Recommendation Precision Research Articles

Evaluating Accuracy of AI-Generated Travel Vaccine Recommendations: GPTs in Public Health

Abstract Introduction Artificial intelligence (AI), particularly generative pre-trained transformers (GPTs), holds promise for enhancing public health strategies like travel vaccine recommendations. This pilot study evaluated GPTs’ accuracy in delivering tailored vaccine advisories compared to standards set by public health professionals. Integrating AI’s data analysis capabilities into healthcare decision-making could improve recommendation precision and personalization. Methods This retrospective study analyzed GPT travel vaccine recommendation accuracy against a gold standard from health professionals for 90 travelers visiting various countries. Sociodemographic data and vaccine recommendation outcomes were examined. Accuracy assessments were stratified by age, sex, country of travel, duration of travel, type of travel, and specific vaccines. Results Preliminary results showed an 77.43% overall accuracy across all vaccine recommendations. Specific vaccine accuracies varied, with 97.78% alignment for hepatitis A, 93.51% for typhoid fever and 89.36% for rabies. However, lower accuracies were observed for cholera (33.33%) and encephalitis (56.25%). Moderate accuracies were noted for yellow fever (75%), 74.07% for malaria prophylaxis, diphtheria and tetanus (63.33%), and dengue (57.58%). Stratified analyses are expected to provide more realistic results and highlight discrepancies in certain groups. Conclusions This pilot demonstrates GPTs can be a valuable tool for supporting international vaccination professionals, but they are still not a substitute for these professionals, achieving 77.43% overall accuracy. Recommendations include: a) Educate health professionals in the use of GPTs, b) Developing guidelines for ethical and accurate AI use in public health, c) Using AI to strengthen surveillance and response systems. Combining AI with traditional strategies aims to optimize international traveler health outcomes. Key messages • Using artificial intelligence can optimize and facilitate the task of clinical consultancy in traveler’s advice. • It is necessary to establish guidelines for AI use to ensure ethical and accurate applications.

A novel method for a technology enhanced learning recommender system considering changing user interest based on neural collaborative filtering

This study introduces an advanced recommender system for technology enhanced learning (TEL) that synergizes neural collaborative filtering, sentiment analysis, and an adaptive learning rate to address the limitations of traditional TEL systems. Recognizing the critical gap in existing approaches—primarily their neglect of user emotional feedback and static learning paths—our model innovatively incorporates sentiment analysis to capture and respond to nuanced emotional feedback from users. Utilizing Bidirectional Encoder Representations from Transformers for sentiment analysis, our system not only understands but also respects user privacy by processing feedback without revealing sensitive information. The adaptive learning rate, inspired by AdaGrad, allows our model to adjust its learning trajectory based on the sentiment scores associated with user feedback, ensuring a dynamic response to both positive and negative sentiments. This dual approach enhances the system’s adaptability to changing user preferences and improves its contentment understanding. Our methodology involves a comprehensive analysis of both the content of learning materials and the behaviors and preferences of learners, facilitating a more personalized learning experience. By dynamically adjusting recommendations based on real-time user data and behavioral analysis, our system leverages the collective insights of similar users and relevant content. We validated our approach against three datasets—MovieLens, Amazon, and a proprietary TEL dataset—and saw significant improvements in recommendation precision, F-score, and mean absolute error. The results indicate the potential of integrating sentiment analysis and adaptive learning rates into TEL recommender systems, marking a step forward in developing more responsive and user-centric educational technologies. This study paves the way for future advancements in TEL systems, emphasizing the importance of emotional intelligence and adaptability in enhancing the learning experience.

A two-stage recommendation optimization algorithm based on item popularity and user features

Financial product recommendation algorithms are mainly product-centered. This article proposes a two-stage recommendation optimization algorithm based on item popularity and user features, named CPCF-TSP, that can make full use of the demographic characteristics of users and mitigate the problem of users being more inclined to choose “hot” financial products. A popularity weight factor is introduced to normalize popularity and modify Pearson's similarity function. The modified Pearson's similarity function is combined with popularity normalization and user features to improve modeling performance. The two-stage recommendation optimization procedure was combined with a collaborative filtering algorithm to improve recommendation precision. CPCF-TSP fully considers user features in building a hybrid recommendation model and solves the problem of user cold-start. It can also mitigate popularity deviations and improve recommendation precision. MovieLens data and Santander Bank client trading data were used in a case study. The results show that the algorithm reduces inaccuracy in the calculation of the weights for recommendation popularity and similarity and is especially suitable for recommending financial products in which user information can be easily collected and the number of users is far greater than the number of products considered.

