INFLUTRUST: Trust-Based Influencer Marketing Campaigns in Online Social Networks

Future Internet, Journal Year: 2024, Volume and Issue: 16(7), P. 222 - 222

Published: June 25, 2024

This paper introduces the INFLUTRUST framework that is designed to address challenges in trust-based influencer marketing campaigns on Online Social Networks (OSNs). The enables influencers autonomously select products across OSN platforms for advertisement by employing a reinforcement learning algorithm. Stochastic Learning Automata algorithm considers platforms’ provided monetary rewards, influencers’ advertising profit, and trust levels towards enable an platform. model incorporates direct indirect trust, which are derived from past interactions social ties among platforms, respectively. allocate rewards through multilateral bargaining supports competition influencers. Simulation-based results validate framework’s effectiveness diverse scenarios, with scalability analysis demonstrating its robustness. Comparative evaluations highlight superiority considering reward allocation fairness, benefiting both platforms.

Language: Английский

---

The credibility assessment of Twitter/X users based organization objectives by heterogeneous resources in big data life cycle

Computers in Human Behavior, Journal Year: 2024, Volume and Issue: 162, P. 108428 - 108428

Published: Sept. 3, 2024

Language: Английский

---

Enhancing digital currency adoption: examining user experiences

Management Decision, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 9, 2024

Purpose This study aimed to analyse user experiences and perceptions of eRupee banking applications in India, focussing on understanding the key factors driving satisfaction dissatisfaction. Design/methodology/approach A comprehensive text-mining approach was employed 5,176 reviews collected from Google Play Store. Sentiment analysis latent Dirichlet allocation (LDA) were used classify uncover prevailing themes. Findings The revealed that positive highlighted themes usefulness, convenience, satisfaction, app attributes, ease use. Negative emphasise issues related lack trust, faulty updates, unreliability, security concerns, inadequate customer support. Logistic Regression model demonstrated superior performance predicting sentiments, achieving an AUC 0.7926 accuracy rate 77.90%. Research limitations/implications limited a single-platform source. Future research could incorporate data multiple online sources employ qualitative methods gain deeper insight. Additionally, longitudinal studies cross-cultural analyses are recommended capture evolving sentiments global perspectives. Practical implications findings provide actionable insights for bank managers, developers policymakers enhance by addressing identified leveraging aspects improve overall experience satisfaction. Originality/value makes novel contribution literature digital currency advanced techniques using machine-learning models feedback context emerging economy. proposed conceptual practical recommendations serve as foundation future development financial services.

Language: Английский

---

Emoji Retrieval from Gibberish or Garbled Social Media Text: A Novel Methodology and a Case Study

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 170 - 189

Published: Dec. 16, 2024

Language: Английский

---

Optimizing Early Stage Diabetes Detection: A Robust Evaluation of Machine Learning Algorithms

International Journal of Academic Research in Business and Social Sciences, Journal Year: 2024, Volume and Issue: 14(12)

Published: Dec. 30, 2024

The escalating global incidence of diabetes emphasizes the imperative for prompt detection to alleviate significant health adversities. This investigation assesses efficacy and robustness three machine learning algorithms—Decision Tree, Support Vector Machine (SVM), Naive Bayes—utilizing methodologies such as Train-Test Split, K-Fold Cross Validation, Stratified Validation. Critical performance indicators including Accuracy, Precision, Recall, F1-Score, ROC-AUC were meticulously examined, with standard deviation employed evaluate stability models. SVM consistently surpassed other algorithms, exhibiting superior accuracy reliability across various validation approaches, particularly within context Bayes revealed commendable recall efficacy, while Decision Tree experienced augmented through application cross-validation techniques. results underscore significance employing methods, K-Fold, dependable model assessment in scenarios characterized by imbalanced datasets. Subsequent research endeavors should investigate ensemble data augmentation strategies further enhance resilience

Language: Английский

---

Fuzzy adaptive learning control network (FALCN) for image clustering and content-based image retrieval on noisy dataset

AIMS Mathematics, Journal Year: 2023, Volume and Issue: 8(8), P. 18314 - 18338

Published: Jan. 1, 2023

<abstract> <p>It has been demonstrated that fuzzy systems are beneficial for classification and regression. However, they have mainly utilized in controlled settings. An image clustering technique essential content-based picture retrieval big datasets is developed using the contents of color, texture shape. Currently, it challenging to label a huge number photos. The issue unlabeled data addressed. Unsupervised learning used. K-means most often used unsupervised algorithm. In comparison c-means clustering, lower-dimensional space resilience initialization resistance. dominating triple HSV was shown be perceptual color made three modules, S (saturation), H (hue) V (value), referring qualities significantly connected how human eyes perceive colors. A deep segmentation (RBNN) built on Gaussian function, adaptive control network (FALCN), radial basis neural network. segmented critical information fed into classifier. suggested (FALCN) system, also known as network, very good at images can extract properties. When conventional system receives noisy input, output neurons grows needlessly. Finally, random convolutional weights features from without labels. Furthermore, state-of-the-art uniting proposed FALCN with RBNN classifier, descriptor achieves comparable performance, such improved accuracy 96.547 reduced mean squared error 36.028 values JAFE, ORL, UMIT datasets.</p> </abstract>

Language: Английский

---

Enhancing Asian Indigenous Language Processing through Deep Learning-based Handwriting Recognition and Optimization Techniques

ACM Transactions on Asian and Low-Resource Language Information Processing, Journal Year: 2023, Volume and Issue: 23(8), P. 1 - 20

Published: Nov. 10, 2023

Asian indigenous language or autochthonous is a which native to region and spoken by people in Asia. This linguistically different community created the region. Recently, researchers handwriting detection studies comparing with languages have attained important internet amongst research community. A new development of artificial intelligence (AI), natural processing (NLP), cognitive analytics, computational linguistics (CL) find it helpful analysis regional low-resource languages. It can be obvious obtainability effectual machine methods open access handwritten databases. Tamil most ancient Indian that mostly exploited Southern part India, Sri Lanka, Malaysia. Character Recognition (HCR) critical procedure optical character detection. Therefore, this study designs Henry Gas Solubility Optimization Deep Learning-based Handwriting Model (HGSODL-HRM) for Indigenous Language Processing. The proposed HGSODL-HRM technique relies on computer vision DL concepts automated recognition language, one popular To accomplish this, employs capsule network (CapsNet) model feature vector generation HGSO algorithm as hyperparameter optimizer. For characters, wavelet neural (WNN) exploited. Finally, WNN parameters optimally chosen sail fish optimizer (SFO) algorithm. demonstrate promising results system, an extensive range simulations implemented. simulation outcomes stated betterment system compared recent models.

Language: Английский

---