User Preference Model Research Articles

User preference modeling for movie recommendations based on deep learning

Current movie recommendation systems often struggle to capture complex user preferences and dynamics, primarily relying on content-based or collaborative filtering techniques. This research introduces a novel deep learning-powered method to enhance movie recommendation models, addressing the limitations of existing systems. By analyzing user behavior records and utilizing movie content elements, our method guarantees the greatest degree of customisation. In this study, we employ Artificial Intelligence (AI), graph-based techniques, and text mining to accurately estimate user preferences. While PageRank ranks the films based on their importance in the individual’s history of surfing, Convolutional Neural Network (CNN) predicts the possibility that the movie would be accepted. The experiments employed a dataset of 215 users’ browsing activity in 508 movie pages for evaluation. The presented approach achieved significant enhancement in recommendation precision and recall metrics resulting in 7.15% precision expansion and 5.19% recall growth which indicates its potential implementation in personalized movie recommendation systems.

Enhancing Recommendation Systems with Real-Time Adaptive Learning and Multi-Domain Knowledge Graphs

In the era of information explosion, recommendation systems play a crucial role in filtering vast amounts of content for users. Traditional recommendation models leverage knowledge graphs, sentiment analysis, social capital, and generative AI to enhance personalization. However, existing models still struggle to adapt dynamically to users’ evolving interests across multiple content domains in real-time. To address this gap, the cross-domain adaptive recommendation system (CDARS) is proposed, which integrates real-time behavioral tracking with multi-domain knowledge graphs to refine user preference modeling continuously. Unlike conventional methods that rely on static or historical data, CDARS dynamically adjusts its recommendation strategies based on contextual factors such as real-time engagement, sentiment fluctuations, and implicit preference drifts. Furthermore, a novel explainable adaptive learning (EAL) module was introduced, providing transparent insights into recommendations’ evolving nature, thereby improving user trust and system interpretability. To enable such real-time adaptability, CDARS incorporates multimodal sentiment analysis of user-generated content, behavioral pattern mining (e.g., click timing, revisit frequency), and learning trajectory modeling through time-aware embeddings and incremental updates of user representations. These dynamic signals are mapped into evolving knowledge graphs, forming continuously updated learning charts that drive more context-aware and emotionally intelligent recommendations. Our experimental results on datasets spanning social media, e-commerce, and entertainment domains demonstrate that CDARS significantly enhances recommendation relevance, achieving an average improvement of 7.8% in click-through rate (CTR) and 8.3% in user engagement compared to state-of-the-art models. This research presents a paradigm shift toward truly dynamic and explainable recommendation systems, creating a way for more personalized and user-centric experiences in the digital landscape.

Mind Individual Information! Principal Graph Learning for Multimedia Recommendation

Graph Neural Network (GNN)-based methods have recently emerged as effective approaches for multimedia recommendation. Typically, these methods employ message passing on the user-item interaction graph, and model user preferences by exploiting co-occurrence patterns. Despite their effectiveness, we argue that they insufficiently exploit the individual information, potentially limiting recommendation performance. To validate our argument, we first analyze existing methods from spectral graph theory. We identify that existing methods focus on capturing global structural features, but underutilize local structural features that convey individual information. Further detailed experiments reveal that such an underutilization leads to overly similar user preferences modeling. Furthermore, we propose a novel Principal Graph Learning (PGL) framework to address this issue. The idea is to enhance user preference modeling by effectively mining and utilizing principal local structural features. PGL first extracts the principal subgraph from the user-item interaction graph using two novel extraction operators: global-aware and local-aware subgraph extraction. It then employs message passing on the principal subgraph to comprehensively model user perference, with the aim of simultaneously capturing co-occurrence patterns and individual information. Compared to existing methods, PGL achieves an average performance improvement of 9%.

Counterfactual Task-augmented Meta-learning for Cold-start Sequential Recommendation

Cold-start sequential recommendation, where user interaction histories are sparse or minimal, remains a significant challenge in recommendation systems. Current meta-learning-based approaches rely heavily on the interaction histories of regular users to construct meta-tasks, aiming to acquire prior knowledge for cold-start adaptation. However, these methods often fail to account for preference discrepancies between regular and cold-start users, leading to biased preference modeling and suboptimal recommendations. To address this issue, we propose a novel counterfactual task-augmented meta-learning method for cold-start sequential recommendations. Our approach intervenes in user interaction histories to create counterfactual sequences that simulate potential but unrealized user behaviors, establishing counterfactual tasks within a meta-learning framework. Additionally, we aggregate meta-path neighbors to uncover latent relationships between items, enabling more detailed and accurate modeling of user preferences. Moreover, by integrating real and counterfactual task losses, we jointly optimize the model through a combination of global and local updates, enhancing its adaptability to cold-start scenarios. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art techniques, achieving superior results in cold-start sequential recommendation tasks.