The design of advertising text keyword recommendation for internet search engines

As the growth of internet technology, human life is full of various advertisements. It is possible for individuals to obtain the advertising information they require, whether in an online or offline context. A research proposal is presented with the objective of enhancing the precision of online advertising recommendations. The proposal is based on the design of internet search engine advertising text keyword recommendation models, which integrate entity naming recognition models to facilitate tasks such as text classification and feature extraction. A recommendation algorithm based on content similarity is used to achieve keyword recommendation. Under the similarity calculation method of continuous bag-of-words model, when K is 100, the model weighted precision of the feature extraction method based on graph sorting and inverse text frequency index is 0.88, the weighted recall is 0.76, and the weighted F1-score is 0.82. In offline simulation testing, 85 % of the keyword recommendation model's recommendation time is less than 1 s, 99 % of the recommendation time is less than 2 s, and the recommendation cost can be significantly reduced by 75 %. In practical applications, the recommendation efficiency of this method can reach 96.3 %, and the recommendation precision can reach 95.8 %. The recommended satisfaction rate can reach 99.5 %. The results demonstrate that this method can provide highly accurate keyword recommendations and reduce the cost of advertising placement. Furthermore, it has been recognized and praised by users.

Constructing and Realising an Employment Platform for Slash Youth in the Age of Digital Intelligence

The current employment environment is becoming increasingly complex, with many job seekers competing with each other in more concentrated and narrower fields, worsening the job market as well as inhibiting the career potential of job seekers. There is a need to provide better employment guidance and employment quality assessment for slash youth. This study attempts to design a job recommendation model for slash youths by combining an improved collaborative filtering algorithm and a dynamic bilateral matching algorithm (BMA). The test results show that the precision rate of the BMA is always the largest with the increase of the number of clusters, with the highest value reaching 90.04%; the average ranking inverse curve of bilateral matching has the fastest growth rate, with the maximum value of 62.04%, which is 34.26% and 10.06% higher than the other two maximum values, and the optimal number of clusters is set to 24. The highest precision rate of the algorithm is 82.17% when the number of recommendations is 10. The algorithm also performed better in terms of recommendation diversity, with a maximum value of around 0.28. The recommendation success rate and satisfaction value reached 87.72% and 47.86%, respectively. The recommendation precision of the model designed in this study is high. It is conducive to solving problems such as difficulty in recruiting and finding jobs, and promotes the healthy development of the recruitment market.

Natural Language Processing (NLP) in Recommendation Systems

This paper delves into the application of Natural Language Processing (NLP) techniques in recommendation systems, specifically focusing on novel approaches to enhance recommendation accuracy and user satisfaction. The utilization of NLP algorithms has revolutionized how content is recommended to users, leveraging linguistic analysis and machine learning to understand user preferences and provide tailored suggestions. Our research explores various NLP methodologies, including sentiment analysis, topic modelling, and semantic analysis, to extract meaningful insights from textual data. Furthermore, we investigate the integration of deep learning models, such as neural networks and transformer architectures, to capture complex patterns and improve recommendation precision. A key highlight of our study is the introduction of a novel recommendation method termed "Knowledge Graph Embedding for Contextual Recommendation." This innovative approach combines knowledge graph representation with contextual understanding, allowing for more nuanced and personalized recommendations based on user interactions, historical data, and contextual relevance. We delve into the intricacies of this technique, detailing its implementation, training process, and evaluation metrics.

