- Ondrej Čerman: Personalized recommendation of TV program
- Peter Gašpar: Revealing Information on Social Adaptive Web
- Veronika Gondová: Web services consumer behavior analysis for improving recommendation
- Mário Hunka: Scalable personalized recommendation
- Adrián Huňa: Supporting Online Student Communities by Utilization of Questions and Answers Archives
- Jakub Mačina: Recommendation of New Questions in Online Student Communities
- Tomáš Matlovič: Methods for feedback recommendation in the domain of programming
- Marek Roštár: Personalized recommender with taking into account visual inputs
- Matúš Salát: User segmentation for personalization of newsletters in CQA systems
- Martin Šrank: Improving Diversity and Freshness of Newsletters in CQA Systems
Personalized recommendation of TV program
Ondrej Čerman
master study, supervised by Mária Bieliková
Abstract. This thesis deals with personalized recommendation of live television broadcasting. Because of very high number of TV channels broadcasting high number of television programs, TV viewers have trouble with searching and choosing TV programs to watch. Personalized recommendation should help these people. We are developing appliction for Android smartphones, that shows live television program. This application also collects data from user, which are then later used for personalized recommendation.
Revealing Information on Social Adaptive Web
Peter Gašpar
doctoral study, supervised by Mária Bieliková
Abstract. Information overload on the Web has been a well-known problem in many domains. Recommender systems have been trying to solve this issue by reducing the number of items presented to user, usually in a personalized way. However, a recent expansion of online services and e-commerce websites has created several new problems which we need to tackle with.
In our research we are exploring the domain of recommender systems. There have been many approaches based either on the users’ or items’ similarity. However, these is also a need to take into account many other inputs that can influence user’s preference, e.g. when or where a user is using a system. Moreover, user’s global preferences are not static and may change in time, which raises another problem – understanding the short-term and long-term user profiles. Most recommender systems use ratings as a user input, but in many domains their acquisition is a too complex or even impossible task.
In our work we will propose method, which will improve user experience using recommender system in selected online web service.
Web services consumer behavior analysis for improving recommendation
Veronika Gondová
master study, supervised by Mária Bieliková
Abstract. Web provides the environment for various services. Visitors of these services (consumer of services) use them to find the most appropriate ones. A number of alternatives that are available together with other factors (e.g. time) cause that the customer can not choose the best one. Personalized recommendation based on data from user behavior can reduce this problem. However, the data itself do not have to carry the sufficient information to generate recommendation that follows the interests of user. User model has a major impact on the accuracy of recommendation. Model may include – finding similar users, segmentation of users and also prediction of user behavior in specific situations.
In our work we focus on the analysis of user behavior in services such as e-commerce or e-bank. Our aim is to reveal the key characteristics of user that are important for effective recommendation. It may be personality traits, interests of user, motivation, skills with web navigation and also short-term characteristics such as emotion. Our method will be verified by different types of recommendation.
Scalable personalized recommendation
Mário Hunka
master study, supervised by Michal Kompan
Abstract. Personalized recommendation is inseparable part of the Web today. It relieves us from quantum of information the web offers and improves user experience. High growth of activities done on the Web increases the amount of data generated by users. In result, there are higher requirements on the calculation methods with emphasis on scalability or reusability.
There are services (e.g. Google News, Youtube) millions of visitors on daily basis. They are supposed to respond to different behavior of users and generate recommendation in real-time. There have been presented algorithms based on co-clustering or using some reduce framework to ensure high scalability of system.
In our research, we will analyze recommendation methods from the perspective of their software features. Our goal is to propose a method that will provide higher scalability of system. We will minimalize computational complexity preserving its accuracy. Our method will be tested on large non-trivial stream of data at chosen application domain (e.g. news, education, multimedia).
Supporting Online Student Communities by Utilization of Questions and Answers Archives
Adrián Huňa
master study, supervised by Ivan Srba
Abstract. Community Question Answering (CQA) sites (e.g. StackOverflow, Yahoo! Answers) provide an effective way to get answers for complex or too specific questions that cannot be understood well by search engines. Other users of CQA sites answer these questions by using their own knowledge and experience. During the recent years, CQA sites gained popularity and currently hold valuable knowledge in their archives of questions and answers.
Massive Open Online Courses (MOOC) emerged as an affordable way to access quality education. The courses are often provided by world-class universities and companies. Students are also provided with discussion forums, where they can, for example, get answers to their questions or can use them as a place to clear confusions about course’s material. We can observe similarities between knowledge search in MOOC discussion forums and CQA sites.
