Emergent Dynamics in Multiplex Social Networks: Agent-Based Modeling of Information Diffusion for Misinformation Control

Northeast Journal of Complex Systems · 2026-04-16

Information misrepresentation is widespread in multi-layered social networks which provide multiple avenues to communicate information. As such, it presents significant opportunities for both information integrity and public discourse to be undermined by disinformation. This paper outlines a new agent-based model, developed to capture emergent dynamics of multi-layered social networks and to help identify technical means to mitigate information misrepresentation in complex systems. A key component of this research includes a novel Multi-Layer Information Diffusion Model (MLIDM), integrating both cross-layer communication among agents, as well as heterogeneous agent behaviors and adaptive intervention strategies. Our methods employ a three-stage process to model misinformation spreading in multi-layered social networks: (1) constructing the layered architecture of a multi-layered social network; (2) using agent-based modeling techniques to simulate the behavior of each layer and to update beliefs based upon those behaviors; and (3) developing targeted intervention strategies that utilize the topology of the network and patterns of information flow. Through experimental testing of both synthetic and actual data sets (e.g., Twitter COVID-19 dataset, n = 50,000 tweets), we demonstrate that our method can reduce the rate at which misinformation spreads by 43.7% when compared to a baseline model. Furthermore, we find that our method improves early detection of misinformation by 28.5%. In addition to these quantitative results, we also find evidence for critical thresholds for the timing of interventions, where interventions applied during the first 15% of the diffusion timeline are significantly more effective than interventions applied later in time (E = 0.67 vs. E = 0.21, Cohen's d = 1.82). Finally, we find evidence of phase transitions in 23% of runs and spontaneous polarization in 67% of runs, indicating emergent phenomena resulting from both agent-network interactions. Therefore, our results will aid in the theoretical development of information dynamics in complex systems, while providing practical guidance for the design of effective counter-measures to misinformation in digital environments.

The psychology of online shopping success: Insights on social media analytics and customer feedback

Acta Psychologica · 2026-02-09

Social media analytics (SMA) practices are playing a vital role in improving online store performance by creating insights about customer preferences, trends, and behaviors. Social media analytics (SMA) practices are a critical contributor to boost online store performance by creating insights on customer preferences, trends and behaviors. The effective utilization of such analytics helps online retailers to adjust their marketing strategies, increase customer engagement, and ultimately boost their sales. This study examines the dynamic link between SMA and customer engagement in online retail firms with special focus on the moderating role of customer voice (promotive and prohibitive) in determining the performance outcomes. Specifically, it examines the impact of consumers' promotive and prohibitive voices on the relationship between customer engagement and online store performance. Using a time-lagged study and data obtained from 407 online stores across three survey waves, the findings show there is a strong positive relationship between SMA and customer engagement. In addition, both promotive and prohibitive customer voice are found to positively moderate the engagement-performance relationship, increasing the effect of engagement on operational outcomes. The study concludes with implications and future research directions.

An Empirical Study on FinTech Awareness and its Impact on Digital Financial Adoption Among Young Consumers

Journal of Emerging Technologies and Innovative Research · 2026-01-01

Emerging Trends and the Future of Business Analytics

2025-10-08

Artificial intelligence (AI) and machine learning (ML) have transformed business analytics in today’s data-driven environment, bringing new trends, technologies, and capabilities. Focusing on areas such as machine learning, predictive analytics, natural language processing (NLP), text analytics, computer vision, and robotic process automation (RPA), this research examines the AI-based technologies needed to advance business intelligence (BI). By integrating these solutions, organizations can improve operations, gain valuable insights, and make data-driven decisions. Finding patterns and predicting trends in big data is accomplished through machine learning and predictive analytics. Natural Language Processing (NLP) and text analytics help unlock the potential of redundant data by facilitating user insights, service automation, and better decision making. This expands business intelligence to include visual data processing. Also, use RPA and AI to automate processes to increase productivity and efficiency. Big data and IoT can also help businesses better adapt to changing business conditions. Advanced design techniques enhance human-computer interaction and enable intelligent data interpretation. This article explores the future potential of AI-ML NLP to reinvent analytics and decision making by highlighting the latest developments and impacts of AI-ML NLP on BI.