Personalized Intelligent Recommendation Model Construction Based on Online Learning Behavior Features and CNN

The current intelligent recommendation models in online learning systems suffer from data sparsity and cold start problems. To address the data sparsity problem, a collaborative filtering recommendation algorithm model (SACM-CF) based on an automatic coding machine is proposed in the study. The model can extract the online learning behavior features of users and match these features with the learning resource features to improve the recommendation precision. For the cold-start problem, the study proposes a CBCNN model based on CNN, using the language model as the input of the model and the implicit factor as the output of the model. To avoid the problem of over-smoothing the implicit factor model, which affects the recommendation precision, an improved matrix decomposition method is proposed to constrain the output of the CNN and improve the model precision. The RMSE of SACM-CF is 0.844 and the MAE is 0.625. The MAE value of CBCNN is 0.72, the recall value is 0.65, the recommendation precision is 0.954 and the F1-score is 0.84. The metrics of SACM-CF and CBCNN are better than the existing state-of-the-art recommendation models. SACM-CF and CBCNN outperform the existing state-of-the-art intelligent recommendation models in all metrics. Therefore, the SACM-CF model and the CBCNN model can effectively improve the precision of the online learning system in recommending interesting learning resources to users, thus avoiding users' wasted learning time in searching and selecting learning resources and improving users' learning efficiency.

Integration of Deep Reinforcement Learning with Collaborative Filtering for Movie Recommendation Systems

In the era of big data, effective recommendation systems are essential for providing users with personalized content and reducing search time on online platforms. Traditional collaborative filtering (CF) methods face challenges like data sparsity and the new-user or cold-start issue, primarily due to their reliance on limited user–item interactions. This paper proposes an innovative movie recommendation system that integrates deep reinforcement learning (DRL) with CF, employing the actor–critic method and the Deep Deterministic Policy Gradient (DDPG) algorithm. This integration enhances the system’s ability to navigate the recommendation space effectively, especially for new users with less interaction data. The system utilizes DRL for making initial recommendations to new users and to generate optimal recommendation as more data becomes available. Additionally, singular value decomposition (SVD) is used for matrix factorization in CF, improving the extraction of detailed embeddings that capture the latent features of users and movies. This approach significantly increases recommendation precision and personalization. Our model’s performance is evaluated using the MovieLens dataset with metrics like Precision, Recall, and F1 Score and demonstrates its effectiveness compared with existing recommendation benchmarks, particularly in addressing sparsity and new-user challenges. Several benchmarks of existing recommendation models are selected for the purpose of model comparison.

Federated recommender systems based on deep learning: The experimental comparisons of deep learning algorithms and federated learning aggregation strategies

Due to the requirements of privacy protection and data asset ownership, recommender systems (RSs) based on centralized training process may be infeasible in some practical situations. In these situations, federated recommender systems (FedRec) based on deep learning are regarded as the substitutes with extensive application backgrounds and enormous potential business values. However, which deep learning algorithm and federated learning aggregation strategy perform best in the training of FedRec is still an unsolved question. To answer this question, experiments are conducted for comparing the performances of four popular deep learning algorithms and three federated learning aggregation strategies in FedRec. The experiments are conducted on 8 public datasets to obtain 96 FedRec precisions (4 deep learning algorithms × 3 federated learning aggregation strategies × 8 datasets). Then, the Wilcoxon test is used to verify whether there is a significant difference between the FedRec combinations and to derive the best combination. The result shows that, in terms of recommendation precision, the best FedRec is the combination of neural FM and federated averaging. In terms of execution iterations, the best FedRec is the combination of deep crossing and attentive federated aggregation. The obtained results would be valuable for further promoting the development of RSs under the situations that a centralized training process is infeasible.

Improving Collaborative Filtering Recommendations with Tag and Time Integration in Virtual Online Communities

In recent years, virtual online communities have experienced rapid growth. These communities enable individuals to share and manage images or websites by employing tags. A collaborative tagging system (CTS) facilitates the process by which internet users collectively organize resources. CTS offers a plethora of useful information, including tags and timestamps, which can be utilized for recommendations. A tag represents an implicit evaluation of the user’s preference for a particular resource, while timestamps indicate changes in the user’s interests over time. As the amount of information increases, it is feasible to integrate more detailed data, such as tags and timestamps, to improve the quality of personalized recommendations. The current study employs collaborative filtering (CF), which incorporates both tag and time information to enhance recommendation precision. A computational recommender system is established to generate weights and calculate similarities by incorporating tag data and time. The effectiveness of our recommendation model was evaluated by linearly merging tag and time data. In addition, the proposed CF method was validated by applying it to big data sets in the real world. To assess its performance, the size of the neighborhood was adjusted in accordance with the standard CF procedure. The experimental results indicate that our proposed method significantly improves the quality of recommendations compared to the basic CF approach.

