Recommendation Framework Research Articles

Temporal dual-target cross-domain recommendation framework for next basket recommendation

Next Basket Recommender systems in e-commerce face challenges such as data sparsity, evolving user preferences, and cross-domain transfer limitations. We propose the Temporal Dual-Target Cross-Domain Recommendation Framework (T-DualCRF) to address these issues. T-DualCRF integrates multi-channel embeddings (user feedback, knowledge graphs, temporal features) and a dual-target mechanism for robust cross-domain knowledge transfer. It also employs time-aware embeddings and a temporal heterogeneous graph to model user preference changes. The framework’s hybrid optimization mechanism, combining the Multi-Verse Optimizer and Whale Optimization Algorithm, enhances recommendation accuracy and stability. Experimental results on Amazon datasets show that T-DualCRF significantly outperforms existing models, with improvements of up to 20% in F1-score and 17% in NDCG, effectively mitigating data sparsity and adapting to real-time user behavior changes.

A novel recommender framework with chatbot to stratify heart attack risk

Cardiovascular diseases are a major cause of mortality and morbidity. Fast detection of life-threatening emergency events and an earlier start of the therapy would save many lives and reduce successive disabilities. Understanding the specific risk factors associated with heart attack and the degree of association is crucial in the clinical diagnosis. Considering the potential benefits of intelligent models in healthcare, many researchers have developed a variety of machine learning (ML)-based models to identify patients at risk of a heart attack. However, the common problem of previous works that used ML concepts was the lack of transparency in black-box models, which makes it difficult to understand how the model made the prediction. In this study, an automated smart recommender system (Explainable Artificial Intelligence) for heart attack prediction and risk stratification was developed. For the purpose, the CatBoost classifier was applied as the initial step. Then, the SHAP (SHapley Additive exPlanation) explainable algorithm was employed to determine reasons behind high or low risk classification. The recommender system can provide insights into the reasoning behind the predictions, including group-based and patient-specific explanations. In the final step, we integrated a Large Language Model (LLM) called BioMistral for chatting functionally to talk to users based on the model output as a digital doctor for consultation. Our smart recommender system achieved high accuracy in predicting a patient risk level with an average AUC of 0.88 and can explain the results transparently. Moreover, a Django-based online application that uses patient data to update medical information about an individual’s heart attack risk was created. The LLM chatbot component would answer user questions about heart attacks and serve as a virtual companion on the route to heart health, our system also can locate nearby hospitals by applying Google Maps API and alert the users. The recommender system could improve patient management and lower heart attack risk while timely therapy aids in avoiding subsequent disabilities.

PREFER: A Pre-trained Model Recommendation Framework for Edge Computing Enabled Traffic Flow Prediction

The recent years have witnessed a surge in the development of traffic flow prediction methods, often deployed on cloud platforms to offer predictive services for entire transportation networks. However, the processes of training and executing a model for the entire traffic network are both time-consuming and computationally expensive. As a result, the utilization of edge servers for local sub-network prediction services has gained prominence. Nevertheless, training prediction models for numerous sub-networks within the extensive traffic network remains a time-intensive and computing resource-consuming task. To tackle this challenge, this paper introduces the Pre-trained model REcommendation Framework for traffic sub-nEtwork in tRaffic flow prediction (PREFER). PREFER trains a set of traffic flow prediction models on selected sub-networks, then recommends optimal pre-trained models for edge servers. The recommendation is specifically based on performance prediction, integrating neural collaborative filtering and traffic flow characteristics. Experiments conducted on real datasets reveal that the pre-trained models recommended by PREFER perform close to the actual optimal ones and significantly outperform existing recommendation algorithms.

