Scanpath Trend Analysis on Web Pages

Abstract

Eye tracking studies have widely been used in improving the design and usability of web pages, and in the research of understanding how users navigate them. However, there is limited research in clustering users' eye movement sequences (i.e., scanpaths) on web pages to identify a general direction they follow. Existing research tends to be reductionist which means the resulting path is so short that is not useful. Moreover, there is little work on correlating users' scanpaths with visual elements of web pages and the underlying source code which means the result cannot be used for further processing. In order to address these limitations, we introduce a new concept in clustering scanpaths called Scanpath Trend Analysis (STA) which does not only consider the visual elements visited by all users, but also considers the visual elements visited by the majority in any order. We present an algorithm which automatically does this trend analysis to identify a trending scanpath of multiple web users in terms of visual elements of a web page. In contrast to existing research, the STA algorithm first analyses mostly visited visual elements in given scanpaths, then clusters the scanpaths by using these visual elements based on their overall positions in the individual scanpaths, and then constructs a trending scanpath in terms of these visual elements. This algorithm was experimentally evaluated by an eye tracking study on six web pages for two different kinds of tasks, and therefore 12 cases in total. Our experimental results show that the STA algorithm generates a trending scanpath that addresses the reductionist problem of existing work by preventing the loss of commonly visited visual elements for all the cases. Based on the statistical tests, the STA algorithm also generates a trending scanpath which is significantly more similar to the inputted scanpaths compared to other existing work in 10 out of 12 cases. In the rest of the cases, the STA algorithm still performs significantly better than some of other existing work. This algorithm contributes to behaviour analysis research on the web which can be used for different purposes, for example re-engineering web pages guided by the trending scanpath to improve users' experience or guiding designers to improve their design.

Trends in Eye Tracking Scanpaths

“…To address this limitation, in our previous work, we developed an algorithm called STA (Scanpath Trend Analysis) to analyse multiple scanpaths on a particular page and identify the most commonly followed path in terms of the visual elements of the page. The STA algorithm is briefly introduced in the following section and detailed description can be found in [10].…”

“…We have already evaluated the STA algorithm by using an eye tracking study [10]. In the evaluation, we used the extended and improved version of the VIPS approach to segment the web pages into their visual elements [2].…”

“…The methodology used in this study was previously used in our another eye tracking study [8,7,10]. The details of the complete methodology can be found in [8,7,10].…”

“…For example, if a web page is transcoded for a particular user, it may not be suitable for another user as their interests may not be the same. In our previous work, we developed an algorithm called Scanpath Trend Analysis (STA) that analyses multiple scanpaths on a particular web page and identifies the most commonly followed path in terms of the visual elements of the page (Section 3) [10]. The resulting scanpath is called a trending scanpath.…”

“…In our previous work, we also evaluated the STA algorithm by using an eye tracking study and our evaluation showed that the STA algorithm performs better than other existing algorithms in terms of providing the most representative scanpath of users (Section 3) [10]. The degree of representativeness was measured by the sequential similarities between the individual scanpaths and the resulting scanpath.…”