Traditional Recommendation Models Research Articles

Enhancing Recommendation Diversity and Novelty with Bi-LSTM and Mean Shift Clustering

In the digital age, personalized recommendation systems have become crucial for information dissemination and user experience. While traditional systems focus on accuracy, they often overlook diversity, novelty, and serendipity. This study introduces an innovative recommendation system model, Time-based Outlier Aware Recommender (TOAR), designed to address the challenges of content homogenization and information bubbles in personalized recommendations. TOAR integrates Neural Matrix Factorization (NeuMF), Bidirectional Long Short-Term Memory Networks (Bi-LSTM), and Mean Shift clustering to enhance recommendation accuracy, novelty, and diversity. The model analyzes temporal dynamics of user behavior and facilitates cross-domain knowledge exchange through feature sharing and transfer learning mechanisms. By incorporating an attention mechanism and unsupervised clustering, TOAR effectively captures important time-series information and ensures recommendation diversity. Experimental results on a news recommendation dataset demonstrate TOAR’s superior performance across multiple metrics, including AUC, precision, NDCG, and novelty, compared to traditional and deep learning-based recommendation models. This research provides a foundation for developing more intelligent and personalized recommendation services that balance accuracy with content diversity.

RGMeta: Enhancing Cold-Start Recommendations with a Residual Graph Meta-Embedding Model

Traditional recommendation models grapple with challenges such as the scarcity of similar user or item references and data sparsity, rendering the cold-start problem particularly formidable. Meta-learning has emerged as a promising avenue to address these issues, particularly in solving the item cold-start problem by generating meta-embeddings for new items as their initial ID embeddings. This approach has shown notable success in enhancing the accuracy of click-through rate predictions. However, prevalent meta-embedding models often focus solely on the attribute features of the item, neglecting crucial user information associated with it during the generation of initial ID embeddings for new items. This oversight hinders the exploitation of valuable user-related information to enhance the quality and accuracy of the initial ID embedding. To tackle this limitation, we introduce the residual graph meta-embedding model (RGMeta). RGMeta adopts a comprehensive approach by considering both the attribute features and target users of both old and new items. Through the integration of residual connections, the model effectively combines the representation information of the old neighbor items with the intrinsic features of the new item, resulting in an improved initial ID embedding generation. Experimental results demonstrate that RGMeta significantly enhances the performance of the cold-start phase, showcasing its effectiveness in overcoming challenges associated with sparse data and limited reference points. Our proposed model presents a promising step forward in leveraging both item attributes and user-related information to address cold-start problems in recommendation systems.

A Comment Aspect-Level User Preference Transfer Model for Cross-Domain Recommendations

Traditional cross-domain recommendation models make it difficult to deeply mine users' aspect-level preferences from comment information due to existing problems such as polysemy of comment text, sparse comment data, and user cold start. A Cross-Domain Recommender (CDR) model that integrates comment knowledge enhancement and aspect-level user preference transfer (C-KE-AUT) was proposed to address the above issues. Firstly, an aspect-level user preference extraction model was constructed by combining the RoBERTa word embedding model, high-level feature representation based on Transformer, and aspect-level attention-learning methods. Then, a user aspect-level preference cross-domain transfer model was constructed based on a two-stage generative adversarial network that can transfer the aspect-level interest preferences of users in the source domain to the target domain with sparse data. The experimental results on the Amazon 2018 comment dataset indicated that the recommendation performance of the proposed C-KE-AUT model was significantly superior to other advanced comparative models.

Cultural tourism attraction recommendation model based on optimized weighted association rule algorithm

To address the challenge of users selecting rich tourism resources, this study proposes a model for cultural tourism attraction recommendation using an optimized weighted association rule algorithm. This model includes time and season weight for tourist attraction recommendations. This model proposes improvement methods to address some inherent issues in traditional tourism recommendation models. Firstly, it constructed a recommendation model for cultural tourism attractions, and then optimized the weighted association rule algorithm by incorporating dynamic time weights. It takes into account the user's intended time in the recommendation outcome. Moreover, it incorporated seasonal weights to optimize the weighted rule algorithm for factors such as user travel time and the attractions' peak season during the recommendation process. The experiment indicates that the F1 value of the improved algorithm model proposed in this study reaches 0.952, the accuracy reaches 0.985, the area under the curve reaches 0.955, the Recall value reaches 0.812, and the fitting degree reaches 0.971. The results suggest that the proposed cultural tourism attraction recommendation model, based on an optimized weighted association algorithm, performs well in recommending tourist destinations. This model can have a positive impact on the development of the tourism industry.

