No abstract

Due to the big data and wide availability of various types of information, data compression plays a significant role in the current age. This task can be done in two aspects. First, it can be done by reducing the redundant features of each entity. Second, it can be employed on each record of the corresponded dataset. These techniques should maintain the crucial and useful information which presents a pivotal role in further process. This work presents an effective knowledge compression for recommender systems based on the attention mechanism. In this method, the data compression is performed in two feature and record levels. The technique is based on time windows and the activity of users. The result of this technique can be efficiently utilized for deep networks which the amount of data is one of the serious problems. The experimental results show that with the help of this technique not only does it reduce the amount of data and process time, but also it can reach acceptable and considerable accuracy in the training and testing phases of networks.

Virtual learning environments have become widespread in today's society to avoid time and space constraints and to share high-quality learning resources. In the process of human-computer interaction, student behaviors are recorded instantly. This article aims to design an educational recommendation system according to the individual's interests in educational resources, which is evaluated based on clicking or downloading the source and the score given to that source by the user. In online tutorials, in addition to the problem of choosing the right source, we face the challenge of how to be aware of diversity in users' preferences and tastes, especially their short-term interests in the near future, at the beginning of a session. We assume that the user's interests consist of two parts: 1) the user's long-term interests, which include the user's constant interests based on the history of the user's dynamic activities, and 2) the user's short-term interests, which indicate the user's current interests. Due to the use of Bilstm networks and their gradual learning feature, the proposed model supports learners' behavioral changes, with an average accuracy of 0.9978 and an error of 0.0051 offers more appropriate recommendations than similar articles.