Denoising Heterogeneous Graph Pre-training Framework for Recommendation

Denoising Heterogeneous Graph Pre-training Framework for Recommendation

An Author-Centric Framework Error Minimization in Scholarly Recommender System (Acfemsr)

In the current landscape of computational innovations, the internet hosts a vast repository of publications sourced from various channels. Consequently, researchers encounter unprecedented challenges in identifying publications relevant to their research interests. Navigating through the multitude of options provided by search engines is not only impractical but also prone to selection errors – termed Recommendation Error (RE). These experiences underscore the need for novel research avenues. Previous studies have proposed numerous recommendation frameworks exclusively for scientific paper recommendations. However, many of these approaches have been plagued by RE, thereby compromising the integrity of recommendation systems. Recommendation Errors typically arise from underutilization of key features in the recommendation process. To mitigate Recommendation Errors, this study leverages publicly available metadata features, including Title, Abstract, Author(s), and keywords. Feature vectors for each candidate paper (CP) and the paper of interest (POI) are computed using CountVectorizer, and cosine similarity formula is employed to identify similar papers suitable for recommendations. The effectiveness of the proposed framework is evaluated using Error evaluation metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Finally, the proposed Framework is compared against two previous Baseline approaches. The evaluation results demonstrate that the proposed approach exhibits lower Recommendation Errors compared to its baseline counterparts. Additionally, this research highlights the Author(s) feature as the most influential among the four features utilized by the Proposed Framework.

NFGCL: A Negative-sampling-free Graph Contrastive Learning Framework for Recommendation

Recently, Graph Contrastive Learning (GCL) has seen rapid growth in recommender systems. GCL-based Collaborative Filtering (CF) methods typically integrate the primary recommendation task with auxiliary CL tasks, which benefit from two key properties: alignment and uniformity. However, these methods often rely on graph augmentation and negative sampling, which are time-consuming and risk learning incorrect signals. To remedy these issues, we propose a novel Negative-sampling-Free Graph Contrastive Learning (NFGCL) framework to achieve high-quality representations without negative sampling or graph augmentation. Specifically, we use in-batch positive user-item pairs to construct a preference matrix where each element represents cosine similarity between a user and an item. We introduce a novel contrastive objective to make the preference matrix close to an identity matrix, drawing positive pairs closer and distancing negative pairs to achieve better alignment while improving uniformity. Additionally, we propose a simple yet effective representation-level augmentation method that integrates the normalized first-layer Graph Convolutional Networks (GCN) output into the final embeddings, further enhancing alignment. We also employ the uniformity loss to regulate the uniformity of user/item representation distribution. Extensive experiments on three public datasets demonstrate that our method outperforms baseline methods and effectively balances alignment and uniformity.

Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation

The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self-discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at https://github.com/sujieyang/MMNCL.

Laser-based disassembly of end-of-life automotive traction batteries: A systematic patent analysis

Battery recycling is a vital component in the decarbonization of the transportation sector. The disassembly step represents a pivotal element within the process chain for battery recycling, as it paves the way for subsequent steps. Semi-destructive disassembly technologies will be key to developing efficient disassembly processes for end-of-life automotive traction batteries. Laser-based separation technologies have emerged as a promising emerging technological approach. Following a systematic search in multiple databases, the obtained records underwent a comprehensive descriptive analysis in terms of both regional and historical context, while key inventors and assignees were identified. Furthermore, citation networks have been identified to provide an overview of the patent landscape and the interrelations within this field. Moreover, an analysis concerning the International Patent Classification and the Cooperative Patent Classification was conducted. An in-depth analysis of relevant patents provides insights into the specific techno-strategic elements currently pursued. The study yields an implication and recommendation framework for research, industry, and policy makers to drive the industrialization of laser-based disassembly technologies as an avenue for efficient end-of-life automotive traction battery disassembly of the future. This framework enables relevant stakeholders to drive their techno-strategic developments in the field of laser-based disassembly, resulting in enhanced laser-based semi-destructive disassembly technologies.

