Registration Number
0218U000674,
0117U000575
, R & D reports
Title
Fuzzy logic and computational linguistics based the identification of hidden dependencies in online social networks
popup.stage_title
Head
Shtovba Serhiy Dmytrovych,
Registration Date
08-02-2018
Organization
Vinnitsa National Technical University
popup.description2
Object of the research is the information processes in online social networks. The goal of the research is creating an information technology for the identification of hidden dependencies in online social networks based on fuzzy logic and computation linguistics the principles. Research methods are system approach, mathematical modeling, fuzzy sets theory, theory of identification, computational linguistics. The method for calculation of social network actor profile features is developed. The method differs from other in the mutual usage of the principles of fuzzy logic and computational linguistics. The method allows use both expert knowledge in this subject area and noised informational messages by actors. The method allows obtaining the relevant quantitative and linguistic assessments of various actor features. The method is taking into account as the traditional time-performance figures of the user activity and network connectivity attributes as well as more complex features. The method is taking into account as the traditional time-performance figures of the user activity and network connectivity attributes as well as more complex features. Two new features reflect difference between the current actor behavior and the typical one, which was predicted by the past observations. The 4-step identification of meaningful lexemes and other signs of words with the correction of their morphemes is proposed for obtaining general linguistic figures of the actor. It provides the correct balance between complexity and completeness of the list of candidate words A new method for classifying of social network actors is proposed. The originality of the method consists of usage the fuzzy multi-label classification approach. It provides the robustness of collective decision making in noised features of the actor. The classification is based on the frequency of keywords in the corpus of pre-labeled and categorized texts. Also the censoring of the category list and aggregation the membership of various keywords for the same categories is carried out. The results of the project are used in lecture courses at Faculty of Computer Systems and Automation of Vinnytsia National Technical University. The results are used during the master's and bachelor's theses producing also.
Product Description
popup.authors
Бісікало Олег Володимирович
Козачко Олексій Миколайович
Кривогубченко Сергій Григорович
Кулаков Павло Ігорович
Лісовенко Анна Ігорівна
Петричко Микола Володимирович
Ракитянська Ганна Борисівна
Тилець Роман Олексійович
Штовба Олена Валеріївна
Штовба Сергій Дмитрович
popup.nrat_date
2020-04-02
