Comparison of Behavior Rate Models Based on Bayesian Belief Network

Aleksandra Toropova, Tatiana Tulupyeva

Результат исследований: Публикации в книгах, отчётах, сборниках, трудах конференцийглава/разделрецензирование

Аннотация

We can use knowledge about human behavior frequency in many fields. There are many problems in sociology, psychology and other sciences studying human behavior where it becomes necessary to predict the behavior frequency. Direct evaluation of frequency is not always executable therefore developing of methods of indirect frequency evaluation is actual problem. The term behavior rate or frequency is determined as the mean number of behavior episodes happened during the particular period. A behavior episode is an activity happened in a certain time. Previously an approach based on Bayesian belief networks and data about last behavior episodes was presented. We suggest an improvement by including in the model a hidden variable representing an interval between the last episode in study period and the next episode, i.e. the first episode occurred after the study period. We compare this and the previous models. For learning and testing the models data are synthesized and collected from Vkontakte, the most popular social Network in Russia. The results can be used in various scientific fields, the subject of which is a human behavior: sociology, psychology, marketing etc.

Язык оригиналаанглийский
Название основной публикацииStudies in Systems, Decision and Control
ИздательSpringer Nature
Страницы510-521
Число страниц12
DOI
СостояниеОпубликовано - 2021

Серия публикаций

НазваниеStudies in Systems, Decision and Control
Том337
ISSN (печатное издание)2198-4182
ISSN (электронное издание)2198-4190

Предметные области Scopus

  • Компьютерные науки (разное)
  • Системотехника
  • Автотракторная техника
  • Социальные науки (разное)
  • Экономика, эконометрия, и финансы (разное)
  • Теория оптимизации
  • Теория принятия решений (разное)

Fingerprint

Подробные сведения о темах исследования «Comparison of Behavior Rate Models Based on Bayesian Belief Network». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать