DIGITAL FOOTPRINT OF THE STUDENT: SEARCH, ANALYSIS, INTERPRETATION

The study of the digital human footprint allows you to simulate its characteristic physiological, psychological and cognitive characteristics and the application of such a model for predicting, programming and managing the desired quality of life. Prospects opening for the analysis of digital data about a person can and should be used in education to solve problems of individualization. Standard MOODLE tools for monitoring the activity and effectiveness of students’ training do not allow individual measurements for each student through all disciplines and in dynamics. To accomplish this task, the TSU has developed additional monitoring tools to collect, store and interpret the following data. The ratio of the types of student learning activities in the training course and the comparison of these values with the averages in the student group allow to determine the individual style of instruction and use this data for adaptive setting of the environment or correction of teaching methods. The frequency and rhythm of activities make it possible to assess the regularity of learning activity, the ability to self-organize. Current assessments of the disciplines in LMS allow to identify: “strong” students ready to go beyond the curriculum for in-depth study of the discipline in the MOOK; “Weak” students, with a high probability of academic debt at the end of the current semester; students who showed a high level of intellectual development and personal motivation, requiring individual planning of the educational trajectory. Authors texts uploaded to the LMS when writing essays and communication in the training forum can be analyzed and interpreted by psycholinguistics methods to monitor the emotional state, identify the personality type and the rudiments of soft skills, the development of which is aimed at the target model of the graduate of the university. To personal electronic environments, accumulating data on people, are primarily popular social networks. As the research shows, the university can identify most of its students in social networks and supplement information from institutional systems. In TSU, a comprehensive study is carried out to study the potential of the social network Vkontakte for individualizing student learning. Checking the algorithms of linguistic analysis of texts on the user’s wall showed the possibility of assuming a profile of student interests. An analysis of the subject matter of communities subscribed to by users also allows you to see a map of their educational interests. The first successful results on the use of machine learning algorithms for predicting the manifestation of attributes of giftedness on the basis of data from a human profile are obtained.

Keywords

Authors

References