Analysis on the Influence Path of User Knowledge Withholding in Virtual Academic Community – Based on Structural Equation Method-Artificial Neural Network Model

Abstract

The phenomenon of knowledge withholding is a vital issue that undermines knowledge sharing and innovation, hinders the development of offline and online organizations. Clarifying the relationship between influencing factors and knowledge withholding is significant to improve the phenomenon of knowledge withholding in offline and online organizations. Few types of research focus on the online virtual academic community and integrate the three factors of knowledge, individual, and environment to research knowledge withholding. To solve the limitation, this research is based on sociology and psychology-related theories. The two dimensions of enabling and inhibition are divided into factors affecting knowledge withholding. An attempt is made to explore the path between the three types of factors influencing knowledge, individual and environment, and knowledge withholding. This study collected data from 616 users in China’s virtual academic community. It used a structural equation model combined with a cross-layer connected neural network to conduct an empirical analysis on the proposed hypothesis. The results found that: in the virtual academic community, knowledge power in the enabling dimension is the main reason for users to form knowledge psychological ownership, which affects users’ knowledge withholding. However, the effect of professional commitment on users’ knowledge psychological ownership is not significant. After SEM-ANN model fitting, the combined inhibitory effect of community privacy protection and community reciprocity on user knowledge withholding in the inhibition dimension is significantly improved. This research has a specific guiding significance for enhancing the knowledge withholding phenomenon of the virtual academic community and creating an excellent academic exchange atmosphere.

Navigating Passenger Satisfaction: A Structural Equation Modeling–Artificial Neural Network Approach to Intercity Bus Services

“…The model used in this study contains a hidden layer, with the number of neurons automatically determined by the SPSS software 29. Standardization processing was performed before with the data input, followed by the definition of the training function and parameters [77]. In addition, ten-fold cross-validation was performed throughout the training to prevent overfitting the neural network [38].…”

How question type influences knowledge withholding in social Q&A community

“…Thus, negative emotions may arise when others appropriate this knowledge without proper recognition (Pierce et al, 2003). In social Q&A communities, members provide knowledge with the expectation of reciprocity, but assessing the fairness and value of this exchange can be challenging (Le & Li, 2022). The fear of knowledge exploitation makes members feel a stronger psychological ownership of their knowledge, possibly resulting in territorial behavior and knowledge withholding (Brown et al, 2005; Empson, 2001).…”

Exploring the recycled water acceptance based on the technological perspective of UTAUT2: a hybrid analytical approach

“…Third, this study takes innovative research approaches by employing both SEM and artificial neural network (ANN) analysis. The hybrid analytical approach not only can verify the hypothesized relationships in influencing recycled water acceptance, but also can reveal the importance rank of critical factors with a supplementary and reinforced perspective ( Le and Li, 2022 ). This study aims to offer significant methodological implications which can provide a comprehensive and robust exploration into the underlying mechanism of residents’ acceptance processes toward recycled water.…”