In the era of information overload, cross-domain recommendations offer a promising solution by leveraging user preferences across domains to improve recommendation accuracy and relevance. This study proposes a novel approach to cross-domain recommendations based on cognitive similarity derived from user-based features. We construct comprehensive user profiles across multiple domains by defining cognitive similarity based on user interaction data, including ratings, reviews, and genre preferences. We employ advanced feature extraction techniques, including TF-IDF for textual data and matrix factorization for latent factors, to quantify similarities in user preferences across domains. These cognitive similarity measures are then used to map user profiles into a common latent space, facilitating the generation of personalized cross-domain recommendations. To visualize the effectiveness of our approach, we use methods such as Multidimensional Scaling (MDS) and heatmaps to depict the cognitive similarity between users across different domains. Additionally, network graphs illustrate the intricate relationships and similarities across user profiles, offering intuitive insights into the recommendation process. The results demonstrate that our cognitive similarity-based approach significantly improves the relevance and diversity of cross-domain recommendations, providing a robust framework for future research and practical applications in personalized recommendation systems.
- Article type
- Year
Open Access
Article
Issue
Open Access
Review
Issue
Natural Language Processing (NLP) has become essential in text classification, sentiment analysis, machine translation, and speech recognition applications. As these tasks become complex, traditional machine learning and deep learning models encounter challenges with optimization, parameter tuning, and handling large-scale, high-dimensional data. Bio-inspired algorithms, which mimic natural processes, offer robust optimization capabilities that can enhance NLP performance by improving feature selection, optimizing model parameters, and integrating adaptive learning mechanisms. This review explores the state-of-the-art applications of bio-inspired algorithms—such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO)—across core NLP tasks. We analyze their comparative advantages, discuss their integration with neural network models, and address computational and scalability limitations. Through a synthesis of existing research, this paper highlights the unique strengths and current challenges of bio-inspired approaches in NLP, offering insights into hybrid models and lightweight, resource-efficient adaptations for real-time processing. Finally, we outline future research directions that emphasize the development of scalable, effective bio-inspired methods adaptable to evolving data environments.
京公网安备11010802044758号