Recommendation Model Research Articles

Deep Learning Social Filtering Model for Event Recommendation Services

In the contemporary time, technology has made the determination and discovery of human preferences, priorities and personal inclinations possible through the use of recommender systems. Activities of users on the internet can be monitored, extracted, stored, analyzed and used by the recommender systems for suggesting future events to users on the web. This paper aims at developing and analyzing a model for event services recommendation for visitors to events. Event seekers, organizers and event service providers get notified, plan and book for upcoming events from their comfort zones without hassles of gallivanting nooks and crannies to enquire about prospective events. There is not any compelling need to interface with under-enthusiasts and intermediaries in the course of organizing, visiting and providing services for an event. However, it is obvious that massive amount of available information on the web exhibit frustrating attributes, hence it is increasingly a difficult task for users to find the content of interest; in other words, a huge chunk of information undiscovered on the network is left behind as “dark information”. In context, event service recommendation uses deep learning social filtering base techniques which adopt similarity computation measures with a bias for Pearson correlation coefficient, cosine similarity, and Euclidean similarity to recommend related and most relevant events/services to the targeted online audience. In this paper, the aim is to develop a deep learning model which integrates social filtering technique for enhancing the quality of event recommendation for users. A model based on the deep learning algorithm of multilayered perceptron and Neural Collaborative Filtering is proposed for event recommender services. The results from various simulations using meetup website dataset shows that the proposed model performs better than other techniques. The results yield 70% accuracy, 66% precision and 98% recall.

Digital Tourism Recommendation and Route Planning Model Design Based on RippleNet and Improved GA

Digital Tourism Recommendation and Route Planning Model Design Based on RippleNet and Improved GA

Channel-Enhanced Contrastive Cross-Domain Sequential Recommendation

Sequential recommendation help users find interesting items by modeling the dynamic user-item interaction sequences. Due to the data sparseness problem, cross-domain sequential recommendation (CDSR) are proposed. CDSR explore rich data from a source domain to improve performance of the target domain. However, most of the existing CDSR methods are difficult to capture the temporal context of sequences and only learn user preference based on interactions of single domain, which leads to suboptimal performance. To address these shortcomings, we propose a channel-enhanced contrastive cross-domain sequential recommendation model (C3DSR). To be specific, (1) we design a feature extractor, which extends attention to the channel dimension, to extract the user’s channel feature and capture the temporal contextual relationships between sequences. Then we calculate the weights of each channel by using three SE-Res2Blocks and multiply it with the channel feature to obtain user preference. (2) We concatenate the user’s single-domain representation, the cross-domain representation, and the user features to make CDSR. Contrastive learning is leveraged to enhance mutual information between two domains. Experimental results show that the proposed model achieves the significant improvement of performance compared with other CDSR models on Amazon and HVIDEO datasets.

DSDRec: Next POI recommendation using deep semantic extraction and diffusion model

Semantics play a crucial role in many AI tasks, yet the lack of high-quality textual data in LBSNs hampers deep semantic feature learning. Sparse user check-in records, characterized by significant spatial or temporal intervals (cut points), create challenges in understanding users' real mobile preferences. However, prior studies often rely on shallow semantic signals from independent textual properties and overlook these cut points when modeling spatio-temporal context. This work proposes a recommender model named DSDRec for the next POI recommendation. To alleviate the shortage of high-quality textual data in LBSNs, we take prompt engineering to freely obtain rich semantic texts (a.k.a., prompt sentences) from the discrete trajectory sequences and then use a pre-trained language model to acquire high-quality deep semantic features based on the functional prompt sentences. To mitigate the risk caused by the cut points, we propose an effective method, Spatio-Temporal Area Encoding, to depict the global spatial and temporal relationship of check-ins in trajectory. Besides, to study the potential of diffusion models in the next POI recommendation, we stacked an improved diffusion model to assist the recommender in learning more abstract interaction information. Comprehensive experiments conducted on two real-world datasets validate the competitive performance of DSDRec over previous SOTA approaches.

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.