LLM-Powered User Simulator for Recommender System

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user simulators generally suffer from significant limitations, including the opacity of user preference modeling and the incapability of evaluating simulation accuracy. In this paper, we introduce an LLM-powered user simulator to simulate user engagement with items in an explicit manner, thereby enhancing the efficiency and effectiveness of reinforcement learning-based recommender systems training. Specifically, we identify the explicit logic of user preferences, leverage LLMs to analyze item characteristics and distill user sentiments, and design a logical model to imitate real human engagement. By integrating a statistical model, we further enhance the reliability of the simulation, proposing an ensemble model that synergizes logical and statistical insights for user interaction simulations. Capitalizing on the extensive knowledge and semantic generation capabilities of LLMs, our user simulator faithfully emulates user behaviors and preferences, yielding high-fidelity training data that enrich the training of recommendation algorithms. We establish quantifying and qualifying experiments on five datasets to validate the simulator's effectiveness and stability across various recommendation scenarios.

BeFA: A General Behavior-driven Feature Adapter for Multimedia Recommendation

Multimedia recommender systems focus on utilizing behavioral information and content information to model user preferences. Typically, it employs pre-trained feature encoders to extract content features, then fuses them with behavioral features. However, pre-trained feature encoders often extract features from the entire content simultaneously, including excessive preference-irrelevant details.We speculate that it may result in the extracted features not containing sufficient features to accurately reflect user preferences. To verify our hypothesis, we introduce an attribution analysis method for visually and intuitively analyzing the content features. The results indicate that certain items’ content features exhibit the issues of information drift and information omission, reducing the expressive ability of features. Building upon this finding, we propose an effective and efficient general Behaviordriven Feature Adapter (BeFA) to tackle these issues. This adapter reconstructs the content feature with the guidance of behavioral information, enabling content features accurately reflecting user preferences. Extensive experiments demonstrate the effectiveness of the adapter across all multimedia recommendation methods.

Entire-Space Variational Information Exploitation for Post-Click Conversion Rate Prediction

In recommender systems, post-click conversion rate (CVR) estimation is an essential task to model user preferences for items and estimate the value of recommendations. Sample selection bias (SSB) and data sparsity (DS) are two persistent challenges for post-click conversion rate (CVR) estimation. Currently, entire-space approaches that exploit unclicked samples through knowledge distillation are promising to mitigate SSB and DS simultaneously. Existing methods use non-conversion, conversion, or adaptive conversion predictors to generate pseudo labels for unclicked samples. However, they fail to consider the unbiasedness and information limitations of these pseudo labels. Motivated by such analysis, we propose an entire-space variational information exploitation framework (EVI) for CVR prediction. First, EVI uses a conditional entire-space CVR teacher to generate unbiased pseudo labels. Then, it applies variational information exploitation and logit distillation to transfer non-click space information to the target CVR estimator. We conduct extensive offline experiments on six large-scale datasets. EVI demonstrated a 2.25% average improvement compared to the state-of-the-art baselines.

Next Point of Interest (POI) Recommendation System Driven by User Probabilistic Preferences and Temporal Regularities

The Point of Interest (POI) recommendation system is a critical tool for enhancing user experience by analyzing historical behaviors, social network data, and real-time location information with the increasing demand for personalized and intelligent services. However, existing POI recommendation systems face three major challenges: (1) oversimplification of user preference modeling, limiting adaptability to dynamic user needs, (2) lack of explicit arrival time modeling, leading to reduced accuracy in time-sensitive scenarios, and (3) complexity in trajectory representation and spatiotemporal mining, posing difficulties in handling large-scale geographic data. This paper proposes NextMove, a novel POI recommendation model that integrates four key modules to address these issues. Specifically, the Probabilistic User Preference Generation Module first employs Latent Dirichlet Allocation (LDA) and a user preference network to model user personalized interests dynamically by capturing latent geographical topics. Secondly, the Self-Attention-based Arrival Time Prediction Module utilizes a Multi-Head Attention Mechanism to extract time-varying features, improving the precision of arrival time estimation. Thirdly, the Transformer-based Trajectory Representation Module encodes sequential dependencies in user behavior, effectively capturing contextual relationships and long-range dependencies for accurate future location forecasting. Finally, the Next Location Feature-Aggregation Module integrates the extracted representation features through an FC-based nonlinear fusion mechanism to generate the final POI recommendation. Extensive experiments conducted on real-world datasets demonstrate the superiority of the proposed NextMove over state-of-the-art methods. These results validate the effectiveness of NextMove in modeling dynamic user preferences, enhancing arrival time prediction, and improving POI recommendation accuracy.

