Combining eye tracking and pupillary dilation analysis to identify Website Key Objects

Identifying the salient zones from Web interfaces, namely the Website Key Objects, is an essential part of the personalization process that current Web systems perform to increase user engagement. While several techniques have been proposed, most of them are focused on the use of Web usage logs. Only recently has the use of data from users' biological responses emerged as an alternative to enrich the analysis. In this work, a model is proposed to identify Website Key Objects that not only takes into account visual gaze activity, such as fixation time, but also the impact of pupil dilation. Our main hypothesis is that there is a strong relationship in terms of the pupil dynamics and the Web user preferences on a Web page. An empirical study was conducted on a real Website, from which the navigational activity of 23 subjects was captured using an eye tracking device. Results showed that the inclusion of pupillary activity, although not conclusively, allows us to extract a more robust Web Object classification, achieving a 14% increment in the overall accuracy.

[1]  Juan D. Velásquez,et al.  Web Usage Data Pre-processing , 2013 .

[2]  Vasile Palade.  Adaptive Web Sites , 2008 .

[3]  Jure Leskovec,et al.  Automatic Versus Human Navigation in Information Networks , 2012, ICWSM.

[4]  Mahesh Motwani,et al.  Survey of clustering algorithms for MANET , 2009, ArXiv.

[5]  G K Poock,et al.  Information processing vs pupil diameter. , 1973, Perceptual and motor skills.

[6]  Hao Jiang,et al.  User-oriented document summarization through vision-based eye-tracking , 2009, IUI.

[7]  Pablo E. Román,et al.  Cognitive Science forWeb Usage Analysis , 2013 .

[8]  W. S. Peavler,et al.  Pupil size, information overload, and performance differences. , 1974, Psychophysiology.

[9]  J. Polt.  Effect of Threat of Shock on Pupillary Response in a Problem-Solving Situation , 1970, Perceptual and motor skills.

[10]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[11]  Tzung-Pei Hong,et al.  A practical extension of web usage mining with intentional browsing data toward usage , 2009, Expert Syst. Appl..

[12]  S. Sutton,et al.  Pupillary Response at Visual Threshold , 1966, Nature.

[13]  Shriram Krishnamurthi,et al.  Using static analysis for Ajax intrusion detection , 2009, WWW '09.

[14]  Lakhmi C. Jain,et al.  New Trends in Web User Behaviour Analysis , 2013 .

[15]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[16]  Juan D. Velásquez,et al.  Extracting significant Website Key Objects: A Semantic Web mining approach , 2011, Eng. Appl. Artif. Intell..

[17]  J. Beatty.  Task-evoked pupillary responses, processing load, and the structure of processing resources. , 1982 .

[18]  Juan D. Velásquez,et al.  Characterizing Web User Visual Gaze Patterns: A Graph Theory Inspired Approach , 2014, Brain Informatics and Health.

[19]  Juan D. Velásquez Silva.  Improvement of a Methodology for Website Keyobject Identification through the Application of Eye-Tracking Technologies , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[20]  Takehiko Ohno.  EyePrint: support of document browsing with eye gaze trace , 2004, ICMI '04.

[21]  Pablo E. Román,et al.  Advanced Techniques in Web Data Pre-processing and Cleaning , 2010 .

[22]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[23]  J. Beatty,et al.  Pupillary responses in a pitch-discrimination task , 1967 .

[24]  G. C. Gupta.  WEB INTELLIGENCE , 2004 .

[25]  E. Hess,et al.  Pupil Size in Relation to Mental Activity during Simple Problem-Solving , 1964, Science.

[26]  Andreas Dengel,et al.  Attentive documents: Eye tracking as implicit feedback for information retrieval and beyond , 2012, TIIS.

[27]  Juan D. Vel,et al.  Advanced Techniques in Web Intelligence-2 , 2016 .

[28]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[29]  Meredith Ringel Morris,et al.  What do you see when you're surfing?: using eye tracking to predict salient regions of web pages , 2009, CHI.

[30]  Pablo E. Román,et al.  A Web Browsing Cognitive Model , 2012, KES.

[31]  Pablo E. Román,et al.  Cognitive Science for Web Usage Analysis , 2013 .

[32]  Ryen W. White,et al.  Leaving so soon?: understanding and predicting web search abandonment rationales , 2012, CIKM.

[33]  Juan D. Velásquez,et al.  Combining eye-tracking technologies with web usage mining for identifying Website Keyobjects , 2013, Eng. Appl. Artif. Intell..

[34]  Arie van Deursen,et al.  Migrating Multi-page Web Applications to Single-page AJAX Interfaces , 2007, 11th European Conference on Software Maintenance and Reengineering (CSMR'07).

[35]  J D Barlow,et al.  Pupillary Size as an Index of Preference in Political Candidates , 1969, Perceptual and motor skills.

[36]  Pablo E. Román,et al.  A neurology-inspired model of web usage , 2014, Neurocomputing.

[37]  Pablo E. Román,et al.  A cognitive model of the web user , 2012, KES.

[38]  E. Hess,et al.  Pupil Size as Related to Interest Value of Visual Stimuli , 1960, Science.

[39]  Pablo E. Román,et al.  A Dynamic Stochastic Model Applied to the Analysis of the Web User Behavior , 2010 .

[40]  Jure Leskovec,et al.  The last click: why users give up information network navigation , 2014, WSDM.