An intelligent java method name recommendation framework via two-phase neural networks

An intelligent java method name recommendation framework via two-phase neural networks

A unified framework for personalized learning pathway recommendation in e-learning contexts

A unified framework for personalized learning pathway recommendation in e-learning contexts

Multi-view graph contrastive representation learning for bundle recommendation

Bundle recommendation can recommend a collection of associated items that can be consumed together to a user rather than recommending these items separately, making it extremely suitable for some scenarios such as product bundle recommendation and game bundle recommendation. Recent bundle recommendation approaches consider auxiliary data to mitigate sparse user-bundle interactions. However, these approaches obtain the node embeddings directly from the established user-bundle graph and do not explicitly exploit the relationships between users (bundles) when constructing recommendation models. Moreover, bundle recommendation approaches based on graph contrastive learning usually construct contrastive views by randomly discarding nodes (edges) in the graph, while discarding some essential nodes or edges will destroy the structure of the original graph, thereby deteriorating the quality of the learned node embeddings. Aiming at these limitations, we propose a bundle recommendation approach based on multi-view graph contrastive representation learning. First, we present a multi-view modeling method to model the relations between entities as several views from different perspectives. These views serve as inputs of graph neural networks for graph representation learning and provide contrastive views for the contrastive learning tasks. Second, we propose a novel framework for bundle recommendation. This framework obtains the user (bundle) embeddings from different views by performing multi-view graph representation learning and enhances the learned user and bundle embeddings through a two-level contrastive learning strategy. On this basis, the enhanced user (bundle) embeddings are fused for prediction. Finally, we design a joint optimization objective to optimize the model parameters, combining the prediction loss that supports multiple negative samples and the contrastive losses. Experiments on the Netease and Youshu datasets reveal that our approach outperforms the state-of-the-art (SOTA) baselines. Furthermore, the average improvements of Recall@K and NDCG@K of our approach over the SOTA baselines are approximately 3.38% and 2.80% on Netease and 3.94% and 4.84% on Youshu.

Enhancing cross-domain recommendations: Leveraging personality-based transfer learning with probabilistic matrix factorization

The conventional method of computing personality scores through extensive questionnaire-based surveys poses practical challenges in real-world scenarios. An alternate route is to predict personality scores from user reviews by analyzing various linguistic features such as writing style, word choices, and specific phrases. However, the reviews are domain-dependent and classification models trained on one domain cannot be readily applied to other domains. To mitigate this challenge, we propose a cross-domain recommendation framework called PEMF-CD which leverages a novel mixing strategy to integrate user reviews from multiple domains with common joint embedding space and predict user personality scores using a transformer model. By capturing the underlying semantics and latent representations within the textual data, the transformer architecture can effectively model the linguistic cues to infer users’ personality traits, and the learning is transferred across domains. To further enhance the recommendation process, our model integrates personality-wise and rating pattern-based similarities of users into a probabilistic matrix factorization method that fosters user neighborhoods based on similarity scores among users. Comprehensive experiments were conducted using five real-world datasets from TripAdvisor and Amazon with varied numbers of users, items, and reviews of up to 44187, 26386, and 426791, respectively. The performance has been benchmarked against thirteen baseline algorithms and the experimental results demonstrate a significant improvements of up to 24.72%, 64.28%, 48.79%, and 61% in RMSE, and 55.9%, 76.7%, 67.6%, and 71.5% in MAE for a 90:10 train-test split with Digital Music, Fashion, Magazine Subscriptions and Video Games datasets from Amazon, respectively. Similar results have been observed for the 80:20 train-test split.

A framework for generating recommendations based on trust in an informal e-learning environment.