Multi-Feature-Enhanced Academic Paper Recommendation Model with Knowledge Graph

This paper addresses the challenges of data sparsity and personalization limitations inherent in current recommendation systems when processing extensive academic paper datasets. To overcome these issues, the present work introduces an innovative recommendation model that integrates the wealth of structured information from knowledge graphs and refines the amalgamation of temporal and relational data. By applying attention mechanisms and neural network technologies, the model thoroughly explores the text characteristics of papers and the evolving patterns of user behaviors. Additionally, the model elevates the accuracy and personalization of recommendations by meticulously examining citation patterns among papers and the networks of author collaboration. The experimental findings show that the present model surpasses baseline models on all evaluation metrics, thereby enhancing the precision and personalization of academic paper recommendations.

The integration of knowledge graph convolution network with denoising autoencoder

The knowledge graph convolution network (KGCN) is a recommendation model that provides a set of top recommendations based on knowledge graph developed between users, items, and their attributes. In this study, we integrate the KGCN model with denoising autoencoder (DAE) to improve its recommendation performance. A trained DAE is used to sample K-dimensional latent representation for each user, which then transforms that representation to generate a probability distribution over items. The relationship between acquired latent representation and the meta features is modelled using multivariate multiple regression (MMR) kernel. As a result, without the need for new configuration assessments, performance estimation of new data is pursued directly through MMR and the decoder of DAE. Empirically, we demonstrate that on real-world datasets, the proposed method substantially outperforms other state-of-the-art baselines. Movie-Lens 100K (ML-100K) and Movie-Lens 1M (ML-1M), two common MovieLens datasets, are used to verify the accuracy of the proposed approach. The results from experiments show significant improvement of 41.17% when the proposed method is applied on KGCN model. The proposed framework outperforms other state-of-the-art frameworks on Recall@K and normalized discounted cumulative gain (NDCG@K) metrics by achieving higher scores for Recall@5, Recall@10, NDCG@1, and NDCG@10.

EDiffuRec: An Enhanced Diffusion Model for Sequential Recommendation

Sequential recommender models should capture evolving user preferences over time, but there is a risk of obtaining biased results such as false positives and false negatives due to noisy interactions. Generative models effectively learn the underlying distribution and uncertainty of the given data to generate new data, and they exhibit robustness against noise. In particular, utilizing the Diffusion model, which generates data through a multi-step process of adding and removing noise, enables stable and effective recommendations. The Diffusion model typically leverages a Gaussian distribution with a mean fixed at zero, but there is potential for performance improvement in generative models by employing distributions with higher degrees of freedom. Therefore, we propose a Diffusion model-based sequential recommender model that uses a new noise distribution. The proposed model improves performance through a Weibull distribution with two parameters determining shape and scale, a modified Transformer architecture based on Macaron Net, normalized loss, and a learning rate warmup strategy. Experimental results on four types of real-world e-commerce data show that the proposed model achieved performance gains ranging from a minimum of 2.53% to a maximum of 13.52% across HR@K and NDCG@K metrics compared to the existing Diffusion model-based sequential recommender model.

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.

An effectual recommendation model using hybrid learning models for early detection of Alzheimer’s disease

Alzheimer’s disease (AD) is a neurodegenerative disorder that affects millions of individuals worldwide, causing progressive cognitive decline. Early prediction and diagnosis the AD accurately is crucial for effective intervention and treatment. In this study, we propose a comprehensive framework for AD prediction using various techniques, including preprocessing and denoising with Multilayer Perceptron (MLP) and Ant Colony Optimization (ACO), segmentation using U-Net, and classification with Spatial Pyramid Pooling Network (SPPNet). Furthermore, we employ Convolutional Neural Network (CNN) with SPPNet for training and develop a chatbot for recommendation based on MRI data input. The preprocessing and denoising techniques play a vital role in enhancing the quality of the input data. MLP is utilized for preprocessing, where it effectively handles feature extraction and noise reduction. ACO is employed for denoising, optimizing the data to improve the signal-to-noise ratio, and enhancing the overall performance of subsequent stages. For accurate segmentation of brain regions, we employ the U-Net architecture, which has shown remarkable success in medical image segmentation tasks. U-Net effectively identifies the regions of interest, aiding in subsequent classification stages. The classification phase utilizes SPPNet, a deep learning model known for its ability to capture spatial information at multiple scales. SPPNet extracts features from segmented brain regions, enabling robust classification of AD and non-AD cases. To enhance the training process, we employ CNN with SPPNet, leveraging the power of convolutional layers to capture intricate patterns and improve predictive accuracy. The CNN-SPPNet model is trained on a large dataset of MRI scans, enabling it to learn complex representations and make accurate predictions. Hence the proposed work can be integrated with a chatbot that takes MRI data as input and provides recommendations based on the predicted AD probability. Experimental evaluation shows that the combination of preprocessing, denoising, segmentation, and classification offers a comprehensive solution for accurate and efficient AD diagnosis and management.