In our work, we focus on supporting online student communities in MOOCs by utilization of question retrieval for automatic question answering. We incorporate specifics of educational setting into our matching model between new question and archive of resolved questions. There is one big difference between questions in general CQA systems and MOOCs. CQA systems allow users to search in an archive of resolved questions, while in MOOCs that is not possible. Because of that, questions in MOOCs tend to repeat when a course is being rerun. In our model, we match a new question with questions from the archive by utilizing TF-IDF cosine similarity and also other features, and if a good match for the new question is found, we eliminate the time needed for manual question answering by automatically providing an answer from the archive.
Recommendation of New Questions in Online Student Communities
Jakub Mačina
master study, supervised by Ivan Srba
Abstract. Community question answering (CQA) systems are commonly used on the open Web and in enterprise environments. With an increasing popularity of Massive Open Online Courses (MOOCs) there is an opportunity for the CQA systems to help students in the online learning communities as well. However, existing CQA systems have difficulties with an increasing proportion of questions that remain unanswered.
Our main objective is to provide a more accurate recommendation of new questions (question routing) in educational CQA systems by considering educational-specific features in comparison to the general recommendation approaches. We are going to focus on answerer preferences by routing questions to students based on their expertise and willingness to answer. Many of existing methods tend to overload only few experts by recommending most of questions to them. Our approach routes new questions to the whole community by taking into account students work capacity and knowledge gap of students.
In our work, we propose ensemble classifier which use extracted features from the MOOC course and related CQA system used within the course. We are conducting an online A/B experiment in one of the courses on the EdX platform.
Methods for feedback recommendation in the domain of programming
Tomáš Matlovič
master study, supervised by Jozef Tvarožek
Abstract.Effectiveness of student learning is affected by many factors. Successful finishing of the learning activity (for example solving exercise) depend on actual knowledge, motivation, personal characteristics, actual mood and also on the activity itself – difficulty, assignment formulation, subject. Research challenge is to provide automatic feedback to students while they are solving individual learning exercises. Feedback could be useful especially in clarifying student mistakes and also motivating him. Automatic feedback recommendation is even more difficult in domain of programming where exercise could not be divided into sequence of independent steps.
In our research, we will analyze existing approaches of feedback recommendation in domain of programming. We will propose the method for automatic feedback recommendation in programming exercise. Then we will evaluate our method with software prototype in domain of online programming using the learning systems. We will also evaluate this prototype in the User Experience and Interaction Research Centre lab using eyetrackers.
Personalized recommender with taking into account visual inputs
Marek Roštár
master study, supervised by Michal Kompan
Abstract. Recommender systems are typical example of solution to the problem of overloading user with information. Well done and chosen recommendation will usually reflect on user experience during the interaction with system, which has further influence on commercial aspects of organisation using the recommender system.
Results of these systems are often accompanied with graphical elements such as pictures. These elements and their attributes may in some domain has significant influence on user preferences. Despite this methods used for recommendation nowadays are focused on processing textual content of items it is recommending, or observing and modeling behavioral relationships and interactions between users, while ignoring graphical elements.
Our aim is to propose a method of recommendation which takes into account the influence of graphical elements and analyze its viability.
User segmentation for personalization of newsletters in CQA systems
Matúš Salát
master study, supervised by Ivan Srba
Abstract. CQA systems are a common resource of knowledge sharing and obtaining information. Every day many questions and answers are created. One way how to inform about news in any CQA system is a newsletter. Nevertheless, in the most popular CQA systems (such as Stack Overflow), existing newsletters are not personalized yet and show random generated content for every user. As the result, newsletters are not very popular because their content has no information value for the most of users.
We propose to create user segments that group users with common interests and activity in a CQA system. For each group, we will generate a newsletter containing specific content dependent on group attributes. In addition, we want to modify one or several specific sections of newsletter by means of personalization based on user previous activity. Personalization of newsletter can help with providing the right content to new as well as stable users. We want to evaluate the proposed method on data from the selected existing CQA system.
Improving Diversity and Freshness of Newsletters in CQA Systems
Martin Šrank
master study, supervised by Ivan Srba
Abstract.Newsletters represent a standard way to inform users of online communities about new or interesting content. Their importance is even greater in online communities producing large amount of user-created data, such as CQA systems. Nevertheless, many popular CQA systems, such as Stack Overflow, only offer generic newsletters, which do not take into account users’ interests or diversity of the recommended content.
We plan to analyze existing approaches in personalized content recommendation in CQA systems and design a method for automatic creation of personalized newsletters for individual users. We want to focus on improving the diversity and freshness of the recommended content as a way to prevent filter bubbles. To avoid the problem of a cold start, we propose combining collaborative filtering and content-based filtering approaches when creating a newsletter for low-activity users.