Learning-to-rank debias with popularity-weighted negative sampling and popularity regularization

Most learning-to-rank recommendation models assume users prefer interacted items more than non-interacted ones. All non-interacted items have the same chance to be selected as negative samples. However, the observed interaction data usually shows long-tailed distributions, making traditional recommendation models trained on such data tend to rank popular items higher than users’ true preference and degrading the performance of recommender systems. Some existing debias methods focus on eliminating such popularity bias, while simply removing all the popularity bias may diminish recommendation accuracy because popularity also contains some useful information implying item attractiveness, making it pivotal to handling popularity bias in proper ways. In this paper, popularity is recognized to have both positive and negative effects on recommendation. The positive effect of popularity should be amplified while the negative effect should be mitigated. Therefore, this paper proposes two novel schemes to distinguish the positive and negative impact of popularity in learning-to-rank models. First, we propose a popular-weighted sampler to sample non-interacted popular items from users’ collaborative items as negative samples with higher probabilities. We believe that if a popular item is collaboratively similar to a user but not interacted with by him, it is more likely to be a true negative sample for the user. We sample such items with higher probabilities to mitigate the harmful negative popularity bias. Second, popularity could be a significant indicator of items’ intrinsic quality. Hence, we design a popularity regularization scheme to capture item attractiveness, prompting cold-start users to prefer popular items. Finally, we conduct extensive experiments to evaluate the performance of the proposed schemes. Experimental results demonstrate that our approach can improve existing learning-to-rank models’ performance and outperform state-of-the-art debias methods.

Data statistical analysis on Amazon e-commerce platform for recommender system

Recommendation systems are a crucial element in engaging users and maintaining their engagement with e-commerce platforms. By recommending products or services that are likely to be relevant to each user's interests and preferences, the system can help maintain user interest and encourage them to spend more time on the platform. This work analyzes the principles of several off-the-shelf recommendation models, including the collaborative filtering model, the singular value decomposition model, and the rating-based collaborative filtering model. These models play a crucial role in the field of recommendation systems for e-commerce. To gain further insights from the comments of various merchandise items, sentiment analysis techniques and word cloud analysis are applied. Evaluation of these results demonstrates the critical role of recommender systems in shaping the future landscape of e-commerce. Sentiment analysis allows us to identify patterns in user feedback and understand how different factors influence user satisfaction with products or services. Word cloud analysis provides a visual representation of the most frequently mentioned features or keywords in the comments, allowing us to identify trends and patterns in user behavior. By combining these techniques with traditional recommendation models, more accurate and personalized recommendations could be made that better meet user needs and enhance their shopping experience on e-commerce platforms.

Weighted Matrix Factorization Recommendation Model Incorporating Social Trust

Utilizing user social networks can unearth more effective information to improve the performance of traditional recommendation models. However, existing models often solely utilize trust relationships and information, lacking efficient models that integrate with user historical ratings, as well as methods for accurately adjusting weights and filtering interfering data. This leads to the models’ inability to efficiently use social networks to enhance recommendation accuracy. Therefore, this paper proposes a novel trust-based weighted matrix factorization recommendation model, Trust-WMF. Initially, the model preliminarily calculates users’ predicted ratings for items using trust relationships in the social network and user similarity relations in user historical ratings, simultaneously dynamically integrating these two parts of predicted ratings using adaptive weights. Subsequently, the ratings are incorporated into an improved weighted matrix factorization model, allowing them to have different weights in training compared to user historical ratings. This enriches matrix information and reduces the impact of noise data, thus forming an efficient, unified, and trustworthy recommendation model. Finally, the model was compared and validated on the Epinions and Ciao datasets, with results confirming its efficiency.

Research and Application of Edge Computing and Deep Learning in a Recommender System

