This Research Topic has been discontinued.

Frontiers Media SA

Frontiers in Psychology

Organizational Psychology

Frontiers in Communication

Online Product Decision Analysis Based on Multi-Modal Emotion Information

This article examines the role of artificial intelligence (AI) models in the cognitive and learning activities of subjects in higher education institutions. The authors design this model using algorithms-sets of rules that enable programs to make decisions, recognize patterns, and generate predictions based on input data relevant to the learning and cognitive processes of university subjects. The aim of the study is to develop computer-based prototypes that simulate the processes of solving intellectual problems. These simulations help to deepen the understanding of such processes and to extract maximum information for future professional development and the construction of intelligent systems. Another key objective of artificial intelligence is to facilitate the execution of tasks characterized by a large number of variables, high complexity, and low suitability manually is systematized. The novelty of the study suggests in the personalization of the educational process for the learner, the application of adaptive cognitive learning strategies, and the incorporation of intelligent feedback mechanisms. The proposed model stands out from others due to the inclusion of components such as machine learning, intelligent tutoring systems, automated assessment systems, and large-scale data analysis. The article shows the possibilities of using AI to enhance engagement of students in forecasting their academic success and optimizing administrative processes. It also substantiates the need for the responsible use of AI in educational platforms, the development of integration strategies, and the assurance of fair access to resources.

Artificial Intelligence Model in the Cognitive and Learning Activities of University Subjects

Ecosystem multifunctionality (EMF) refers to the integrated capacity of an ecosystems to provide a variety of services and functions. It plays a crucial role in maintaining ecological balance and achieving sustainable grassland development. Grassland type is a classification unit based on dominant species within the grassland ecosystem. However, the response of EMF to grassland type is still unclear, and its influencing factors need to be studied in depth. This study aimed to investigate the distribution characteristics of EMF in the Longzhong Loess Plateau temperate desert under different grassland types (Kalidium foliatum type, Reaumuria songarica type, Salsola passerinum type, and Sympegma regelii type grasslands) and to identify the key factors driving changes in EMF. The results indicated the K. foliatum type grassland exhibited higher EMF and belowground ecosystem multifunctionality (BEMF) indices (0.80 and 0.77, respectively), significantly greater compared to R. soongorica type, S. passerine type, and S. regelii type grasslands (P < 0.05). EMF and BEMF were significantly correlated with plant factors (coverage, root-shoot ratio), soil factors (mean weight 2 diameter, MWD and geometric mean diameter, GMD) (P < 0.05), and showed strong positive relationships with Shannon diversity index. Hierarchical partitioning further indicated that MWD and GMD explained 29.86% and 38.21% of the variance in EMF, respectively. Structural equation modeling revealed that soil factors (MWD, GMD), plant factors (coverage, root-shoot ratio), and Simpson diversity index collectively explained 86% of the variation in EMF. Soil factors primarily exerted direct effects and indirectly promoted EMF by enhancing plant factors, with a total effect of 0.921. These findings suggest that K. foliatum type grassland can maintain EMF through soil factors, thereby supporting the sustainable development of temperate desert ecosystems in the Longzhong region of the Loess Plateau.