Recommendation of SLM Process Parameters Based on Analytic Hierarchy Process and Weighted Particle Swarm Optimization for High-Temperature Alloys.

Selective laser melting (SLM) of high-temperature alloys involves intricate interdependencies among key process parameters, such as laser power and scanning speed, affecting properties such as density and tensile strength. However, relying solely on experiential knowledge for process parameter design often hampers the precise attainment of target requirements. To address this challenge, we propose an innovative approach that integrates the analytic hierarchy process (AHP) and weighted particle swarm optimization (WPSO) to recommend SLM process parameters for high-temperature alloy fabrication. Our proposed AHP-WPSO model consists of three main steps. First, a comprehensive historical database is established, capturing the process parameters and performance metrics of high-temperature alloy SLM parts. Utilizing an AHP framework, we compute the performance similarity between target and historical cases, applying rational thresholds to identify analogous cases. When suitable analogs are elusive, the model seamlessly transitions to the second step. Here, the WPSO model optimizes and recommends process parameters according to target specifications. Lastly, our experimental validation of the GH4169 high-temperature alloy through SLM experiments corroborates the effectiveness of our AHP-WPSO model in making process parameter recommendations. The outcomes underscore the model's high accuracy, attaining a recommendation precision of 99.81% and 96.32% when historical analogs are present and absent, respectively. This innovative approach offers a robust and reliable solution to the challenges posed in SLM process parameter optimization for high-temperature alloy applications.

Social Influence-Maximizing Group Recommendation

In this paper, we revisit the group recommendation problem, by taking into consideration the information diffusion in a social network, as one of the main criteria that must be maximised. While the well-known influence maximization problem has the objective to select k users (spread seeds) from a social network, so that a piece of information can spread to the largest possible number of people in the network, in our setting the seeds are known (given as a group), and we must decide which k items (pieces of information) should be recommended to them. Therefore, the recommended items should at the same time be the best match for that group's preferences, and have the potential to spread as much as possible in an underlying diffusion network, to which the group members (the seeds) belong. This problem is directly motivated by group recommendation scenarios where social networking is an inherent dimension that must be taken into account when assessing the potential impact of a certain recommendation. We present the model and formulate the problem of influence-aware group recommendation as a multiple objective optimization problem. We then describe a greedy approach for this problem and we design an optimisation approach, by adapting the top-k algorithms NRA and TA. We evaluate all these methods experimentally, in three different recommendation scenarios, for movie, micro-blog and book recommendations, based on real-world datasets from Flixster, Twitter, and Douban respectively. Unsurprisingly, with the introduction of information diffusion as an optimization criterion for group recommendation, the recommendation problem becomes more complex. However, we show that our algorithms enable spread efficiency without loss of recommendation precision, under reasonable latency.

A Real-Time Tourism Route Recommendation System Based on Multitime Scale Constraints

In order to increase the capability of real-time intelligent recommendation of tourists’ information on cross-regional city-level tourist routes with epidemic normalization, a real-time intelligent recommendation algorithm for cross-regional city-level tourist routes with epidemic normalization based on multi-time scale constraints is proposed. Under the training of limited samples, the tourist correlation model of the epidemic normalization of cross-regional city-level tourist routes is created. In addition, two kernel functions i.e. the mixed and the global are assembled to excerpt the correspondence features of the epidemic normalization cross-regional city-level tourist route recommendation information. As a result, the well-known particle swarm optimization (PSO) procedure and algorithm with multitime scale constraints are adopted to carry out the adaptive learning of the epidemic normalization cross-regional city-level tourist route recommendation, and the convergence control of the recommended method is comprehended through mining the geographic information data sets of cities. This paper analyzes the universality and ergodicity of tourists' personal interest preferences and social characteristics in urban tourism and combines a gradient algorithm to carry out particle swarm evolution and self-adaptive optimization for the recommendation of cross-regional city-level tourist routes with a normalized epidemic situation, so as to realize the group real-time intelligent recommendation of tourists’ information on cross-regional city-level tourist routes with the normalized epidemic situation. The model outcomes indicate that the exactitude and precision of cross-regional city-level tourism route information recommendation with this algorithm are decent, and the convergence of the swarm intelligence optimization (SIO) problem is robust, which can circumvent dipping into the local optimal solution in the process of real-time intelligent recommendation of tourism routes and improve the intelligence and global stability of cross-regional city-level tourism route recommendation with epidemic normalization.