Recommendation systems play a pivotal role in improving product competitiveness. Traditional recommendation models predominantly use centralized feature processing to operate, leading to issues such as excessive resource consumption and low real-time recommendation concurrency. This paper introduces a recommendation model founded on deep learning, incorporating edge computing and knowledge distillation to address these challenges. Recognizing the intricate relationship between the accuracy of deep learning algorithms and their complexity, our model employs knowledge distillation to compress deep learning. Teacher–student models were initially chosen and constructed in the cloud, focusing on developing structurally complex teacher models that incorporate passenger and production characteristics. The knowledge acquired from these models was then transferred to a student model, characterized by weaker learning capabilities and a simpler structure, facilitating the compression and acceleration of an intelligent ranking model. Following this, the student model underwent segmentation, and certain computational tasks were shifted to end devices, aligning with edge computing principles. This collaborative approach between the cloud and end devices enabled the realization of an intelligent ranking for product listings. Finally, a random selection of the passengers’ travel records from the last five years was taken to test the accuracy and performance of the proposed model, as well as to validate the intelligent ranking of the remaining tickets. The results indicate that, on the one hand, an intelligent recommendation system based on knowledge distillation and edge computing successfully achieved the concurrency and timeliness of the existing remaining ticket queries. Simultaneously, it guaranteed a certain level of accuracy, and reduced computing resource and traffic load on the cloud, showcasing its potential applicability in highly concurrent recommendation service scenarios.

Causal Disentanglement for Semantic-Aware Intent Learning in Recommendation

Traditional recommendation models trained on observational interaction data have generated large impacts in a wide range of applications, it faces bias problems that cover users true intent and thus deteriorate the recommendation effectiveness. Existing methods tracks this problem as eliminating bias for the robust recommendation, e.g., by re-weighting training samples or learning disentangled representation. The disentangled representation methods as the state-of-the-art eliminate bias through revealing cause-effect of the bias generation. However, how to design the semantics-aware and unbiased representation for users true intents is largely unexplored. To bridge the gap, we are the first to propose an unbiased and semantics-aware disentanglement learning called CaDSI (Causal Disentanglement for Semantics-Aware Intent Learning) from a causal perspective. Particularly, CaDSI explicitly models the causal relations underlying recommendation task, and thus produces semantics-aware representations via disentangling users true intents aware of specific item context. Moreover, the causal intervention mechanism is designed to eliminate confounding bias stemmed from context information, which further to align the semantics-aware representation with users true intent. Extensive experiments and case studies both validate the robustness and interpretability of our proposed model.

A Study on the Construction of Translation Curriculum System for English Majors from the Perspective of Human-Computer Interaction

This paper proposes a collaborative human-computer interaction recommendation model for English major translation courses to address the problems of poor course recommendation and lack of robustness to noisy data in traditional recommendation models for English major translation courses. First, a new data enhancement method is proposed for the bipartite graph structure. Then, the enhanced data is fed into a graph convolutional neural network for node feature extraction to obtain node representations of users and items. A recommendation supervision task and an auxiliary task for contrast learning are constructed for joint optimization. The human-computer interaction model of the knowledge graph is designed, and the dialogue entities are embedded in the knowledge graph ripple network to obtain potentially interesting content for students. Finally, the student interaction content and node representations are combined to obtain the optimal translation course recommendation. The experimental results indicate that the proposed model in this work is capable of producing higher-quality English major course recommendations and beats other current models. This model is suitable for English primary translation course content recommendation and helps to improve students’ translation ability.

PERSONALIZED USER FEATURE SIMILARITY SUPPORTED COLLABORATIVE FILTERING AND WEB USAGE MINING FOR PAGE RECOMMENDATION

The rapid growth of the web has run to a considerable increase in information dissemination. Freshly, Research on hybrid personalized recommendation systems mainly addresses two problems: prediction and completion of sparse data, and the user s personalized recommendation. To address the issue of high data sparsity and low recommendation accuracy in the traditional service recommendation models, this study presents a hybrid personalized collaborative filtering model for page recommendation based on collaborative filtering by introducing user preferences. The example verified that the hybrid personalized recommendation system based model can effectively reduce the data sparsity and increase the accuracy of the prediction.In this work, the efficacy of collaborative filtering and web usage for recommender system is investigated and proposed. The experimental results demonstrate that the proposed WUM improves the performance of the recommendations.

Research on Intelligent Recommendation Model of E-Commerce Commodity Based on Feature Selection and Deep Belief Network

Due to the complexity and uncertainty of customer demand behavior, it was often difficult to obtain satisfactory recommendation results by using the existing online commodity recommendation systems. Therefore, a network commodity intelligent recommendation model based on feature selection and deep belief network was proposed. Based on the basic structure and function of the existing recommendation systems, this paper expounded the interaction process between customers, e-commerce platforms, enterprises, and the recommendation system. By analyzing the internal relationship between customer demand and commodity recommendation, the relationship model between customer demand and commodity recommendation was established. After analyzing the characteristics of customers’ demand for goods, a data mining method was used to classify the characteristics of customers’ demand behavior, and a feature selection method based on deep belief network (DBN) was proposed to obtain the main information conducive to commodity recommendation. Finally, an e-commerce commodity recommendation algorithm based on feature selection and deep belief network was proposed. The experimental results showed that the network commodity recommendation model proposed in this paper can not only provide customers with satisfactory recommendation results but also has better performance than other traditional recommendation models. The recommendation model proposed in this paper can support different e-commerce website recommendation systems.

