Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.

The global agreement on environmentally friendly policies puts pressure on businesses to implement good practices to increase legitimacy in a competitive environment. This research aims to examine business dynamic capabilities and value creation processes through the concept of green dynamic marketing capabilities. This concept addresses the ability of businesses to absorb, manage information and accumulate new knowledge that fuels innovative endeavors. The dynamic capability view and customer value theory are integrated to theoretically explain the value creation process of market-orientated innovative products. A total of 58 global companies in Clean200 were sampled. A quantitative approach was conducted to measure the effect of organizational learning (environment management team, environment management training, environment supply chain management) on green innovation (environmental innovation score, eco design product). The results showed that the contribution of Model-1 (0.473 or 47.3%) explained the effect of organizational learning on environmental innovation score, respectively on the variables of environment management team (2.859/0.005), environment management training (−2.971/0.003), and environment supply chain management (7.786/0.000). The contribution of Model-2 (0.448/44.8%) explains the effect of organizational learning on eco-design product, respectively on the variables of environment management team (4.280/0.000), environment management training (−6.401/0.000), and environment supply chain management (7.910/0.000). Model-3 tested the structural association variables in organizational learning and green innovation. A significant influence can be seen with a probability value smaller than 0.05. This research shows that the concept of green dynamic marketing capabilities can be used to explain the ability of businesses in response to the pressure of green global norms through the development of organizational learning towards creation of green innovation product that has impact on market performance. The implication of this research is the creation of new mindset in which green global norms challenge becomes an opportunity for businesses to improve competitiveness.

Young people are a traditional risk group for radicalization and involvement in protest and extremist activities. The relevance of this topic is due to the growing threat of youth radicalization, the expansion of the activities of extremist organizations, and the need to organize high-quality preventive work in educational organizations at various levels. The article provides an overview of research on the topic under consideration and also presents the results of a series of surveys in general educational institutions and organizations of secondary vocational education (n = 11,052), universities (n = 3966) located in the Arctic zone of the Russian Federation. The results of the study on aspects of students’ ideas about extremism are presented in terms of assessing their own knowledge about extremism, the presence/absence of radically minded people around them, determining the degree of threat from the activities of extremist groups for themselves and their social environment, and identifying approaches to preventing the growth of extremism in society. Conclusions are drawn about the need to improve preventive work models in educational organizations towards a targeted (group) approach.

In the wake of the COVID-19 pandemic, the prevalence of online education in primary education has exhibited an upward trajectory. Relative to traditional learning environments, online instruction has evolved into a pivotal pedagogical modality for contemporary students. Thus, to comprehensively comprehend the repercussions of environmental changes on students’ psychological well-being in the backdrop of prolonged online education, this study employs an innovative methodology. Founded upon three elemental feature sequences—images, acoustics, and text extracted from online learning data—the model ingeniously amalgamates these facets. The fusion methodology aims to synergistically harness information from diverse perceptual channels to capture the students’ psychological states more comprehensively and accurately. To discern emotional features, the model leverages support vector machines (SVM), exhibiting commendable proficiency in handling emotional information. Moreover, to enhance the efficacy of psychological well-being prediction, this study incorporates an attention mechanism into the traditional Convolutional Neural Network (CNN) architecture. By innovatively introducing this attention mechanism in CNN, the study observes a significant improvement in accuracy in identifying six psychological features, demonstrating the effectiveness of attention mechanisms in deep learning models. Finally, beyond model performance validation, this study delves into a profound analysis of the impact of environmental changes on students’ psychological well-being. This analysis furnishes valuable insights for formulating pertinent instructional strategies in the protracted context of online education, aiding educational institutions in better addressing the challenges posed to students’ psychological well-being in novel learning environments.

While the notion of the smart city has grown in popularity, the backlash against smart urban infrastructure in the context of changing state-public relations has seldom been examined. This article draws on the case of Hong Kong’s smart lampposts to analyse the emergence of networked dissent against smart urban infrastructure during a period of unrest. Deriving insights from critical data studies, dissentworks theory, and relevant work on networked activism, the article illustrates how a smart urban infrastructure was turned into both a source and a target of popular dissent through digital mediation and politicisation. Drawing on an interpretive analysis of qualitative data collected from multiple digital platforms, the analysis explicates the citizen curation of socio-technic counter-imaginaries that constituted a consent of dissent in the digital realm, and the creation and diffusion of networked action repertoires in response to a changing political opportunity structure. In addition to explicating the words and deeds employed in this networked dissent, this article also discusses the technopolitical repercussions of this dissent for the city’s later attempts at data-based urban governance, which have unfolded at the intersections of urban techno-politics and local contentious politics. Moving beyond the common focus on neoliberal governmentality and its limits, this article reveals the underexplored pitfalls of smart urban infrastructure vis-à-vis the shifting socio-political landscape of Hong Kong, particularly in the digital age.