Purpose With the widespread use of the Internet and mobile phone, cyberbullying has become a new type of bullying among adolescents. It is of great practical significance to explore the relevant factors affecting cyberbullying for prevention and intervention of adolescents’ cyberbullying. However, few studies have considered the effect of both the family and social factors on cyberbullying. Therefore, the current study examines whether the parent-adolescent conflict as a family factor and deviant peer affiliation as a social factor have an effect on adolescents’ cyberbullying, as well as the role of moral disengagement and gender. Methods A total of 777 middle school students (females = 336; mean age = 13.57; SD = 0.98) were surveyed by using the Parent-child Relationship Questionnaire, Deviant Peer Affiliation Questionnaire, Moral Disengagement Questionnaire and Cyber Bullying Behavior Questionnaire. SPSS21.0 was used to conduct descriptive statistics, Pearson correlation analysis and T -test, PROCESS were used to conduct significance test of moderated mediation effect on the data. Results Parent-adolescent conflict does not directly predict cyberbullying. Moral disengagement played a complete mediating role between parent-adolescent conflict and cyberbullying, and gender played a moderating role between moral disengagement and cyberbullying. Deviant peer affiliation directly predict cyberbullying. Moral disengagement played a partially mediating role between parent-adolescent conflict and cyberbullying, and gender played a moderating role between moral disengagement and cyberbullying. Conclusion Attention should be paid to the effect of moral disengagement on cyberbullying in family and social factors, as well as the role of gender.

Adolescence is a high‐risk age for exposure to violent media (EVM) and bullying. Some previous theories and empirical studies have highlighted a moderated mediating model that normative beliefs about aggression (NBA) as a mediator and self‐control (SC) as a moderator for the link between EVM and aggressive behaviors (including bullying behaviors). However, most previous studies analyzed traditional bullying (TB) and cyberbullying (CB) separately, which is not conducive to finding the differences between the two bullying behaviors. Therefore, this study aims to compare the differences between risk prediction models of TB and CB among adolescents. A total of 777 Chinese adolescent students (336 girls; Mage = 13.57 ± 0.98) completed questionnaires including EVM, NBA, TB, CB, and SC. The results showed that: (1) EVM was positively related to adolescent TB/CB; (2) NBA mediated the above relations; and (3) SC buffers the direct effect of EVM on TB and the effect of NBA on TB. However, SC buffers the effect of NBA on adolescent CB but not buffers the direct effect of EVM on CB. This study highlights the necessity of distinguishing offline and online situations in aggressive behavior research. We suggested “online disinhibit hypothesis” would be adopted to explain why protector factors (e.g., SC) do not buffer the link between aggression‐related risk factors (e.g., EVM) and online aggression (e.g., CB).

No abstract

No abstract

This paper uses neural network as a predictive model and genetic algorithm as an online optimization algorithm to simulate the noise processing of Chinese-English parallel corpus. At the same time, according to the powerful random global search mechanism of genetic algorithm, this paper studied the principle and process of noise processing in Chinese-English parallel corpus. Aiming at the task of identifying isolated words for unspecified persons, taking into account the inadequacies of the algorithms in standard genetic algorithms and neural networks, this paper proposes a fast algorithm for training the network using genetic algorithms. Through simulation calculations, different characteristic parameters, the number of training samples, background noise, and whether a specific person affects the recognition result were analyzed and discussed and compared with the traditional dynamic time comparison method. This paper introduces the idea of reinforcement learning, uses different reward mechanisms to solve the inconsistency of loss function and evaluation index measurement methods, and uses different decoding methods to alleviate the problem of exposure bias. It uses various simple genetic operations and the survival of the fittest selection mechanism to guide the learning process and determine the direction of the search, and it can search multiple regions in the solution space at the same time. In addition, it also has the advantage of not being restricted by the restrictive conditions of the search space (such as differentiable, continuous, and unimodal). At the same time, a method of using English subword vectors to initialize the parameters of the translation model is given. The research results show that the neural network recognition method based on genetic algorithm which is given in this paper shows its ability of quickly learning network weights and it is superior to the standard in all aspects. The performance of the algorithm in genetic algorithm and neural network, with high recognition rate and unique application advantages, can achieve a win-win of time and efficiency.