Autumn 2015-16

Search engine keyword prediction based on user need derived from eye tracking

Date: December 2015
Experiment conductor: Jozef Balun
Supervisor: Eduard Kuric
Short description: In this paper we introduce an improvement to phrase prediction used in search engines. Suggesting phrases is an important role in using search tools. Many researches were focused on improvement of query estimation based on mouse movement and clicking, scrolling and time spent reading the document. However, our method should ensure improvement by predicting queries right away from actuals user’s view so the user could get queries in real time. User’s view can be tracked by a device called Eye tracker, which returns information about eye fixation in real-time. Based on the collected information we can predict user’s intention by our method and suggest queries which result from the context of user’s read material. Queries can by used directly as a suggestion for the next searching of the user in the context of his relation.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Automatic segmentation of a screen recording for scene identification

Date: December 2015
Experiment conductor: Jakub, Benjamin Vrba
Supervisor: Jakub Šimko
Short description: The main problem of analyzing data gained from user experience tests is to identify scenes, which are basically static screens with areas of interest, and map them to eye-tracking data. Nowadays the process of annotating record from experiments is done manually. What means, that researcher has to go through all recorded videos of user activity and try to identify scenes. This could be exhaustive and painful activity, if you consider summative experiments, where the quantity is the central point of focus. We want to propose solution, that will automatically segmentate screen record and identify scenes just from the record. Our basic approach is to implement methods, that are used in identifying cuts in videos. Later we want to further develop methods based on image processing, which will allow us to cover specific cases, that could occur while recording activity of user.
Link to a formal description of the UX experiment: experiment description (In Slovak)

User Experience on the Web

Date: November 2015
Experiment conductor: Veronika Balážová
Supervisor: Róbert Móro
Short description: Nowadays it is important for the websites to be as usable, user-friendly and easily searchable for what the users need as possible. A user interface of a website decides how the users will use the site – whether they will effectively reach their goals, less effectively, or not at all. This may be also related to the fact, what kind of person the user is. In our work we focus on user experience on the Web, especially in the banking domain. In this experiment we want to test usability of the website, mainly its navigation and the main goal is to identify usability issues in the interface and then offer improvements. Also, we want to have basic information about relationship between the number of detected errors and the type of users’ personalities.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Evaluation of user experience by eyetracking and emotions analysis

Date: November 2015
Experiment conductor: Mária Dragúňová
Supervisor: prof. Ing. Mária Bieliková PhD.
Short description: Measuring of the web page target findability is often used to evaluate web page designs usability. Eye tracking provides us several measures, such as time or number of fixations prior to the first fixation on the target. However, people are different and therefore the measured values differ. Our work is based on the natural diversity of human visual search abilities, since visual search is subject of attraction for many psychologists around the world. We will evaluate the participants’ visual search ability not only employing the standard visual search tests, but also by our developed tests, which contain typical icons from the web environment. In this experiment we would like to find out if the tasks in experiment are well understandable and also explore number of fixations on the stimuli in visual search tests with various set sizes.
Link to a formal description of the UX experiment: experiment description (In Slovak)

What can eye tracker reveal about filled electronic questionnaire?

Date: November 2015
Experiment conductor: Matej Války
Supervisor: Alena Kovárová
Short description: Aim of this thesis is to evaluate suitability of an electronic questionnaire using eye tracking technology and analysis of output data. Respondents will fill an electronic questionnaire and a feedback questionnaire. Each element of questionnaire can affect it’s comprehension and congnitive load on the respondent. Thereby, high congnitive load and/or misinterpretation of asked question possibly leads to invalid or incorrect answers, which can distort validity of final data set. We shall look which elements caused higher cognitive load for respondents. These first sessions will serve to familiriaze with faculty provided equipment and it’s capabilities.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Analysis of user activities in web browser

Date: November 2015
Experiment conductor: Miroslav Hurajt
Supervisor: Martin Labaj
Short description: In our thesis, we try to offer an analysis of the work of a group of users by monitoring perspective and areas of interests on the web sites and parts of a web browser. Further, we realize an experiment of analyzing ordinary work while using the web browser by a group of participants representing a programming user group. We have proposed a method to simulate ordinary work in a web browser by this group of users. The experiment will offer a detail view of a closer analysis of behavior in the short-term page revisitation and usage of revisitating mechanisms. The main goal of this sessions is preparation and execution of pilot experiment and acquiantance with the testing environment.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Search engine keyword prediction based on user need derived from eye tracking

