- Martin Civáň: Visualization of Eye-Tracking Records
- Gabriel Csikmák: Discovery of gaze patterns in navigational tasks on the Web
- Samuel Gedera: Inference of user characteristics based on scanpaths
- Martina Hanáková: Analysis of fake news reader’s view behaviour
- Patrik Hlaváč: Human Behaviour in the Web Navigation
- Michal Hucko: Identification of User Confusion in a Web Application
- Patrik Kovács: Discovery of view patterns in navigational tasks on the Web
- Jakub Kubanyi: Analysis of gaze patterns based on user interaction in navigation tasks
- Vladimír Kuchár: Automatic Text Comprehension Detection
- Michal Melúch: Prediction of Perceived Text Difficulty
- Andrej Nemeček: Support of website usability testing
- Michal Oláh: Comparison of scanpaths
- Márius Rak: Automated User Interface Flaws Detection Based on Eye Movements Analysis
- Lukáš Rešutík: Detection of respecting instruction based on user behavior
- Ľubomír Samotný: Automatic Categorization of Users Based on their Web Navigation
- Andrej Vítek: Probabilistic Models for Analysis of Performed Task based on Eye
- Ján Vnenčák: Generalization of User Characteristics Identification Methods Using Eyetracking
Visualization of Eye-Tracking Records
Abstract: One of the most efficient ways how to do eye-tracking experiment with many participants is to record more people at one session that one by one. However usual eye-tracking recording programs are not optimal for this kind of task. So the UXR infrastructure has been developed to help us with it. Unfortunately, the client nor the server part does not include any visualization tool to take a look at the recorded data.
In our work, we are trying to develop a visualization tool compatible with the data from the UXR infrastructure. One of the considered approaches are to create import module to Ogama. While exploring Ogama, some UX problems were detected and possibly experiment set-up export plugin was considered to be implemented.
Discovery of gaze patterns in navigational tasks on the Web
Abstract: Nowadays, the use of the Web has become an everyday activity of almost every person in the world. Their most popular actions include searching for information, which they complete on so-called web search engines. However, their behavior during interactions with these resources can be affected in several ways. There are various efforts that try to understand, also to describe the behavior of users on the Web at the same time.
One possible way of observing is to use a gaze tracking device to get valuable information about the interaction of users on the Web. For this purpose, eye-tracking methodology can be used, which is increasingly used for such types of observation. The information obtained by this tool allows us to determine different patterns of behavior based on user properties or also based on the situation on the Web.
The aim of this work is to understand the behavior of users when performing navigational tasks on the Web, also to determine how their behavior can be influenced while interacting with the browser. It also aims to suggest a solution for information gaining from user interaction and then perform analysis on a diverse sample of users for this type of solution.
Inference of user characteristics based on scanpaths
Abstract: Filling in questionnaires takes a lot of time to evaluate user characteristics. It has been shown, that i tis possible to determine the values of individual user characteristics on the basis of collected data from eye-tracker. As a result of his eye movements, the values of his individual user characteristics can then be inferred. In a domain like an e-commerce, this knowledge is important, as a graphical interface can be tailored to the user based on these values, which can lead to a reduction in task time.
In our work, we focus on inference of user characteristics, based on data, that is collected by the eye-tracker. There are a lot of work on this issue, but the accuracy of inference of the user characteristics are different, which is caused by different methods in inferring this characteristics. It should be a different user model, where researchers try to combine different features or the algorithm itself, which is based on this mode. In our work, we want to focus on the user model, where, in addition to standard features such as fixation length, fixation number, and more, we want to extend this model with scanpath that could improve accuracy in inference of user characteristic.
Analysis of fake news reader’s view behaviour
Abstract: Since fake news overwhelm the public online space more than ever before and manipulate the minds and opinions of people, it is necessary to understand these messages and know how to detect them. The aim of this work is to reveal the features of fake news by the eye-tracking technique. We want to investigate the behaviour of users when reading true and fake news. Next sentence serves us as a basis: “Everyone wants to read about things that confirm his point of view”.
We decided to prepare an experiment in which we provide the participants with articles that are in line with their opinion and the ones that are in opposite. The articles could be both true and false. The important thing is that participants will have no clue what is the experiment really about.
After the experiment all participants fill in a questionnaire to determine their opinion on selected themes and rate of interest about that themes. The questionnaire also helps us to define which articles are in line with the conviction of the participant and which against it. Afterwards we will verify differences in behaviour of participants from collected data.
Human Behaviour in the Web Navigation
Abstract: I am very curious about the different navigation strategies of skilled and novice users. We selected interesting websites as stimuli, we performed an eye-tracking study with 120 participants and now we are working on explorative analysis among participants. Participant’s gaze is the most investigated feature.
