Перегляд за Автор "Leshchynska, Irina"
Зараз показуємо 1 - 2 з 2
Результатів на сторінці
Налаштування сортування
Документ Designing explanations in the recommender systems based on the principle of a black box(Національний технічний університет "Харківський політехнічний інститут", 2019) Chalyi, Serhii; Leshchynskyi, Volodymyr; Leshchynska, IrinaThe subject matter of the article is the process of designing of explanations in the recommender system. The goalis to develop a conceptual model for designing explanations in recommender systems based on the black box principle. Such a model binds the conditions, the result and the constraints on the choice of objects from the user's position.The user should receive justification of the recommendations taking into account context-oriented possibilities of using the proposed objects.Tasks: to adapt the principle of a black box to the task of constructing explanations in the recommender system; to develop a conceptual scheme for constructing explanations according to the functional principle; to develop a conceptual model for the designing of explanations based on the principle of a black box.The principle used is: functional, or the principle of a black box.The following resultsare obtained. The principle of the black box to the problem of constructing explanations in the recommender system was adapted. The conceptual scheme of constructing explanations on the basis of a functional principle is developed, taking into account both the properties of objects and the sequences of their use. The conceptual model of the explanation based on the black boxprinciple is developed.Conclusions.Scientific novelty of the results is as follows.The conceptual model for constructing explanations with recommendations on the functional principle or the principle of a black box is proposed. The model takes into account the characteristics of subjects and consumers, information on the use of objects in the subjectarea, as well as recommendations in the form of a list of objects.The advantage of using the proposed model lies in the fact that it takes into account the methods of applying the recommended objects for constructing explanations. This creates conditions for personalizing recommendations in cases of a cold start of the recommender system, as well as artificial increase in the ratings of individual items.Документ Multilevel personalization of explanations in recommender systems(Національний технічний університет "Харківський політехнічний інститут", 2020) Chalyi, Serhii; Leshchynskyi, Volodymyr; Leshchynska, IrinaThe scientific novelty of the results is as follows. A formal description of the explanations of the recommended personal list of objects in the form of a hierarchy of levels of data, information, knowledge and meta-knowledge about user behavior and characteristics of objects is proposed. At the data level, a description of the variables and their values is given, taking into account the instant of occurrence of these values. Information at the next level is represented by the relationships between individual facts. Knowledge is represented by causal or temporal explanatory rules that generalize the relationship of the informat ion level to a subset of facts. Meta-knowledge sets the key patterns that determine the benefits and relevance of the proposed choice for the user of the recommendation system. In a practical aspect, the proposed formalization of explanations determines the typical sequence of constructing and personalizing multilevel explanations regarding recommendations, taking into account the characteristics of the subject area.