Rapid advancement in information technology promotes the growth of new online learning communities in an e-learning environment that overloads information and data sharing. When a new learner asks a question, how a system recommends the answer is the problem of the learner's cold start. In this article, our contributions are: (i) We proposed a Trust-aware Deep Neural Recommendation (TDNR) framework that addresses learner cold-start issues in informal e-learning by modeling complex nonlinear relationships. (ii) We utilized latent Dirichlet allocation for tag modeling, assigning tag categories to newly posted questions and ranking experts related to specific tags for active questioners based on hub and authority scores. (iii) We enhanced recommendation accuracy in the TDNR model by introducing a degree of trust between questioners and responders. (iv) We incorporated the questioner-responder relational graph, derived from structural preference information, into our proposed model. We evaluated the proposed model on the Stack Overflow dataset using mean absolute precision (MAP), root mean squared error (RMSE), and F-measure metrics. Our significant findings are that TDNR is a hybrid approach that provides more accurate recommendations compared to rating-based and social-trust-based approaches, the proposed model can facilitate the formation of informal e-learning communities, and experiments show that TDNR outperforms the competing methods by an improved margin. The model's robustness, demonstrated by superior MAE, RMSE, and F-measure metrics, makes it a reliable solution for addressing information overload and user sparsity in Stack Overflow. By accurately modeling complex relationships and incorporating trust degrees, TDNR provides more relevant and personalized recommendations, even in cold-start scenarios. This enhances user experience by facilitating the formation of supportive learning communities and ensuring new learners receive accurate recommendations.

Multimodal Pre-training for Sequential Recommendation via Contrastive Learning

Sequential recommendation systems often suffer from data sparsity, leading to suboptimal performance. While multimodal content, such as images and text, has been utilized to mitigate this issue, its integration within sequential recommendation frameworks remains challenging. Current multimodal sequential recommendation models are often unable to effectively explore and capture correlations among behavior sequences of users and items across different modalities, either neglecting correlations among sequence representations or inadequately capturing associations between multimodal data and sequence data in their representations. To address this problem, we explore multimodal pre-training in the context of sequential recommendation, with the aim of enhancing fusion and utilization of multimodal information. We propose a novel Multimodal Pre-training for Sequential Recommendation (MP4SR) framework, which utilizes contrastive losses to capture the correlation among different modality sequences of users, as well as the correlation among different modality sequences of users and items. MP4SR consists of three key components: (1) multimodal feature extraction; (2) a backbone network, Multimodal Mixup Sequence Encoder (M 2 SE); and (3) pre-training tasks. After utilizing pre-trained encoders to generate initial multimodal features of items, M 2 SE adopts a complementary sequence mixup strategy to fuse different modality sequences, and leverages contrastive learning to capture modality interactions at the sequence-to-sequence and sequence-to-item levels. Extensive experiments on four real-world datasets demonstrate that MP4SR outperforms state-of-the-art approaches in both normal and cold-start settings. We further highlight the efficacy of incorporating multimodal pre-training in sequential recommendation representation learning, serving as an effective regularizer and optimizing the parameter space for the recommendation task.

MF-GSLAE: A Multi-Factor User Representation Pre-training Framework for Dual-Target Cross-Domain Recommendation

MF-GSLAE: A Multi-Factor User Representation Pre-training Framework for Dual-Target Cross-Domain Recommendation

A multidimensional recommendation framework for identifying biological targets to aid the diagnosis and treatment of liver metastasis in patients with colorectal cancer

The quest to understand the molecular mechanisms of tumour metastasis and identify pivotal biomarkers for cancer therapy is increasing in importance. Single-omics analyses, constrained by their focus on a single biological layer, cannot fully elucidate the complexities of tumour molecular profiles and can thus overlook crucial molecular targets. In response to this limitation, we developed a multiobjective recommendation system (RJH-Metastasis 1.0) anchored in a multiomics knowledge graph to integrate genome, transcriptome, and proteome data and corroborative literature evidence and then conducted comprehensive analyses of colorectal cancer with liver metastasis (CRCLM). A total of 25 key genes significantly associated with CRCLM were recommended by our system, and GNB1, GATAD2A, GBP2, MACROD1, and EIF5B were further highlighted. Specifically, GNB1 presented fewer mutations but elevated RNA transcription and protein expression in CRCLM patients. The role of GNB1 in promoting the malignant behaviours of colon cancer cells was demonstrated via in vitro and in vivo studies. Aberrant expression of GNB1 could be regulated by METTL1-driven m7G modification. METTL1 knockdown decreased m7G modification in the 3’ UTR of GNB1, increasing its mRNA transcription and translation during liver metastasis. Furthermore, GNB1 induced the formation of an immunosuppressive microenvironment by promoting the CLEC2C-KLRB1 interaction between memory B cells and KLRB1+PD-1+CD8+ cells. GNB1 expression and the efficacy of PD-1 antibody-based treatment in CRCLM patients were significantly correlated. In summary, our recommendation system can be used for effective exploration of key molecules in colorectal cancer, among which GNB1 was identified as a critical CRCLM promoter and immunotherapy biomarker in colorectal cancer patients.