Personalized recommendation of entertainment robots in fine arts education based on human–computer interaction and data mining

In the current digital entertainment environment, the art learning mode of human–computer interaction can effectively enhance students’ interest. Entertainment robots, as a novel personalized interaction tool, can provide a more intelligent and entertaining way for art teaching. This article analyzes the personalized recommendation of entertainment robots in art education based on human–computer interaction and data mining.On the basis of collecting a large number of fine art education resources and organizing and labeling them, data mining technology is used to extract user background information and interest preferences. Information retrieval technology is used to filter out content related to user interests from the massive art education resources based on the extracted user interests. We also use recommendation algorithms to sort and personalize the recommended content based on the user’s historical behavior and other user evaluations, in order to improve the accuracy of recommendation results and user satisfaction. The effectiveness and practicality of this personalized recommendation model were verified through user surveys and data analysis. The experimental results indicate that this model can quickly and accurately recommend suitable fine art education content for users, improving their learning effectiveness and experience.

A Personalized Framework for Consumer and Producer Group Fairness Optimization in Recommender Systems

In recent years, there has been an increasing recognition that when machine learning (ML) algorithms are used to automate decisions, they may mistreat individuals or groups, with legal, ethical, or economic implications. Recommender systems are prominent examples of these ML systems that aid users in making decisions. The majority of past literature research on recommender systems fairness treats user and item fairness concerns independently, ignoring the fact that recommender systems function in a two-sided marketplace. In this article, we propose CP-FairRank , an optimization-based re-ranking algorithm that seamlessly integrates fairness constraints from both the consumer and producer side in a joint objective framework. The framework is generalizable and may take into account varied fairness settings based on group segmentation, recommendation model selection, and domain, which is one of its key characteristics. For instance, we demonstrate that the system may jointly increase consumer and producer fairness when (un)protected consumer groups are defined on the basis of their activity level and main-streamness , while producer groups are defined according to their popularity level. For empirical validation, through large-scale on eight datasets and four mainstream collaborative filtering recommendation models, we demonstrate that our proposed strategy is able to improve both consumer and producer fairness without compromising or very little overall recommendation quality, demonstrating the role algorithms may play in avoiding data biases. Our results on different group segmentation also indicate that the amount of improvement can vary and is dependent on group segmentation, indicating that the amount of bias produced and how much the algorithm can improve it depend on the protected group definition, a factor that, to our knowledge, has not been examined in great depth in previous studies but rather is highlighted by the results discovered in this study.

Revisiting Bundle Recommendation for Intent-aware Product Bundling

Product bundling represents a prevalent marketing strategy in both offline stores and e-commerce systems. Despite its widespread use, previous studies on bundle recommendation face two significant limitations. Firstly, they rely on noisy datasets, where bundles are defined by heuristics, e.g., products co-purchased in the same session. Secondly, they target specific tasks by holding unrealistic assumptions, e.g., the availability of bundles for recommendation directly. This paper proposes to take a step back and considers the process of bundle recommendation from a holistic user experience perspective. We first construct high-quality bundle datasets with rich metadata, particularly bundle intents, through a carefully designed crowd-sourcing task. We then define a series of tasks that together, support all key steps in a typical bundle recommendation process, from bundle detection, completion and ranking, to explanation and auto-naming, whereby 19 research questions are raised correspondingly to guide the analysis. Finally, we conduct extensive experiments and analyses with representative recommendation models and large language models (LLMs), demonstrating the challenges and opportunities, especially with the emergence of LLMs. To summarize, our study contributes by introducing novel data sources, paving the way for new research avenues, and offering insights to guide product bundling in real e-commerce platforms.