Meta Path-Aware Recommendation Method Based on Non-Negative Matrix Factorization in LBSN

Location-based social networks (LBSN) is a new type of heterogeneous information network (HIN). The check-in data usually has the characteristics of a large amount of data and high sparsity. It is a problem worth studying how to effectively discover its complex community structure and accurately recommend it to users. Most HIN-based recommendation methods rely on path-based similarity, which cannot fully mine latent structure features of LBSN users and items. This paper proposes a meta-path-aware common clustering recommendation method MPNMF (meta-path-aware non-negative matrix factorization), based on non-negative matrix tri-factorization. By establishing the objective function based on non-negative matrix tri-factorization and second-order meta-path method, LBSN users and points of interest are integrated with their multi-dimensional heterogeneous relationships. The interrelated user clusters and interest point clusters can be obtained, effectively alleviating the influence of data sparsity. To solve the initial value problem of the model, this method uses the spectral cluster method, which provides a good initial value for the construction of the prediction model. It improves the operational efficiency of the model and the precision of model recommendations. Experiments on the real LBSN datasets show that the proposed method has a high recommendation precision and recall.

Detecting Lung Cancer Region from CT Image Using Meta-Heuristic Optimized Segmentation Approach

Lung tumor detection using computer-aided modeling improves the accuracy of detection and clinical recommendation precision. An optimal tumor detection requires noise reduced computed tomography (CT) images for pixel classification. In this paper, the butterfly optimization algorithm-based [Formula: see text]-means clustering (BOAKMC) method is introduced for reducing CT image segmentation uncertainty. The introduced method detects the overlapping features for optimal edge classification. The best-fit features are first trained and verified for their similarity. The clustering process recurrently groups the feature matched pixels into clusters and updates the centroid based on further classifications. In this classification process, the uncertain pixels are identified and mitigated in the tumor detection analysis. The best-fit features are used to train local search instances in the BOA process, which influences the similar pixel grouping in the uncertainty detection process. The proposed BOAKMC improves accuracy and precision by 10.2% and 13.39% and reduces classification failure and time by 11.29% and 11.52%, respectively.

Mobile Social Recommendation Model Integrating Users’ Personality Traits and Relationship Strength under Privacy Concerns

Aiming at the problem of data sparsity, cold start, and privacy concerns in complex information recommendation systems, such as personalized marketing on Alibaba or TikTok, this paper proposes a mobile social recommendation model integrating users’ personality traits and social relationship strength under privacy concerns (PC-MSPR). Firstly, PC-MSPR focuses on specific personality traits, including openness, extraversion, and agreeableness, and their impacts on mobile users’ online behaviors. A personality traits calculation method that incorporates privacy preferences (PP-PTM) is then introduced. Secondly, a novel method for calculating the users’ relationship strength, based on their social network interactive activities and domain ontologies (AI-URS) is proposed. AI-URS divides the interactive activities into activity domains and calculates the strength of relationships between users belonging to the same activity domain; at the same time, the comprehensive relationship strength of users in the same domain, including direct relationships and indirect relationships, is calculated based on interactive activity documents. Finally, social recommendations are derived by integrating personality traits and social relationships to calculate user similarity. The proposed model is validated using empirical data. The results show the model’s superiority in alleviating data sparsity and cold-start problems, obtaining higher recommendation precision, and reducing the impact of privacy concerns regarding the users’ adoption of personalized recommendation services.

