The main goal of this research is to identify some notable trends, opportunities and limitations regarding the application of social media in higher education based on studying the way students use social media during their education. The re-search is focused on the impact of social media on the process of learning, creation and distribution of education related content, as well as on education related communication. The target groups of the research are students in University of Economics Varna enrolled in different bachelor and master programs. An association analysis was implemented to identify the most common pat-terns regarding the application of social media in the education process. Statistical methods for testing hypothesis were used to assess the relationship between students’ specialty and derived social media patterns. The findings show that Facebook groups are а preferable social media tool for communication with colleagues, content sharing and distribution, while wikis and university Learning Management Systems (LMSs) are most used for content creation and additional learning. Some social media channels are more preferable for content creation and additional learning compared to scientific databases and e-books. Following the research results a conclusion can be drawn regarding the leading part of the students in initiating the use of social media compared to the relatively smaller role of the academic staff in this process. A medium to small relationships were discovered between students’ specialty and the application of con-tent sharing communities and forums in knowledge process with students in computer science more likely to use these social media types compared to students in economics.

The purpose of this research is to evaluate several popular machine learning algorithms for credit scoring for peer to peer lending. The dataset to fit the models is extracted from the official site of Lending Club. Several models have been implemented, including single classifiers (logistic regression, decision tree, multilayer perceptron), homogeneous ensembles (XGBoost, GBM, Random Forest) and heterogeneous ensemble classifiers like Stacked Ensembles. Results show that ensemble classifiers outperform single ones with Stacked Ensemble and XGBoost being the leaders.

Social media have enormous power and trigger changes in whole spectrum of businesses, as well as learning and education. A study of students’ adoption of social media at the University of Economics – Varna (UE-Varna), Bulgaria, has proven its significant impact on young people. Using online questionnaire among 378 students, the high popularity of social media has been confirmed. An important research question is whether higher education institutions teaching students mainly in the fields of social, economic and legal sciences use the benefits of the social media in the context of Learning Management Systems (LMSs) and integrated social media tools. The majority of the examined 24 universities use two LMSs - Moodle and Blackboard Learn. Both possess tools like forums, chat, wikis, internal messaging, blogs, learning groups, collaboration tools. The study of the two Moodle platforms implemented at the UE-Varna shows use of discussion forums, chat, and internal messaging.

No abstract

No abstract