Personalised Multi-modal Interactive Recommendation with Hierarchical State Representations

Multi-modal interactive recommender systems (MMIRS) can effectively guide users towards their desired items through multi-turn interactions by leveraging the users’ real-time feedback (in the form of natural-language critiques) on previously recommended items (such as images of fashion products). In this scenario, the users’ preferences can be expressed by both the users’ past interests from their historical interactions and their current needs from the real-time interactions. However, it is typically challenging to make satisfactory personalised recommendations across multi-turn interactions due to the difficulty in balancing the users’ past interests and the current needs for generating the users’ state (i.e., current preferences) representations over time. However, hierarchical reinforcement learning has been successfully applied in various fields by decomposing a complex task into a hierarchy of more easily addressed subtasks. In this journal article, we propose a novel personalised multi-modal interactive recommendation model (PMMIR) using hierarchical reinforcement learning to more effectively incorporate the users’ preferences from both their past and real-time interactions. In particular, PMMIR decomposes the personalised interactive recommendation process into a sequence of two subtasks with hierarchical state representations: a first subtask where a history encoder learns the users’ past interests with the hidden states of history for providing personalised initial recommendations and a second subtask where a state tracker estimates the current needs with the real-time estimated states for updating the subsequent recommendations. The history encoder and the state tracker are jointly optimised with a single objective by maximising the users’ future satisfaction with the recommendations. Following previous work, we train and evaluate our PMMIR model using a user simulator that can generate natural-language critiques about the recommendations as a surrogate for real human users. Experiments conducted on two derived fashion datasets from two well-known public datasets demonstrate that our proposed PMMIR model yields significant improvements in comparison to the existing state-of-the-art baseline models. The datasets and code are publicly available at: https://github.com/yashonwu/pmmir

A Novel Constraint-Aware Flexible Model with Ant Colony Optimization for Symmetrical Travel Recommendation

This paper proposes a flexible travel recommender model (FTRM) that emphasizes the symmetry between user preferences and travel constraints, addressing key challenges in the field such as the integration of diverse constraint types and the customization of travel itineraries. The key contribution of the proposed model lies in its integration with the item constraints data model (ICDM), which effectively manages a plethora of constraint types. Additionally, this study develops a novel algorithm inspired by ant colony optimization (ACO) principles, demonstrating performance metrics that are comparable to state-of-the-art algorithms in this field. A comprehensive set of systematic experimental analyses is conducted, employing various models across diverse situational contexts, with the primary goal of illustrating the capabilities of the proposed symmetrical FTRM using real-world data from the Durham dataset. The obtained results highlight the model’s ability to accommodate diverse constraint types, facilitating the customization of travel itineraries to suit individual user preferences and achieve a balanced and symmetrical travel experience. Specifically, our model outperforms existing models in terms of flexibility and customization, showing significant improvements in user satisfaction and itinerary efficiency.

Intention enhanced mixed attentive model for session-based recommendation

AbstractSession-based recommendation aims to generate recommendations for the next item of users’ interest based on a given session. In this manuscript, we develop intention enhanced mixed attentive model () to generate session-based recommendations using two important factors: temporal patterns and estimates of users’ intentions. Unlike existing methods which primarily leverage complicated gated recurrent units to model the temporal patterns, models the temporal patterns using a light-weight while effective position-sensitive attention mechanism. In , we also leverage the estimate of users’ prospective preferences to signify important items, and generate better recommendations. Our experimental results demonstrate that models significantly outperform the state-of-the-art methods in six benchmark datasets, with an improvement as much as 19.2%. In addition, our run-time performance comparison demonstrates that during testing, models are much more efficient than the best baseline method, with a significant average speedup of 47.7 folds.

A scholars’ personality traits augmented multi-dimensional feature fusion scholarly journal recommendation model

Journal recommendation is a popular research topic in academic resource recommendation. However, the reliability of the current model depends on rich features in the dataset, and ignores the issue of model performance being degraded by sparse sample features. To tackle this issue, inspired by personality trait-based recommendation techniques, we propose a Personality Trait-augmented Multi-dimensional Feature Fusion Journal Recommendation (PTMFFJRec) model that integrates scholars’ personality traits and multi-dimensional deep semantics, and utilize linguistic features and the big-5 personality model to estimate the personality of the scholars. This is the first multi-dimensional feature model that incorporates Transfer Learning, BERT, and GCN techniques to recommend academic journals based solely on the abstracts and titles of submitted manuscripts. Experimental results on the real-world Scopus’s dataset demonstrate that PTMFFJRec outperforms advanced benchmark models, specifically, surpassing the baseline models in metrics of MAP, MRR, Recall@20 and Diversity.

