Petr Saloun

Learn More
The paper is focused on sentiment analysis in Web 2.0 capable systems. The analysed text needs to be in the Slavic languages and Czech language in particular. We have used our experience from both environment, business one (e-shops) and educational one (adaptive web system XAPOS) and the native knowledge of the Czech language in our approach to analysing(More)
This paper presents a proposal of navigation for the user, based on an existing ontology of the domain of the learning course. The navigation scheme of the course stands on interconnection of an ontology with existing learning material by the use of the keywords of the domain. On one side there is the user’s needs and goals and on the other side are(More)
Navigation of a student over learning objects can be solved by using concept space of a domain which contains information about structural and dependency relations between concepts. Every learning object has defined relations to several concepts. Relations which exist in the learning object space also exist in the concept space between the corresponding(More)
Models of behavior mining from logs in adaptive systems are one from many methods how to obtain useful information for personalized navigation. Target of this paper is to describe modified results of full scan algorithm used to creation recommended links to concepts. For creation recommended links is used technique of traversal patterns. Established weights(More)
  • Petr Saloun
  • 2015 IEEE 13th International Scientific…
  • 2015
Mosaic of research, applications and case studies, starting with natural language text processing, automated domain building, sentiment analysis, document similarities, and ending with indication of mental illness based on self-essay analysis, is given in an overview of this extended abstract of the invited paper.