A Bayesian Statistical Personalized Recommendation System: Model Construction and Evaluation in Big Data Environment

In the era of big data, personalized recommendation systems have become indispensable for enhancing user experience and driving engagement across various platforms. This paper introduces a Bayesian statistical personalized recommendation system designed to effectively model user preferences in a big data environment. Leveraging the principles of Bayesian statistics, the system is capable of handling uncertainty and updating user profiles based on continuous feedback. The paper outlines the theoretical framework, including the derivation of Bayesian updating rules and the selection of appropriate priors and likelihood functions. A comprehensive evaluation of the system is conducted through offline and online methods, with a focus on precision, recall, and F1-score as key performance indicators. The system's performance is further illustrated through case studies in e-commerce, social media, and music streaming services. The paper concludes with a discussion on the system's scalability, performance optimization, and potential future enhancements, emphasizing the importance of ethical considerations in the development of personalized recommendation systems.

Group attention for collaborative filtering with sequential feedback and context aware attributes

The deployment of recommender systems has become increasingly widespread, leveraging users’ past behaviors to predict future preferences. Collaborative Filtering (CF) is a foundational method that depends on user-item interactions. However, due to individual variations in rating patterns and dynamic interplays of item attributes, it becomes challenging to model user preferences accurately. Existing attention-based methods often do not prove very reliable in capturing fine-grained intricate item-attribute relationships or in furnishing global explanations across temporal, attribute, and item levels. To overcome these limitations, we propose GCORec, a novel framework that integrates short- and long-term user preferences using innovative mechanisms. A Hierarchical Attention Network returns a highly complicated item-attribute relationship, while a Group-wise enhancement mechanism improves the representation of features by reducing noise while emphasizing important attributes. Likewise, an Attentive Bi-Directional GRU does splendidly when trying to model long-term user behaviors while the Collaborative Multi Head Attention Mechanism evaluates the effect of item attributes on user preferences. Experiments conducted on benchmark datasets demonstrate the advantages of the proposed GCORec. Specifically, GCORec achieves improvements over the best baselines by 3.03% and 1.49% in terms of Recall@20, and by 5.88% and 5.92% in terms of NDCG@20 on real-world datasets with different levels of sparsity and domain features.

Graph Neural Network-Based User Preference Model for Social Network Access Control

Graph Neural Network-Based User Preference Model for Social Network Access Control

Interactive Preference Elicitation under Noisy Preference Models: an Efficient Non-Bayesian Approach

Interactive Preference Elicitation under Noisy Preference Models: an Efficient Non-Bayesian Approach

Study on a User Preference Conversational Recommender Based on a Knowledge Graph

In the era of information explosion, as a form of personalized recommendation, dialogue recommendation systems provide users with personalized recommendation services through natural language interaction. However, in the face of complex user preferences, the traditional dialogue recommendation system has the problem of a poor recommendation effect. To solve these problems, this paper proposes a user preference dialogue recommendation algorithm (KGCR) based on a knowledge graph, which aims to enhance the understanding of user preferences through the semantic information of the knowledge graph and improve the relevance and accuracy of recommendations. This paper proposes a personalized conversation recommendation algorithm framework for user preference modeling. The framework uses a bilinear model attention mechanism and self-attention hierarchical coding structure to model user preferences to rank and recommend candidate items. By introducing rich user-related information, the recommendation results are not only more in line with users’ individual preferences but also have better diversity, effectively reducing the negative impact of information cocoons and other phenomena. At the same time, the experimental results on the open dataset prove the effectiveness and accuracy of the proposed model in the personalized conversation recommendation task.

Aspect-Enhanced Explainable Recommendation with Multi-modal Contrastive Learning

Explainable recommender systems ( ERS ) aim to enhance users’ trust in the systems by offering personalized recommendations with transparent explanations. This transparency provides users with a clear understanding of the rationale behind the recommendations, fostering a sense of confidence and reliability in the system’s outputs. Generally, the explanations are presented in a familiar and intuitive way, which is in the form of natural language, thus enhancing their accessibility to users. Recently, there has been an increasing focus on leveraging reviews as a valuable source of rich information in both modeling user-item preferences and generating textual interpretations, which can be performed simultaneously in a multi-task framework. Despite the progress made in these review-based recommendation systems, the integration of implicit feedback derived from user-item interactions and user-written text reviews has yet to be fully explored. To fill this gap, we propose a model named SERMON (A s pect-enhanced E xplainable R ecommendation with M ulti-modal C o ntrast Lear n ing). Our model explores the application of multimodal contrastive learning to facilitate reciprocal learning across two modalities, thereby enhancing the modeling of user preferences. Moreover, our model incorporates the aspect information extracted from the review, which provides two significant enhancements to our tasks. Firstly, the quality of the generated explanations is improved by incorporating the aspect characteristics into the explanations generated by a pre-trained model with controlled textual generation ability. Secondly, the commonly used user-item interactions are transformed into user-item-aspect interactions, which we refer to as interaction triple, resulting in a more nuanced representation of user preference. To validate the effectiveness of our model, we conduct extensive experiments on three real-world datasets. The experimental results show that our model outperforms state-of-the-art baselines, with a 2.0% improvement in prediction accuracy and a substantial 24.5% enhancement in explanation quality for the TripAdvisor dataset.