Assessment of Barriers, Supports, and Context to Implement Best Practice Pain Management in the Emergency Department: The IMPAINED Study

AimTo assess the emergency department practice context and identify strategies to improve outcomes of patients with acute pain. BackgroundEffective treatment of acute pain in the emergency department depends upon clinicians adopting pain interventions into practice. However, it is well-recognized that acute pain is often undertreated. The local practice context strongly influences clinicians’ adoption of interventions into their clinical practice. An assessment of this practice context can inform implementation interventions and strategies to improve outcomes for patients with acute pain. MethodsChart audit, staff survey, and staff working groups were conducted from June 2020 to May 2021 Data were analyzed and synthesized across sources informed by assessment elements of the Ottawa model of research use (OMRU) implementation model and expert recommendations for implementing change strategies. ResultsThe OMRU facilitated contextual assessment of pain treatment practice in the emergency department and the development of implementation strategies. Adoption of evidence-based pain interventions was low in the sample studied. Workflow and workload were the primary barriers to evidence-based pain practices by potential adopters, while positive beliefs and high awareness of evidence-based pain interventions were supportive factors. Implementation strategies were informed by assessment findings and mapped to the Ottawa model and expert recommendations for implementing change elements. ConclusionThe adoption of evidence into practice in the emergency department relies upon a comprehensive assessment of the local context. The use of the OMRU assessment process resulted in meaningful engagement with staff and a deeper understanding of local pain management practices. Clinicians view evidence-based pain management as important, however, there are competing priorities within the emergency department, such as patient flow and triage. This study provides an exemplar of utilizing an implementation framework to identify pain practices within the emergency department. Clinical ImplicationsAchieving impactful change in clinical practice to improve patient outcomes should start with the application of implementation methods that enable comprehensive analysis of the local practice context. The assessment should begin with collaboration with local clinicians that persist throughout the life of the study to ensure change is sustainable.

Smart irrigation with crop recommendation using machine learning approach

Increasing crop yield with sustainable growth is the primary requirement for farmers with a growing population. Effective management and conservation of depleting natural resources is a priority task. Decrease in manpower due to migrating population has forced automation in agriculture. In this work, an automatic water irrigation and an effective crop recommendation system is proposed. Gypsum blocks based soil sensor is used to measure dielectric permittivity associated with the tested soil. The water-potential present in soil, along with potassium (K), nitrogen (N), phosphorus (P), potential of hydrogen (pH) helps to quantify the soil nutrients available and the suitable crop that can be considered for harvesting in a specified demography and environment. Sensory data indicating soil quality obtained is used to recommend crops by utilizing machine learning approaches. Telegram application is linked to the recommendation model to assist decision making and to ensure farmer-friendliness by sending notifications periodically.

HeteLFX: Heterogeneous recommendation with latent feature extraction

This study proposes a heterogeneous recommendation model that does not rely on data sharing. Previous studies have predominantly focused on nested homogeneous domains that share data. However, this approach encounters issues as it could lead to diminished recommendation performance when there is a scarcity of redundant data within these domains. To overcome these challenges, we propose the HeteLFX model, which extracts and bridges the latent features (LF) of each domain. This model resolves the problems by leveraging the metainformation of domain items to generate an LF. LF is extracted for each domain, and bridges are established based on the relevance of the latent knowledge, thereby enabling heterogeneous recommendations. The efficacy of the HeteLFX model was assessed by comparing it with four other heterogeneous recommendation systems, which are variants of X-Map and NX-Map. The results revealed that the HeteLFX model improved performance by reducing the mean absolute error (MAE) by approximately 0.3, thereby underscoring the superiority of the model. Additionally, HeteLFX reduced the MAE by up to approximately 0.45, depending on the relevance of the data within the domain.