As part of this process, we design questionnaire suitable for representing user web-navigation skill.
Identification of User Confusion in a Web Application
Abstract: Web applications are daily visited by everyone of us. There is variety of users from novice ones to experts. While filling our needs we might be confused, many times. For example, it might be in the situation when we visit the application for the first time, but confusion might also occurred dealing with application we are experienced with, while trying some new feature or after update. These situations might be problematic. In this work we deal with automatic identification of user confusion in web application.
Proposed method works with interaction data from keyboard and mouse. We focus on identification of right moment to display a guide for user. This guide may consists of hints which will explain how to work with certain web application.
We conduct a user study with 60 participants working on 6 tasks at FIRO tour travel agency’s website. Based on the gathered data we trained a machine learning classifier using logistic regression for real time confusion prediction. Reached results show that we are able to predict the confusion in web application using only mouse interaction data.
Discovery of view patterns in navigational tasks on the Web
Abstract: Nowadays a considerable effort is invested into the development of methods aiming to influence the viewing patterns of Web users. It is a challenging task to understand and describe the behavior of Web users. To overcome this problem, we need to assign different patterns of behavior that is specific to user profiles and also to the information presented on web pages. With eye tracking devices we can obtain additional feedback from users about their interaction with the web.
In our work we shall focus on navigational elements of websites. We are going to test the effectiveness of different types of menus on the sample of users. Data from the eye tracker will be used for measuring and evaluating the effectiveness of different types of menus.
We hope that our findings will help the web designers to create more effective menus.
Analysis of gaze patterns based on user interaction in navigation tasks
Abstract: User behaviour is influenced by his skill and familiarity with the environment. Information about user skill can contribute to automatic detection of usability issues. Research of user skill is also conducted in the area of web navigation.
From the user’s gaze, we can learn how a user searches for information and what affects his actions and decisions during the process. From the measured data, different gaze metrics can be obtained, such as the fixations count or the duration of fixations. The gaze can be interpreted as saccadas, which allows us to examine the gaze patterns. User interaction itself can be examined on prepared stimuli. Examples are websites where the user performs web navigation tasks.
The work analyses the possibilities of examining user skills at the level of gaze patterns. We focus on Web navigation skill. We have gaze data from 110 participants. We are working on method of analysing and processing the data collected to extract patterns and then classifying the user’s skill level.
Automatic Text Comprehension Detection
Abstract: Reading is one of the main ways in which information is acquired and understanding of the text being read is essential to gaining new knowledge. The reader’s ability to understand the text is influenced by their knowledge, their current psychological state and the difficulty of the text itself. One of the ways to verify the level of comprehension is to test the reader based on the text. Another possibility is to determine the level of comprehension automatically based on the physiological characteristics of a person that were recorded during reading. It is known that the movement of the eyes while reading with comprehension reflects the thought processes behind the reading process.
This work focuses on the automatic text comprehension detection using eyetracking and natural language processing of texts. The current development of natural language processing allows us to automatically calculate many features based on the text being read that affect its complexity. These text features are directly associated with specific eye movements. The knowledge gained from the analysis was used in designing of our method and selection of interesting eyetracking features, features based on the text itself and their combination. In this moment we are working on preprocessing the data gained in conducted user study and verifying our model.
Prediction of Perceived Text Difficulty
Abstract: Reading of textual content on various kinds of devices has become a substantial part of our everyday life. When evaluating difficulty of these texts, we distinguish between perceived and actual difficulty. There are many ways of estimating the actual text difficulty beforehand, however, when it comes to perceived difficulty, there are almost none. In our work, we propose a way of perceived text difficulty prediction based on psychological traits and gaze data.
We treat this problem as a classification task and propose a solution based on machine learning. In order to maximize the accuracy of our model, we define a combination of advanced ensemble learning methods. To assess the suitability of our solution, we evaluate it on a complex dataset reflecting the real-life reading process. Using the proposed model, we have achieved an overall improvement of several percent over the chosen baseline in most of the measured performance metrics.
Support of website usability testing
Abstract: The usability of websites can be tested by using several tools. In our project we mainly focus on information architecture tests, namely the method of card sorting and tree testing. Both methods can be used to understand how users think of website structure and content. Without user understanding, it is impossible to design good information architecture.
For remote and unmoderated testing, we often loose some valuable data. Existing solutions usually only show the participant’s overall results, but do not show enough data of participant behavior while performing test tasks. Our goal is to properly represent these data.