AgriSynth: Machine Learning - Driven Crop Intelligence, Fertilizer Rationalization and Disease Diagnostics

2025-03-07 · 4 citations

Agriculture is important to feeding the world's growing population, especially in the face of climate change. Machine learning technology has the potential to greatly improve agriculture by helping farmers make more educated decisions. However, current systems have considerable limitations. Many fertilizer recommendations only address the key nutrients NPK: nitrogen, phosphorus, and potassium, fail to account for water availability, and rely on out-of-date historical data. This study would close these gaps by producing a machine learning system that can help farmers with crop recommendations, fertiliser guidance, and plant disease detection. The algorithm considers micronutrients and organic matter in addition to NPK when recommending fertiliser. It also incorporates water availability and real-time meteorological data to provide more precise crop suggestions, especially important for drought-prone areas. Deep learning methods analyze plant photos to detect diseases early on. Our findings indicate that by incorporating micro nutrients, water data, and real-time climate updates, the system can deliver more precise crop and fertilizer recommendations. The Random Forest and XGBoost models outperform, and the disease detection component helps to prevent crop losses by intervening early. The key takeaway from this study is that merging machine learning with large amounts of data can significantly improve farming techniques, raise crop yields, and provide farmers with reliable insights, thereby enhancing food security and sustainable agriculture.

A holistic mini -review: Artificial Intelligence and the future of finance

International Journal of Computing Programming and Database Management · 2025-01-01

The field of contemporary financial services is changing due to artificial intelligence (AI), which is propelling innovation in anything from asset management to algorithmic procedures. Automated trading, robo-advisory, fraud detection, credit risk assessment, and personalised banking are just a few of the many uses of AI in the financial ecosystem that are examined in this review article. The technologies that allow financial institutions to improve efficiency, accuracy, and customer experience are examined, including machine learning, natural language processing, and predictive analytics. The literature illustrates whether AI is impacting operational processes, strategic decision-making, and regulatory compliance through an analysis of case studies and real-world deployments. Additionally, we examine concerns about model interpretability, ethical usage, and data governance as we delve over the advantages and disadvantages of adopting AI. The review article provides a comprehensive viewpoint on artificial intelligence evolved from theoretical algorithms to useful resources in the finance industry and conclude by evaluating the future direction of AI in finance and highlighting important themes as the emergence of decentralised finance (DeFi), AI-driven ESG investment, and hybrid human-AI collaboration.

Happy Wisdom Framework

Advances in human resources management and organizational development book series · 2025-01-10

The phrase “Happy Wisdom” is not attributed to a specific person or philosopher. It is a concept that combines two universal ideas—happiness and wisdom. While many researchers have investigated the relationship between happiness and wisdom throughout literature, there's no single person credited with coining the exact phrase “Happy Wisdom”. It is a phrase that combines the idea of happiness and wisdom, suggesting that true wisdom often leads to happiness, and a happy life is guided by wisdom. It can be interpreted as a state of being where one finds joy in understanding and learning, or where wise decisions lead to a fulfilling and content life. The study provides a step-by-step guide to happy wisdom adapted from Maslow hierarch theory. This step-by-step guide will provide a framework for academicians to test it quantitatively, and to corporate people to implement the same in organization for better growth and profit. Finally, it concludes with the scope for future research.

Publisher Correction: HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification

Scientific Reports · 2025-03-12 · 3 citations

HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification

Scientific Reports · 2025-02-18 · 30 citations

Optical Coherence Tomography (OCT) plays a crucial role in diagnosing ocular diseases, yet conventional CNN-based models face limitations such as high computational overhead, noise sensitivity, and data imbalance. This paper introduces HDL-ACO, a novel Hybrid Deep Learning (HDL) framework that integrates Convolutional Neural Networks with Ant Colony Optimization (ACO) to enhance classification accuracy and computational efficiency. The proposed methodology involves pre-processing the OCT dataset using discrete wavelet transform and ACO-optimized augmentation, followed by multiscale patch embedding to generate image patches of varying sizes. The hybrid deep learning model leverages ACO-based hyperparameter optimization to enhance feature selection and training efficiency. Furthermore, a Transformer-based feature extraction module integrates content-aware embeddings, multi-head self-attention, and feedforward neural networks to improve classification performance. Experimental results demonstrate that HDL-ACO outperforms state-of-the-art models, including ResNet-50, VGG-16, and XGBoost, achieving 95% training accuracy and 93% validation accuracy. The proposed framework offers a scalable, resource-efficient solution for real-time clinical OCT image classification.

Do the Individualized Differences in the Student; Age, Gender, Marital Status, Work Experience, and Educational Qualification Affect FOMO

Springer proceedings in business and economics · 2025-01-01