RGCF: Refined graph convolution collaborative filtering with concise and expressive embedding

Graph Convolution Networks (GCNs) have attracted significant attention and have become the most popular method for learning graph representations. In recent years, many efforts have focused on integrating GCNs into recommender tasks and have made remarkable progress. At its core is to explicitly capture the high-order connectivities between nodes in the user-item bipartite graph. However, we found some potential drawbacks existed in the traditional GCN-based recommendation models are that the excessive information redundancy yield by the nonlinear graph convolution operation reduces the expressiveness of the resultant embeddings, and the important popularity features that are effective in sparse recommendation scenarios are not encoded in the embedding generation process. In this work, we develop a novel GCN-based recommendation model, named Refined Graph convolution Collaborative Filtering (RGCF), where a refined graph convolution structure is designed to match non-semantic ID inputs. In addition, a new fine-tuned symmetric normalization is proposed to mine node popularity characteristics and further incorporate the popularity features into the embedding learning process. Extensive experiments were conducted on three public million-size datasets, and the RGCF improved by an average of 13.45% over the state-of-the-art baseline. Further comparative experiments validated the effectiveness and rationality of each part of our proposed RGCF. We released our code at https://github.com/hfutmars/RGCF.

Deep learning based dual encoder retrieval model for citation recommendation

Citation recommendation recommends relevant documents to users based on their inputs and other information. Many traditional citation recommendation models use keywords to describe item attributes and ignore the semantics of sequences, which cause the relevance of the search results unsatisfactory. This paper proposes a deep-learning-based dual encoder retrieval (DER) model, which combines a text representation technique and a sentence pair matching approach, to improve the performance of citation recommendation. First, an input query and paper titles from publication databases are encoded to semantic vectors separately by two deep-learning-based encoders. Second, the semantic vector of the input query is matched with vectors that representing papers in the published databases by the multilayer perceptron approach to compute similarity scores. Finally, a list of documents, which are sorted in descending order of similarity scores, is generated. To validate the effectiveness of the proposed approach, it is compared with five baselines using a citation dataset. The results show that the proposed model achieves the best performance in terms of accuracy, recall, F1-measure, and AUC. In addition, we compare the DER (Glove) model with Google Scholar using a small example of twenty articles. The DER (Glove) model outperformed Google Scholar in seven recommendations, and tied in ten recommendations.

Hybrid collaborative filtering model for consumer dynamic service recommendation based on mobile cloud information system

The rapid development of the web has led to a considerable increase in information dissemination. Recently, personalized web service recommendation has become a popular research area in service computing. Research on web service recommendation systems mainly addresses two problems: prediction and completion of sparse QoS data, and the user's personalized recommendation. To address the issue of high data sparsity and low recommendation accuracy in the traditional service recommendation models under mobile cloud, this study presents a hybrid collaborative filtering model for consumer service recommendation based on mobile cloud by introducing user preferences. The example verified that the service recommendation based on the model can effectively reduce the data sparsity and increase the accuracy of the prediction.

Towards Non-Linear Social Recommendation Using Gaussian Process

Recent research on recommender systems has proved that by leveraging social network information, the quality of recommendations can be evidently improved. Traditional social recommendation models typically <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">linearly</i> combine social network information. For instance, matrix factorization based models linearly combine latent factors of relevant users and items. However, in practice, the multifaceted social relations are so complex that simple linear combination may not be able to reasonably organize such information for accurate social recommendation. On the other hand, existing deep learning based non-linear methods lack systematic modeling of user-item-friend relations. To handle these issues, we propose a novel, non-linear latent factor model for social recommendations leveraging Gaussian process. By introducing a social-aware covariance function, we organize individual users’ past feedback, as well as the associated social information (e.g., friends’ feedback to the same items) into a covariance matrix, which non-linearly and systematically learns the complex interactions among users, their interacted items and their friends’ opinions. A stochastic gradient descent based optimization algorithm is developed to fit the model. Extensive experiments conducted on three real-world datasets demonstrate that the proposed model outperforms the state-of-the-art social recommendation models and Gaussian process based models.

