI based on visual data and then by analyzing them so as to discover scanpaths patterns. In order to do so, two techniques are combined: the mean shift procedure to detect AOI automatically, and the T-pattern techniques developed by Magnusson (2000). This study indicates that this approach is relevant and yields interesting results.

References

1. Drusch, G., Bastien, J. M. C., & Dinet, J. L'exploration visuelle de pages web. In J. Dinet & J. M. C. Bastien (Eds.), L'ergonomie des objets et des environnements physiques et numéériques, Paris: Lavoisier (2011), 219--244.
2. Nielsen, J. F-Shaped Pattern for Reading Web Content. In Jakob Nielsen's Alertbox (2006).
3. West, J.M., Haake A.R., Rozanski E.P. and Karn K. Eyepatterns: Software for Identifying Patterns and Similarities across Fixation Sequences. In Proc. Conf. ETRA, ACM (2006), 149--154.
4. Josephson, S., & Holmes, M. E. Attention to repeated images on the World-Wide Web: Another look at scanpath theory. Behavior Research Methods, Instruments, & Computers, 34 (2002), 4, 539--548.
5. Santella, A., & DeCarlo, D. (2004). Robust Clustering of Eye Movement Recordings for Quantification of Visual Interest. In Proc. Conf. ETRA, ACM (2004), 27--34.
6. Duchowski, A. T., Driver, J., Jolaoso, S., Tan, W., Ramey, B. N., & Robbins, A. Scanpath comparison revisited. In Proc. Conf. ETRA, ACM (2010), 219--226.
7. Jarodzka, H., Holmqvist, K., & Nyströöm, M. (2010). A vector-based, multidimensional scanpath similarity measure. In Proc. Conf. ETRA, ACM (2010), 211--218.
8. Mast, M., & Burmester, M. (2011). Exposing repetitive scanning in eye movement sequences with T-pattern detection. In Proc. Conf. IADIS (2011), 137--145.
9. Aula, A., Majaranta, P., & Rääihä, K.-J. Eye-Tracking Reveals the Personal Styles for Search Result Evaluation. Human-Computer Interaction-INTERACT 2005, 1058--1061.
10. Drusch, G., Bastien, J. M. C., & Dinet, J. From gaze plots to eye fixation patterns using a clustering method based on Hausdorff distances. In Conf. Proc. IHM, ACM (2011).
11. Magnusson, M. S. Discovering hidden time patterns in behavior: T-patterns and their detection. Behavior Research Methods, Instruments, & Computers, 32, 1 (2000), 93--110.
12. Magnusson, M.S. Hidden real-time patterns in intra- and inter-individual behavior: description and detection. European Journal of Psychological Assessment, 12 (1996), 112--123.

Index Terms

• Applied computing

  • Document management and text processing

    • Document preparation

      • Multi / mixed media creation

• Human-centered computing

  • Human computer interaction (HCI)

    • Interaction paradigms

      • Hypertext / hypermedia