News Recommendation Method Based on Candidate-Aware Long- and Short-Term Preference Modeling

Personalized news recommendations focus on providing users with news that fits their interests and alleviates their information overload. User preference modeling is crucial for achieving personalized news recommendations, and user preferences are usually expressed as long-term and short-term user preferences. Existing news recommendation methods have difficulty accurately matching user preferences with candidate news, which is the main challenge plaguing the news recommendation field. For this purpose, we propose a novel news recommendation method based on candidate-aware long- and short-term preference modeling, named NRCLS. The method contains: (1) a Candidate-Enhanced graph attention network, which learns high-order structural information in graphs, mines the potential relationship between long-term user preferences and candidate news; and (2) a candidate-aware attention network that incorporates news subtopics. In this network, the dynamic impact of candidate news on short-term user preferences is considered. Results on real-world datasets demonstrate the effectiveness of our proposed method in improving the performance of news recommendations. We have also conducted several ablation studies that demonstrate the effectiveness of the core module in NRCLS.

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.

Edge Computing Enabled Lightweight Neural Network for User Preference Based Customization Recommendation Mechanism

ABSTRACTThe rapid development of computer and network technologies has led to an explosion of information, ushering in an era of e‐commerce dominated by online shopping. This shift underscores the need for precise, efficient, and customized recommendation systems. Traditional search engines struggle to cater to users' diverse information needs, leading to information overload and “dark information.” The customization recommendation systems emerge as a solution, leveraging user data to discern product correlations and formulate recommendations. However, remote server latency poses a challenge for real‐time recommendations. In this regard, we necessitate the exploration of edge computing and propose an edge computing enabled lightweight neural network for a user preference‐based customization recommendation mechanism including the edge computing based user preference model, the customization preference relevance, and the lightweight neural network‐based customization recommendation. In particular, the user preference model quantifies user affinity toward products and a preference connection pattern that ensures a clean relationship map by mitigating attribute interference, while the customization recommendation integrates back‐propagation for nonlinear input–output mappings, achieving generalization while maintaining efficiency. Experimental results indicate that the proposed mechanism can enhance customization and efficiency in recommendation systems when compared to the state‐of‐the‐art methods in terms of the recommendation accuracy, error rate as well as iterations.

Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models

Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents. However, the aspects and intents are inferred directly from user reviews or behavior patterns, suffering from the data noise and the data sparsity problem. Furthermore, it is difficult to understand the reasons behind recommendations due to the challenges of interpreting implicit aspects and intents. To address these constraints, we harness the sentiment analysis capabilities of Large Language Models (LLMs) to enhance the accuracy and interpretability of the conventional recommendation methods. Specifically, inspired by the deep semantic understanding offered by LLMs, we introduce a chain-based prompting strategy to uncover semantic aspect-aware interactions, which provide clearer insights into user behaviors at a fine-grained semantic level. To incorporate the rich interactions of various aspects, we propose the simple yet effective Semantic Aspect-based Graph Convolution Network (short for SAGCN). By performing graph convolutions on multiple semantic aspect graphs, SAGCN efficiently combines embeddings across multiple semantic aspects for final user and item representations. The effectiveness of the SAGCN was evaluated on four publicly available datasets through extensive experiments, which revealed that it outperforms all other competitors. Furthermore, interpretability analysis experiments were conducted to demonstrate the interpretability of incorporating semantic aspects into the model.

Multimodal Recommender Systems: A Survey

The recommender system (RS) has been an integral toolkit of online services. They are equipped with various deep learning techniques to model user preference based on identifier and attribute information. With the emergence of multimedia services, such as short videos, news, and and so on, understanding these contents while recommending becomes critical. Besides, multimodal features are also helpful in alleviating the problem of data sparsity in RS. Thus, M ultimodal R ecommender S ystem (MRS) has attracted much attention from both academia and industry recently. In this article, we will give a comprehensive survey of the MRS models, mainly from technical views. First, we conclude the general procedures and major challenges for MRS. Then, we introduce the existing MRS models according to four categories, i.e., Modality Encoder , Feature Interaction , Feature Enhancement , and Model Optimization . Besides, to make it convenient for those who want to research this field, we also summarize the dataset and code resources. Finally, we discuss some promising future directions of MRS and conclude this article. To access more details of the surveyed articles, such as implementation code, we open source a repository. 1

Efficient and adaptive secure cross-domain recommendations

Efficient and adaptive secure cross-domain recommendations