A survey of recommender systems with multi-objective optimization

Recommender systems have been widely applied to several domains and applications to assist decision making by recommending items tailored to user preferences. One of the popular recommendation algorithms is the model-based approach which optimizes a specific objective to improve the recommendation performance. These traditional recommendation models usually deal with a single objective, such as minimizing the prediction errors or maximizing the ranking quality of the recommendations. In recent years, there is an emerging demand for multi-objective recommender systems in which multiple objectives are considered and the recommendations can be optimized by the multi-objective optimization. For example, a recommendation model may be built by optimizing multiple metrics, such as accuracy, novelty and diversity of the recommendations. The multi-objective optimization methodologies have been well developed and applied to the area of recommender systems. In this article, we provide a comprehensive literature review of the multi-objective recommender systems. Particularly, we identify the circumstances in which a multi-objective recommender system could be useful, summarize the methodologies and evaluation approaches in these systems, point out existing challenges or weaknesses, finally provide the guidelines and suggestions for the development of multi-objective recommender systems.

Automatic Generation of Meta-Path Graph for Concept Recommendation in MOOCs

In MOOCs, generally speaking, curriculum designing, course selection, and knowledge concept recommendation are the three major steps that systematically instruct users to learn. This paper focuses on the knowledge concept recommendation in MOOCs, which recommends related topics to users to facilitate their online study. The existing approaches only consider the historical behaviors of users, but ignore various kinds of auxiliary information, which are also critical for user embedding. In addition, traditional recommendation models only consider the immediate user response to the recommended items, and do not explicitly consider the long-term interests of users. To deal with the above issues, this paper proposes AGMKRec, a novel reinforced concept recommendation model with a heterogeneous information network. We first clarify the concept recommendation in MOOCs as a reinforcement learning problem to offer a personalized and dynamic knowledge concept label list to users. To consider more auxiliary information of users, we construct a heterogeneous information network among users, courses, and concepts, and use a meta-path-based method which can automatically identify useful meta-paths and multi-hop connections to learn a new graph structure for learning effective node representations on a graph. Comprehensive experiments and analyses on a real-world dataset collected from XuetangX show that our proposed model outperforms some state-of-the-art methods.

FSCR: A Deep Social Recommendation Model for Misleading Information

The popularity of intelligent terminals and a variety of applications have led to the explosive growth of information on the Internet. Some of the information is real, some is not real, and may mislead people’s behaviors. Misleading information refers to false information made up by some malicious marketer to create panic and seek benefits. In particular, when emergency events break out, many users may be misled by the misleading information on the Internet, which further leads them to buy things that are not in line with their actual needs. We call this kind of human activity ‘emergency consumption’, which not only fails to reflect users’ true interests but also causes the phenomenon of user preference deviation, and thus lowers the accuracy of the personal recommender system. Although traditional recommendation models have proven useful in capturing users’ general interests from user–item interaction records, learning to predict user interest accurately is still a challenging problem due to the uncertainty inherent in user behavior and the limited information provided by user–item interaction records. In addition, to deal with the misleading information, we divide user information into two types, namely explicit preference information (explicit comments or ratings) and user side information (which can show users’ real interests and will not be easily affected by misleading information), and then we create a deep social recommendation model which fuses user side information called FSCR. The FSCR model is significantly better than existing baseline models in terms of rating prediction and system robustness, especially in the face of misleading information; it can effectively identify the misleading users and complete the task of rating prediction well.

Generating Knowledge-Based Attentive User Representations for Sparse Interaction Recommendation

Deep neural networks (DNNs) have been widely imported into collaborative-filtering (CF) based recommender systems and yielded remarkable superiority over traditional recommendation models. However, most deep CF-based models perform weakly when observed user-item interactions are sparse since user preferences and item characteristics are inferred mainly based on observed (historical) interactions. To address this problem, we propose a deep knowledge-enhanced recommendation model in this paper. Specifically, to augment user/item representations in the scenario of sparse historical user-item interactions, we first incorporate the knowledge from open knowledge graphs and personal information of users as side information, from which sufficient features of users and items are extracted. Second, to well capture shifted user preferences, we leverage a memory component constituted by recently interacted items rather than all historical ones. Third, attentive user representations are generated by attention mechanism to capture the diversity of user preferences. Furthermore, we build a convolutional neural network to pool the latent features in user representations for better user modeling, which enhances recommendation performance further. Our extensive experiments conducted against two real-world datasets, i.e., Douban movie and NetEase music, demonstrate our model’s remarkable superiority over the state-of-the-art deep recommendation models.