Precise Recommendation Algorithm for Online Sports Video Teaching Resources

INTRODUCTION: With the development of the epidemic, online teaching has gradually become a hot topic. However, unlike traditional teaching programs, there are many types of physical education resources, and the recommendation of related content has always been a difficulty in online teaching. OBJECTIVES: Therefore, this paper designs an accurate recommendation algorithm for online video teaching resources of sports to meet the personalized needs of online learning of sports majors. The data layer of the entire recommendation algorithm stores the video in the database and transmits it to the service processing layer after receiving the data. METHODS: This study was conducted using techniques from social network analysis. After receiving the data, the data layer of the recommendation algorithm stores the video in the database and transmits it to the business processing layer at the same time. The business processing layer uses the designed collaborative filtering resource recommendation algorithm to formulate recommendation results for different users, and push the recommended results to the user display interface of the user layer. RESULTS: The test results of the algorithm show that the designed system has a high recommendation success rate, and the system can still maintain stable running performance when the concurrent users are 500. The average precision of resource recommendation of this method is 98.21%, the average recall rate is 98.35%, and the average F1 value is 95.37%. CONCLUSION: The proposed resource recommendation algorithm realizes accurate recommendation of sports online video teaching resources through efficient recommendation algorithms.

Differentially private recommender system with variational autoencoders

To provide precise recommendations, traditional recommender systems (RS) collect personal data, user preference and feedback, which are sensitive to each user if such information is maliciously used for extra analysis. In recent years, differential privacy (DP) has been widely applied in RS to provide privacy protection for sensitive information. Prior studies explored the combination of DP and RS, while neglecting the disparate effect on model accuracy of imbalanced subgroups as large user groups control the trained model, and DP can worsen the disparate effect of degrading the performance of recommender systems significantly. Besides, the number of uploaded contributions can differ among users for training a recommender system, so it is necessary to set the user-level privacy guarantee.In this paper, we make four contributions. First, we propose an efficient way of constructing datasets for training a recommender system based on prior theories. Second, we compute the user-level priors based on user metadata to optimize the VAE model. Besides, we add noise into the calculation process to protect user metadata. Third, we analyze and propose a tighter theoretical bound on gradient updates for DP Stochastic Gradient Descent (DPSGD). Finally, we exploit these theoretical results and propose a novel DP-VAE based recommender system. Extensive experimental results on multiple datasets show that our system can achieve high recommendation precision while maintaining a reasonable privacy guarantee.

Explicable recommendation based on knowledge graph

Most of the existing researches on recommendation system assemble in how to enhance precision of recommendation, ignoring acceptance and recognition of users. To work out the problem, a model of explainable recommendation on account of knowledge graph as well as many-objective evolutionary algorithm is proposed, which combines recommendation and explanation. In this work, embedding vectors obtained by embedding-based method are used to quantify the explainability, so as to obtain the explainability of paths between users and items. Candidate recommendation list of users is gained from constructed knowledge graph. Many-objective evolutionary algorithm is used to optimize the list of candidate recommendation so as to seek a set of tradeoff solutions to the four objective functions of accuracy, diversity, novelty and explainability. Then, the best path among object user and recommended items is chosen in knowledge graph as the explanation. Finally, the conclusion that can be drawn from various experiments is that the presented model can boost explainability without reducing the precision, diversity as well as novelty.

Research on Recommendation Algorithm of Joint Light Graph Convolution Network and DropEdge

Overfitting in a deep neural network leads to low recommendation precision and high loss. To mitigate these issues in a deep neural network-based recommendation algorithm, we propose a recommendation algorithm, LG-DropEdge, joint light graph convolutional network, and the DropEdge. First, to reduce the cost of data storage and calculation, we initialize user and item embedding in the embedding layer of the algorithm. Then, to obtain high-order interaction relationships to optimize the embedding representation, we enrich the embedding by injecting high-order connectivity relationships in the convolutional layer. In the training phase, DropEdge is used to randomly discard connected relationships (interaction edges) to prevent overfitting. Finally, to reasonably aggregate the embedding results learned on all layers, the weighted average is expressed as the final embedding, so that users can make preferences in the item. We conduct experiments on three public datasets, using two performance indicators; namely, recall and NDCG, are used for evaluation. For the Gowalla dataset, compared with the optimal baseline method, recall@20 and ndcg@20 increased by 2.53% and 2.39%, respectively. For the Yelp2018 dataset, recall@20 and ndcg@20 increased by 6.17% and 5.58%, respectively. For the Amazon-book dataset, recall@20 and ndcg@20 increased by 4.82% and 4.67%, respectively. The results show that LG-DropEdge can not only reduce the degree of neural network overfitting but also improve the recommended results’ precision.