PREDICTION IN INTELLECTUAL ASSISTANT SYSTEMS BASED ON FISH SCHOOL SEARCH ALGORITHM
Abstract
The work is related to solving the problem of personalizing Internet resources in order to increase the efficiency of organization and maintenance of psychologically safe user behavior in the Internet space. This problem is of particular relevance for the field of online education in the context of the continuous growth of the number of educational Internet resources and services, the development of content, which has a victimic effect on the moral and ethical aspects of the stu-dent's personality. Among the most promising approaches to its solution, currently stands out an approach that is based on predicting user preferences for generating content that meets their in-terests and expectations. In order to efficiently extract and process data, as well as to identify patterns that allow conclusions (predictions) to be made about specific user preferences, data mining and machine learning methods are used. The article proposes a method for predicting the preferences of the subject of training in intelligent assistant systems for generating recommenda-tions and personalizing educational content and services. The principal difference of the proposed method is the transition from personal recommendations to group based on methods of collabora-tive filtering of users with similar preferences. To formulate recommendations, a preference eval-uation model has been developed, based on the combined use of Item-Item CF and User-User CF methods, which will solve the cold start problem and improve the quality of recommendations for users with similar interests and behavior characteristics. Evaluation of forecasting is associated with a large dimension of the parameters of the learning model. To reduce the dimension of the search space preferences from a large amount of implicit data about user activity and improve the accuracy of the forecast, a bioinspired fish school search algorithm has been developed that is distinguished by scalability and the ability to process sparse data. Experimental studies of the efficiency of the algorithm were carried out on MovieLens test data and confirmed the high gener-alizing ability and accuracy of forecasting preferences.
References
2. Tingting Z., Chen L.Y., Liang-Hsien T. Understanding user motivation for evaluating online content: a self-determination theory perspective // Behaviour and Information Technology. – 2015. – No. 34. – P. 479-491.
3. Wilson P.M., Mack D.E., Grattan K.P. Understanding motivation for exercise: A self-determination theory perspective // Canadian Psychology. – 2008. – No. 49. – P. 250-256.
4. Lin H.F. Examining of cognitive absorption influencing the intention to use a virtual commu-nity // Behaviour and Information Technology. – 2009. – No. 28 (5). – P. 421-431.
5. Войскунский А., Евдокименко А., Федунина Н. Сетевая и реальная идентичность: сравни-тельное исследование // Психология. Журнал Вышей школы экономики. – 2013. – Т. 10, № 2. – P. 98-121.
6. Родзин С.И., Родзина Л.С. M-learning - управление контентом в контекстно-зависимой мобильной системе обучения // Информатика, вычислительная техника и инженерное образование. – 2014. – № 1 (16). – С. 53-61.
7. Кравченко Ю.А. Задачи семантического поиска, классификации, структуризации и инте-грации информации в контексте проблем управления знаниями // Известия ЮФУ. Тех-нические науки. – 2016. – № 7 (180). – С. 5-18.
8. Курейчик В.М., Картиев С.Б. Выбор алгоритма прогнозирования для разработки аналитиче-ского программного обеспечения // Инженерный вестник Дона. – 2017. – № 4 (47). – С. 128.
9. Guo G., Zhang J., Thalmann D. Merging trust in collaborative filtering to alleviate data sparsity and cold start // Knowledge-Based Systems. – 2014. – No. 57. – P. 57-68.
10. Kartiev S.B., Kureychick V.M. Algorithm for building recommendations for intelligent systems // Advances in Intelligent Systems and Computing. – 2018. – Vol. 680. – P. 76-83.
11. Su Z., Yan J., Ling., Che H. Research on personalized recommendation algorithm based on ontological user interest model // Journal of Computational Information Systems. – 2012. – No. 8 (1). – P. 169-181.
12. Кулиев Э.В., Лежебоков А.А., Лещанов Д.В., Шкаленко Б.И. Механизмы роевого интел-лекта и эволюционной адаптации на основе виртуального набора популяций для реше-ния задач управления проблемно-ориентированными знаниями // Информатика, вычис-лительная техника и инженерное образование. – 2017. – № 1 (29). – С. 34-45.
13. Wedyan S. Review and Comparison of Associative Classification Data Mining Approaches // International Journal of Computer, Information, Systems and Control Engineering. – 2014. – No. 8. – P. 34-45.
14. Логинов О.А., Лежебоков А.А., Бова В.В., Щеглов С.Н. Интеллектуальный анализ дан-ных на основе биоинспирированного подхода // Информатизация и связь. – 2018. – № 4. – С. 67-70.
15. Pan W., Ming Z. Collaborative Recommendation with Multiclass Preference Context // IEEE Intelligent Systems. – 2016. – No. 32 (2). – P. 45-51.
16. Курейчик В.М., Каланчук С.А. Обзор и состояние проблемы роевых методов оптимиза-ции // Информатика, вычислительная техника и инженерное образование. – 2016. – № 1 (25). – С. 1-13.
17. Monteiro R. P., Verçosa L. F. V., Bastos-Filho C. J. A. Improving the Performance of the Fish School Search Algorithm // International Journal of Swarm Intelligence Research (IJSIR). – 2018. – № 9 (4). – P. 21-46.
18. Bastos-Filho C.J.A., Lima-Neto F.B., Lins Sousa M.F.C., Pontes M.R. On the influence of the swimming operators in the fish school search algorithm // IEEE International Conference on Systems Man and Cybernetics. – 2009. – P. 5012-5017.
19. Lima Neto F.B.D., Lacerda M.G. Weight based fish school search // IEEE International Con-ference Systems, Man and Cybernetics (SMC). – 2014. – P. 270-277.
20. Частикова В.А., Дружинина М.А., Кекало А.С. Исследование эффективности алгоритма поиска косяком рыб в задаче глобальной оптимизации // Современные проблемы науки и образования. – 2014. – № 4. – URL: http://science-education.ru/ru/article/view?id=14142 (дата обращения: 04.06.2019).
