Michal Hucko

Since emotion detection mostly employs supervised machine learning, big labeled datasets are needed to train accurate detectors. Currently, there is a lack of the open datasets, especially in the domain of confusion detection on the web. In this paper, we introduce a confusion detection dataset comprising of two modalities - the mouse movements and the eye movements of the users. The dataset was gathered during a quantitative controlled user study with 60 participants. We chose a travel agency… Show more

Since emotion detection mostly employs supervised machine learning, big labeled datasets are needed to train accurate detectors. Currently, there is a lack of the open datasets, especially in the domain of confusion detection on the web. In this paper, we introduce a confusion detection dataset comprising of two modalities - the mouse movements and the eye movements of the users. The dataset was gathered during a quantitative controlled user study with 60 participants. We chose a travel agency web application for the study, where we carefully designed six tasks reflecting the common behavior and the problems of the day-to-day users. In the paper, we also discuss the issue of labeling emotional data during the study and provide exploratory analysis of the dataset and insights into the confused users' behavior. Show less

Onboarding of new employees is a common process in all companies. Many hours of qualified employees’ time need to be invested to teach new employees how to use the company’s internal systems. This process can be significantly eased by onboarding solutions leveraging application guides. However, if not personalized, the guides can quickly become annoying to users. This can be overcome by employing emotion detection in real-time, but the solutions face several major challenges, such as… Show more

Onboarding of new employees is a common process in all companies. Many hours of qualified employees’ time need to be invested to teach new employees how to use the company’s internal systems. This process can be significantly eased by onboarding solutions leveraging application guides. However, if not personalized, the guides can quickly become annoying to users. This can be overcome by employing emotion detection in real-time, but the solutions face several major challenges, such as scalability, detection time, or model retraining. In this paper, we describe how we tackled these challenges and implemented an emotion detection-based personalization module in the onboarding solution YesElf. The module leverages the mouse interaction data of users to detect their confusion. We show the scalability of our solution in the production environment which has been deployed to three customers with more than 200 concurrent users. Show less

Onboarding users to a complex application or a new functionality can be a serious issue, especially for organizations that need to train their new employees. Using a complex application without proper training or guidance can lead to users' confusion and frustration. In this paper, we introduce the onboarding platform YesElf intended for web applications. Its approach to onboarding is to use embedded guides within the application; its novelty lies in the robustness, ease of setup and… Show more

Onboarding users to a complex application or a new functionality can be a serious issue, especially for organizations that need to train their new employees. Using a complex application without proper training or guidance can lead to users' confusion and frustration. In this paper, we introduce the onboarding platform YesElf intended for web applications. Its approach to onboarding is to use embedded guides within the application; its novelty lies in the robustness, ease of setup and integration of the YesElf guides into any web-based application. Most importantly, YesElf supports personalized adaptation of user guidance. This, we demonstrate by a novel method for automated recognition of user's confusion in real time that we integrated into YesElf. The information on user's confusion serves as a basis for adaptive display of the guides, when they are needed the most. We evaluated the proposed method on the data collected in a user study with 60 participants and achieved 63% precision which outperforms the state-of-the-art classifier based on the eye tracking data (although, in our case, we used the more readily available mouse movement data). Show less

By operating at a very detailed level, unit tests are very susceptible to changes in production code. Writing unit tests in aspect-oriented programming can help with their maintainability. However, the existing approaches do not take into account so-called pointcut fragility: a failure to address the intended join points due to small changes in the base code. An approach to increasing unit test resilience to changes in production code by decreasing pointcut fragility is proposed in this paper… Show more

By operating at a very detailed level, unit tests are very susceptible to changes in production code. Writing unit tests in aspect-oriented programming can help with their maintainability. However, the existing approaches do not take into account so-called pointcut fragility: a failure to address the intended join points due to small changes in the base code. An approach to increasing unit test resilience to changes in production code by decreasing pointcut fragility is proposed in this paper. The approach is implemented in AspectJ with JUnit used as a test oracle. The approach has been evaluated on several scenarios encompassing typical code modification that render unusable the tests writ- ten in a simple object-oriented way. The approach proposed in this paper managed to make the test resilient to the most of the changes introduced by these scenarios. Show less

We aim to improve the communication process of a teacher with students during lectures using question answering. Our work is focused on the analysis of students' answers to support the teacher in his lecturing. We work with students' answers to open questions, where it is impossible to identify finite number of solutions. In large classes it is impossible to react in real time to such answers since their evaluation is time consuming. We propose our own approach that helps the teacher by… Show more

We aim to improve the communication process of a teacher with students during lectures using question answering. Our work is focused on the analysis of students' answers to support the teacher in his lecturing. We work with students' answers to open questions, where it is impossible to identify finite number of solutions. In large classes it is impossible to react in real time to such answers since their evaluation is time consuming. We propose our own approach that helps the teacher by grouping similar answers. These groups are created based on proposed method employing text classification and clustering. Proposed method automatically estimates a number of clusters in answers using combination of k-Nearest Neighbors (KNN) algorithm and affinity propagation. We evaluated the method on real data in Slovak language collected from the course Principles of Software Engineering using real time presentation system ASO. Show less