Students interdisciplinary knowledge estimation with analysis of his (Her) behavior in social network: Ontological approach

Mikhail Zakharov, Anatoly Karpenko, Elena Smirnova, Elizaveta Tikhomirova

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The paper considers task of quantitative estimation of the student’s interdisciplinary knowledge. A set of estimation methods based on subject ontology usage formalized as a semantic network is been proposed. The following machine learning types were used: supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, active learning, multi-level learning, multitasking learning. The prototype of a software system that extracts information about the activity of students in social networks and evaluates their interdisciplinary knowledge with the use of these methods is being presented.

Original languageEnglish
Title of host publicationCreativity in Intelligent Technologies and Data Science - 1st Conference, CIT and DS 2015, Proceedings
EditorsAlla Kravets, Maxim Shcherbakov, Marina Kultsova, Olga Shabalina
PublisherSpringer Verlag
Pages593-602
Number of pages10
ISBN (Print)9783319237657
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event1st Conference on Creativity in Intelligent Technologies and Data Science, CIT and DS 2015 - Volgograd, Russian Federation
Duration: 15 Sep 201517 Sep 2015

Publication series

NameCommunications in Computer and Information Science
Volume535
ISSN (Print)1865-0929

Conference

Conference1st Conference on Creativity in Intelligent Technologies and Data Science, CIT and DS 2015
Country/TerritoryRussian Federation
CityVolgograd
Period15/09/1517/09/15

Keywords

  • Interdisciplinary skills
  • Machine learning
  • Ontology
  • Semantic net
  • Social network

Fingerprint

Dive into the research topics of 'Students interdisciplinary knowledge estimation with analysis of his (Her) behavior in social network: Ontological approach'. Together they form a unique fingerprint.

Cite this