Modeling of Recommendation System Based on Emotional Information and Collaborative Filtering

Construction of self-learning classroom history teaching mode based on human-computer interaction emotion recognition

Due to the continuous epidemic in recent years, the traditional teaching mode of history classroom has been gradually replaced by the teaching mode of self-learning classroom. The teaching mode of autonomous learning classroom has become a popular teaching mode in recent years. However, in the autonomous learning classroom under the current history teaching mode, the lecturer cannot always pay attention to the various states of the students. It is also difficult to understand and receive the information the teacher wants to convey in real time. For this reason, human-computer interaction emotion recognition technology has been proposed and developed. In order to construct and realize the teaching mode of self-learning classroom history, this paper studies the emotion recognition technology of human-computer interaction. The research results show that the introduction of human-computer interaction emotion recognition technology into the construction of autonomous learning classroom teaching mode can fully understand students' emotional behavior. It improves the accuracy of students' emotion recognition by 2.67%, enables students to maintain a good learning motivation, and make reasonable plans and arrangements for the historical time and progress of learning. At the same time, it enhances the history teaching intensity and autonomous learning ability, and improves the original single learning mode. By establishing a new teaching-teacher-student relationship, it creates a good and active autonomous classroom atmosphere.

Integration of Wearable Devices and English Teaching under Positive Psychology

Positive psychology, as a core subject to the study of people's positive power and positive quality, is intended to cultivate positive personality traits and positive emotions, and to promote the development of inspiring creativity, cooperation, and interest. The study of positive psychology provides a new perspective for our research in the field of education. The "New Curriculum Standards for Junior Middle School English" clearly states: "Students can only maintain the inner driving force of English learning and achieve results only if they have positive emotions in English learning. Negative emotions will not only affect the effect of English learning, but also affect students' long-term development. In English teaching, teachers should pay attention to students' emotions from beginning to end, and strive to create a relaxed, democratic, and harmonious teaching atmosphere. Therefore, how to infiltrate the theory of positive psychology into the frontline English teaching of junior high school becomes especially important. With the advancement of science and technology and the advent of the Internet era, various high-tech information technologies have gradually flourished, and the rapid development of information technology has promoted the reform and innovation of the teaching industry. Wearable technology is the current trend and direction of the information technology revolution. It realizes the interconnection and deep integration of people, machines and objects through the functions of collecting, sorting and analyzing mobile Internet and cloud data. The realization of wearable technology-based wearable technology not only can highly integrate educational resources, improve learning interest, but also enhance the pertinence of teaching, cultivate students' creativity, and realize personalized teaching in "full time, all-round, all fields." This article explores the integration of wearable devices and junior high school English teaching in the context of positive psychology. First of all, this paper introduces the theoretical basis of the integration of wearable devices with English teaching. Secondly, it introduces the research methods of this paper. Finally, through questionnaires and experimental comparison analysis, it tests the interest of students in learning through the auxiliary teaching of wearable devices, and whether the academic performance has a positive effect.

Cluster Analysis Algorithm in the Analysis of College Students' Mental Health Education

With the rapid development of curricula, a large number of studies are emerging to assist in the development of curricula. But in an information society, in the face of rapid learning and increased life expectancy, students face the pressure not to forget; the mental health status as a result of our curricula is closely related to our learning. The research and application of the integration algorithm plays an important role in the analysis of the mental health education system. The purpose of this work is to study the application analysis algorithm in the students' context. This work applies the integration analysis algorithm to students' mental health analysis and identifies students' mental health problems using the integration analysis algorithm so that students are well informed and guided. Based on the system engineering method, using the data mining clustering method, a detailed analysis and research on the mental health of college students is done. In this work, a method of student behavior analysis and statistical tools are used to collect mental health data to find common features of different groups of students, in order to better visualize and investigate the mental health of these students on a scientific basis. The results of this study are as follows: a general analysis algorithm application on the analysis of students' mental health education system allows for an effective understanding of scientific data. FCM and FCM algorithms based on the density of information entropy characteristics were used to investigate the effect of mental health factors on the results of the study and the practicality of the algorithm used, which provided an effective method for the prevention of student mental problems. Assisting the school in formulating corresponding new methods of early prevention and intervention of college students' psychological disorders will create a good and healthy atmosphere for college students' study and life. The research results provide a reliable basis for managing and cultivating students.

Enterprise Strategic Management From the Perspective of Business Ecosystem Construction Based on Multimodal Emotion Recognition

Emotion recognition (ER) is an important part of building an intelligent human-computer interaction system and plays an important role in human-computer interaction. Often, people express their feelings through a variety of symbols, such as words and facial expressions. A business ecosystem is an economic community based on interacting organizations and individuals. Over time, they develop their capabilities and roles together and tend to develop themselves in the direction of one or more central enterprises. This paper aims to study a multimodal ER method based on attention mechanism. It analyzes the current emotional state of consumers and the development direction of enterprises through multi-modal ER of human emotions and analysis of market trends, so as to provide the most appropriate response or plan. This paper firstly describes the related methods of multimodal ER and deep learning in detail, and briefly outlines the meaning of enterprise strategy in the business ecosystem. Then, two datasets, CMU-MOSI and CMU-MOSEI, are selected to design the scheme for multimodal ER based on self-attention mechanism. Through the comparative analysis of the accuracy of single-modal and multi-modal ER, the self-attention mechanism is applied in the experiment. The experimental results show that the average recognition accuracy of happy under multimodal ER reaches 91.5%.

Efficient Graph Collaborative Filtering via Contrastive Learning

Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.