Sukru Eraslan

Eye tracking scanpath analysis on web pages: how many users?

The number of users required for usability studies has been a controversial issue over 30 years. Some researchers suggest a certain number of users to be included in these studies. However, they do not focus on eye tracking studies for analysing eye movement sequences of users (i.e., scanpaths) on web pages. We investigate the effects of the number of users on scanpath analysis with our algorithm that was designed for identifying the most commonly followed path by multiple users. Our experimental results suggest that it is possible to approximate the same results with a smaller number of users. The results also suggest that more users are required when they serendipitously browse on web pages in comparison with when they search for specific information or items. We observed that we could achieve 75% similarity to the results of 65 users with 27 users for searching tasks and 34 users for browsing tasks. This study guides researchers to determine the ideal number of users for analysing scanpaths on web pages based on their budget and time.

Scanpath Trend Analysis on Web Pages: Clustering Eye Tracking Scanpaths

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 that the resulting path is so short that it 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) that not only considers 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 for multiple web users in terms of visual elements of a web page. In contrast to existing research, the STA algorithm first analyzes the most visited visual elements in given scanpaths, clusters the scanpaths by arranging 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 (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 cases. Based on the statistical tests, the STA algorithm also generates a trending scanpath that is significantly more similar to the inputted scanpaths compared to other existing work in 10 out of 12 cases. In the remaining cases, the STA algorithm still performs significantly better than some other existing work. This algorithm contributes to behavior analysis research on the web that 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.

Identifying Patterns in Eyetracking Scanpaths in Terms of Visual Elements of Web Pages

Web pages are typically decorated with different kinds of visual elements that help sighted people complete their tasks. Unfortunately, this is not the case for people accessing web pages in constraint environments such as visually disabled or small screen device users. In our previous work, we show that tracking the eye movements of sighted users provide good understanding of how people use these visual elements. We also show that people’s experience in constraint environments can be improved by reengineering web pages by using these visual elements. However, in order to reengineer web pages based on eyetracking, we first need to aggregate, analyse and understand how a group of people’s eyetracking data can be combined to create a common scanpath (namely, eye movement sequence) in terms of visual elements. This paper presents an algorithm that aims to achieve this. This algorithm was developed iteratively and experimentally evaluated with an eyetracking study. This study shows that the proposed algorithm is able to identify patterns in eyetracking scanpaths and it is fairly scalable. This study also shows that this algorithm can be improved by considering different techniques for pre-processing the data, by addressing the drawbacks of using the hierarchical structure and by taking into account the underlying cognitive processes.

Do Web Users with Autism Experience Barriers When Searching for Information Within Web Pages

Elements related to cognitive disability are given lower priority in web accessibility guidelines due to limited understanding of the requirements of neurodiverse web users. Meanwhile, eye tracking has received a lot of interest in the accessibility community as a way to understand user behaviours. In this study, we combine results from information location tasks and eye tracking data to find out whether users with high-functioning autism experience barriers while using the web compared to users without autism. Our results show that such barriers exist and there is higher variance in the scanpaths of the participants with high-functioning autism while searching for the right answer within web pages.

Detecting Autism Based on Eye-Tracking Data from Web Searching Tasks

The ASD diagnosis requires a long, elaborate, and expensive procedure, which is subjective and is currently restricted to behavioural, historical, and parent-report information. In this paper, we present an alternative way for detecting the condition based on the atypical visual-attention patterns of people with autism. We collect gaze data from two different kinds of tasks related to processing of information from web pages: Browsing and Searching. The gaze data is then used to train a machine learning classifier whose aim is to distinguish between participants with autism and a control group of participants without autism. In addition, we explore the effects of the type of the task performed, different approaches to defining the areas of interest, gender, visual complexity of the web pages and whether or not an area of interest contained the correct answer to a searching task. Our best-performing classifier achieved 0.75 classification accuracy for a combination of selected web pages using all gaze features. These preliminary results show that the differences in the way people with autism process web content could be used for the future development of serious games for autism screening. The gaze data, R code, visual stimuli and task descriptions are made freely available for replication purposes.

Trends in Eye Tracking Scanpaths: Segmentation Effect?

Eye tracking has been widely used to investigate user interactions with the Web to improve user experience. In our previous work, we developed an algorithm called Scanpath Trend Analysis (STA) that analyses eye movement sequences (i.e., scanpaths) of multiple users on a web page and identifies their most commonly followed path in terms of the visual elements of the page. These visual elements are mainly the segments of a page generated by automated segmentation approaches. In our previous work, we also showed that the STA algorithm performs better than other existing algorithms in terms of providing the most representative scanpath of users. However, we did not know whether the validity of the algorithm is limited to a particular segmentation approach. In this paper, we investigate the effect of two different segmentation approaches on the STA algorithm. The results suggest that the validity of the algorithm is not affected by the segmentation approach used. Specifically, the resulting scanpath of the STA algorithm is the most representative scanpath of users in comparison with the resulting scanpaths of other existing algorithms regardless of the segmentation approach used.

Understanding Eye Tracking Data for Re-engineering Web Pages

Existing re-engineering, namely transcoding, techniques improved disabled and mobile Web users experience by making Web pages more accessible in constrained environments such as on small screen devices and in audio presentation. However, none of these techniques use eye tracking data to transcode Web pages based on understanding and predicting users experience. The overarching goal is to improve the user experience in such constrained environments by using a novel application of eye tracking technology. Thus, this PhD research project aims to propose an algorithm to identify common scanpaths, which are eye movement sequences, and relating those scanpaths to elements of Web pages. It can then be used to transcode Web pages, for instance, unnecessary information can be removed. It is obvious that both visually disabled and mobile users would benefit from such development.

Engineering web-based interactive systems: trend analysis in eye tracking scanpaths with a tolerance

Web-based interactive systems can be verified and validated with eye tracking which provides valuable insights for understanding user interactions. However, individual eye movements (scanpaths) tend to be complicated and different from each other. Existing algorithms focus on clustering multiple scanpaths into a single representative path, but do not tolerate differences. This may result in excluding some popular elements from the resulting path and the representativeness of the path can decrease. Scanpath Trend Analysis (STA) is one of these algorithms which is being increasingly used. It can be used for identifying trending areas of interest (AoIs) on a web page among multiple users and discovering their trending path in terms of these AoIs. Compared to the outputs of other algorithms, the output of the STA algorithm is the most representative. Since this algorithm considers all given scanpaths while discovering their trending path, it can be negatively affected when the variance is high between the scanpaths. In this paper, we introduce a new parameter to the STA algorithm, called tolerance level. This parameter makes the algorithm more tolerant by allowing the identification of trending AoIs based on a subset of given scanpaths instead of all of them. Our study shows that the STA algorithm can achieve more representative path with a tolerance. Thus, the validity and verification of interactive systems can be investigated with more representative path.

Anlaysis of algorithms to identify patterns in eye-tracking scanpaths

The main goal of this study is to develop an algorithm to identify a common scanpath in a given eye-tracking data. This paper provides a set of guidelines on how to develop such an algorithm. To develop these guidelines, we have conducted experiments with existing algorithms and investigated their strengths and weaknesses. The main purpose of creating a common scanpath is to guide the transcoding of web pages. Transcoded web pages would remove unnecessary information such that when they are accessed in constrained environments, for instance from mobile devices and screen readers, they save time and energy to users.