SABTR: semantic analysis-based tourism recommendation

Online tourism spot recommendations, as a key component of tourism services, aim to present travel options that align with users’ personal preferences. However, current recommendation systems often underperform due to the sparsity of tourism data and the wide variance in user preferences. To address this challenge, we propose a Semantic Analysis-Based Tourism Recommendation framework, abbreviated as SABTR (Semantic Analysis-Based Tourism Recommendation). The framework comprises two stages: Firstly, Latent Dirichlet Allocation (LDA) models are utilized to deeply mine data between users and attractions, constructing two core matrices: the user similarity matrix and the attraction similarity matrix. Secondly, based on the user similarity matrix, similarity calculation methods are applied to predict ratings for tourism spots that users have not yet evaluated. Simultaneously, within the attraction similarity matrix, probability distributions for each attraction across various thematic interests are calculated. When the system identifies a user’s interest in specific types of attractions, SABTR can select a series of related attractions from associated interest tags. Then, these candidate attractions are ranked according to both known and predicted user ratings, ultimately forming personalized attraction packages recommended to users. Extensive experiments have demonstrated that compared to existing tourism recommendation solutions, our method significantly improves the quality of attraction recommendations and enhances user satisfaction.

A Human Resource Evaluation and Recommendation System based on Big Data Mining

This investigation presents a paradigm-shifting Human Resource (HR) Assessment and Recommendation Framework, leveraging progressed huge information mining procedures. Drawing bits of knowledge from cybersecurity, healthcare, education, and further detecting spaces, our framework utilizes a different cluster of calculations, counting Arbitrary Forests, Support Vector Machines, K-Means Clustering, and a Feedforward Neural Organize. The comparative investigation uncovers the Feedforward Neural Network as the standout entertainer, emphasizing its various levels including learning for complicated design acknowledgement inside HR measurements. Uniquely, this framework draws on methodologies and insights from varied domains such as cybersecurity, healthcare, and education, applying these rich, interdisciplinary perspectives to HR analytics. This cross-pollination of ideas enables the framework to adopt sophisticated data mining and pattern recognition techniques that are not traditionally utilized within HR, offering new avenues for detecting and interpreting complex employee data patterns. Result values illustrate the system’s adequacy, with a precision of 88%, an accuracy of 90%, a review of 87%, and an F1 score of 88%. These measurements emphasize the system’s capacity to comprehensively assess worker execution, giving exact suggestions for key HR decision-making. Ethical contemplations, innovation acknowledgement, and custom-fitted proposal frameworks, propelled by related works, are coordinates to guarantee the system’s reasonability over assorted organizational settings. This research contributes to the advancing scene of HR administration, offering a spearheading arrangement for organizations looking for data-driven, comprehensive, and morally sound approaches to workforce optimization.

A novel framework for MOOC recommendation using sentiment analysis

A novel framework for MOOC recommendation using sentiment analysis

Multi-view graph contrastive learning for social recommendation.

With the rapid popularity of online social media, recommendation systems have increasingly harnessed social relations to enhance user-item interactions and mitigate the data sparsity issue. Beyond social connections, the semantic relatedness among items has emerged as a crucial factor in comprehending their inherent connections. In this work, we propose a novel Multi-view Contrastive learning framework for Social Recommendation, named MultiCSR. This framework adaptively incorporates user social networks and item knowledge graphs into modeling users preferences within recommendation systems. To facilitate the alignment of different views, we introduce a dedicated multi-view contrastive learning process that extracts rich information from each view and foster mutual enhancement. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of our framework over representative recommendation methods. Furthermore, ablation studies offer a deeper understanding of the mechanisms underlying our framework.