Date: December 2015
Experiment conductor: Patrik Januška
Supervisor: Eduard Kuric
Short description: Query represents key part of information retrieval. In this context, query is defined as word or group of words describing or characterizing retrieved information. Biggest problem we face is creation of said query, whose execution results in relevant information and thus retrieval success. Main goal of browser is to provide user with the most relevant information from query result. However, user doesn’t always find resulting information relevant. Recently, a wide variety of studies on information retrieval (IR) have focused on tracking users’ eye movements, and the use of high-performance cameras or eye-trackers has made applying this technique much easier than before. The method we propose in this paper can be regarded as a type of implicit relevance feedback because it estimates a user’s search intent implicitly from data about where the user looked while browsing Web pages.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Pupila dilatation and stress in user studies

Date: November 2015
Experiment conductor: Matej Červenka
Supervisor: Martin Krupa
Short description: Analysis of user testing records consumes much of the study moderator’s time. If we want to find a problem in user interface, it’s necessary to watch whole record of the testing and focus on all its outputs. Forms are one of the most problematic features of the user interface. We assume that problematic forms cause stress, cognitive overload and negative emotion of users. These phenomena are manifested by mydriasis (pupil dilation), which we are able to measure with eye tracker. Our primary metric is pupil size. Alternatively we will monitor emotions (Nodulus Face Reader) and skin conductance (GSR). If we find a correlation between mydriasis and stress that was caused by problematic areas of forms, we will be able to determine time at which the participant had a problem and determine where exactly in the form problematic areas are (by using AOIs). The goal is to develop a tool which determines times of problematic areas and saves moderator’s time which he would spend on finding these areas.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Crowdsourcing supported by condition detection of annotators via eyetracking

Date: November 2015
Experiment conductor: Matej Kucek
Supervisor: Jakub Šimko
Short description: With growing of potential which can crowdsourcing offers more and more is significance to improve process of its data gathering. One of the improvements can be found within lack of feedback from participants. Therefore we try to provide mentioned feedback from users by eyetracking device. This experiment consists of tasks of word sense disambiguation. Participants will be given with set of words. For every word there is a group of sentences containing this word and also a group of options as meanings. Participants will be guided through sentences one by one. From this sentence they should be able to come to conclusion of word sense. Our aim is to show how beneficial can be cooperation of two fields such as crowdsourcing and eyetracking.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Presentation of personalized recommendations via web

Date: November 2015
Experiment conductor: Martin Svrček
Supervisor: Michal Kompan
Short description: The main idea of my diploma thesis is to find a method to explain the recommendations to the user. Therefore our goal is to use explanations as a method for presenting recommendations. In the context of this goal, we need to find not only the best way to explain the recommendations, but also the most pleasant user interface to work with. This experiment will allow us to find out basic information (in the context of the user interface) about the positioning of the objects, amount of information, structure information or even about explanations itself. We prepare different types of designs or different ways how to present these explanations. Our aim is show these designs to users and let them decide which type is best for them. Then we use these suggestions to create the first prototype of the recommendation system with explanations.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Mind-Controlled Application

Date: 20th October 2015
Experiment conductor: Patrik Berger
Supervisor: Róbert Móro
Short description: In this session, we are going to take a look at the Emotiv Epoc device and the API it came with, so we can use it correctly in following part of work. Our goal is to implement successful signal processing and P300 ERP classifying algorithm. Firstly, we want to select the optimal components for our algorithm, to reach high accuracy. During the future sessions, we are going to conduct an experiment in which we want to use EEG Epoc Emotiv device to collect data from participants using P300 speller application. We will use collected data to find out how accurate our algorithm is and furthermore, whether the data from Emotiv Epoc is good enough for detecting ERP like P300. Finally, we will compare accuracy of our algorithm with recent studies in this area and evaluate the results.
Link to a formal description of the UX experiment: experiment description (In Slovak)

Mind-Controlled Applicationn

Date: 20th October 2015
Experiment conductor: Tomáš Matlovič
Supervisor: Róbert Móro
Short description: In this session, we take a look at environment we are going to do experiments in. We try the Emotiv Epoc device so we can use it effectively later on. In the following sessions, we are going to use EEG Epoc Emotiv device to collect data from participants while watching music videos. Music videos are chosen to evoke specific emotions. We use machine learning algorithms and try to classify those emotions. We plan to compare the accuracy of those algorithms and also with the method which comes with the Epoc Emotiv device. At the end, we will evaluate usability of an EEG Epoc device in measuring emotions by comparing its accuracy with FaceReader device.
Link to a formal description of the UX experiment: experiment description (In Slovak)