We focus on the usability of the websites and the methods for testing usability. We analyze existing tools for testing the information architecture. Consequently, our goal is to create a tool that tracks the participant’s complete behavior during card sorting and tree testing and represent the results of these two tests.
Comparison of scanpaths
Abstract: Eye tracking reseach has been applied in many areas, including cognitive psychology, medicine and now it’s often used in exploring user interactions with websites in order to test usability or modeling user’s behavior.
The approaches used in analysis often have different limitations and drawbacks. In many scenarios, it’s not enough to initially pre-process and remove invalid data to get relevant results when comparing scanpaths. This problem could be caused by anomalous scanpaths identified with respect to the analyzed data. Often, significant deviations in data may distort the results of the analysis and therefore it‘s necessary to identify this type of data and analyze its origin.
In our work we focus on the comparison of scanpaths and the identification of anomalous scanpaths. Our main objective is to design and implement a method of comparison of scanpaths in order to identify local anomalous scanpaths. We believe that by combining the previously analyzed approaches, we will achieve relevant results in the proposed approach and successfully verify the proposed method in finding a common scanpath.
Automated User Interface Flaws Detection Based on Eye Movements Analysis
Abstract: The master’s thesis explores aspects of human-computer interaction and user experience (UX). It describes current state of knowledge in field of psychology applicable in the field of UX. The thesis describes methods that are used in practice in field of UX and what possibilities psychology and physiology offers for UX.
Goal of the thesis is to design new method for improving objectivity of work in UX. The method offers possibility to differentiate emotional state and mental workload of user by using electroencephalography (EEG) and applying currently used principles in UX, primarily eye movement analysis. Master’s thesis describes principles, functioning, implementation and possible application of the method. Further it describes design and realization of experiment, its realization, evaluation and evaluation of application of the method.
Detection of respecting instruction based on user behavior
Abstract: Nowadays, intuitive software design is very important. One of the method to assect usability of sofware is usability study. In user studies, it is important that participants follow the instructions defined by the moderator. The form of these instructions is varies and very often instructions has written form. Analysing user’s behaviour during reading instructions can help identifiy participants which not adhered instructions.
We analysed detailed examination of the eye movement behaviorduring reading, the detections methods of adherence of instruction , the cognitive states of the user and the prediction models of eye movement.
The output of our work is a predictive model of instruction compliance using the most predictive eye-tracking metrics.
Automatic Categorization of Users Based on their Web Navigation
Abstract: Web navigation can be researched in several ways. Apparently the most popular is the evaluation of navigation using user experiments. Specialized peripheral devices such as an eye-tracker allow us to get a lot of information in real time about the user. There are also papers about personalizing the web and predicting user properties by observable variables from navigation. Personalization can be helped by knowing the cognitive style of the user, that is, how he thinks and organizes information, which can in turn make him more efficient when navigating the web. However, there are several separations of cognitive styles that focus on different human aspects, such as his or her orientation in space or the way he or she observes situation and organizes information.
In this work, we are predicting the cognitive style of a user based on metrics evaluated from our experiment. Using classification method we can evaluate the cognitive style according to the chosen Wholist-Analyst and Verbal-Imager dimensions based on user’s navigation behavior. Further, we are suggesting positive changes for effective navigation on the web based on individual cognitive styles determined from acquired user data during our experiment.
Probabilistic Models for Analysis of Performed Task based on Eye
Abstract: Gaze and visual patterns of observer while looking on visual stimuli is affected by 3 factors. First factor (bottom-up) is related to visual stimuli and its properties. Second factor (top-down) is related to personal characteristics of observer like task at hand, experience, mood or gender. Third factor is related to characteristics of oculomotor system. As a result of these factors, the observer’s gaze contains a great amount of information about the user as well as about what they are looking at.
Models, which are using information about gaze, are often based only on evaluation of aggregated metrics of gaze, thereby losing temporal information about visual exploration of observer. In this work, we focus on the creation of features by using probabilistic models, which could abstract this information from data. We investigate, which probabilistic model and with what input features has best ability to model data from selected domain and whether the subsequent clustering of created probabilistic models can improve its ability.
Generalization of User Characteristics Identification Methods Using Eyetracking
Abstract: User characteristics can affect the success and effectiveness of performing tasks on the system. Based on the user model, it is possible to customize system to user requirements or target information that might be useful. User characteristics also play a role in system usability testing, where knowledge of these characteristics helps us to reduce distortion of test results.
In our work we deal with the effect of the user personality traits to solving typical tasks in the e-shop using eye-tracking. The aim of our work is to identify features that are related to individual personality traits and then select and design those features that are significant within various online stores. Based on our findings, we want to create a model which will be able to automatically identify user personality trait independently of the page interface.