Improve Recommendation Quality Research Articles

Break Out of a Pigeonhole: A Unified Framework for Examining Miscalibration, Bias, and Stereotype in Recommender Systems

Despite the benefits of personalizing items and information tailored to users’ needs, it has been found that recommender systems tend to introduce biases that favor popular items or certain categories of items, and dominant user groups. In this study, we aim to characterize the systematic errors of a recommendation system and how they manifest in various accountability issues, such as stereotypes, biases, and miscalibration. We propose a unified framework that distinguishes the sources of prediction errors into a set of key measures that quantify the various types of system-induced effects, both at the individual and collective levels. Based on our measuring framework, we examine the most widely adopted algorithms in the context of movie recommendation. Our research reveals three important findings: (1) Differences between algorithms: recommendations generated by simpler algorithms tend to be more stereotypical but less biased than those generated by more complex algorithms. (2) Disparate impact on groups and individuals: system-induced biases and stereotypes have a disproportionate effect on atypical users and minority groups (e.g., women and older users). (3) Mitigation opportunity: using structural equation modeling, we identify the interactions between user characteristics (typicality and diversity), system-induced effects, and miscalibration. We further investigate the possibility of mitigating system-induced effects by oversampling underrepresented groups and individuals, which was found to be effective in reducing stereotypes and improving recommendation quality. Our research is the first systematic examination of not only system-induced effects and miscalibration but also the stereotyping issue in recommender systems.

Enhancing Recommendation Systems with Skew Deviation Bias for Shilling Attack Detection

Introduction: Recommender systems serve as a powerful tool to address the challenges of information overload by delivering personalized recommendations. However, their susceptibility to profile injection or shilling attacks poses a significant threat. Malicious entities can introduce fabricated profiles into the database of users to manipulate the popularity of specific items, subsequently influencing prediction outcomes. Method: Detecting and mitigating the impact of such attacks is critical for preserving recommendation accuracy and user trust. The primary objective of this study is to develop an integrated framework for robust shilling attack detection and data sparsity mitigation in recommendation systems. This approach aims to make the system more resistant to manipulative attacks and improve recommendation quality, especially when dealing with limited data. In this paper, Skew Deviation Bias (SDB), is a novel metric that gauges the skewness within rating distributions, enabling the identification of both fabricated shilling profiles and the anomalous rating behaviors exhibited by attackers. Building upon this foundation, SDB is integrated with other statistical metrics like Rating deviation from the mean agreement (RDMA), Weighted deviation from the mean agreement (WDMA), Weighted degree of agreement (WDA), and length variance. This research investigates the impact of incorporating SDB alongside existing attributes in countering various attack scenarios, including random, average, and bandwagon attacks. Result: Extensive experiments are conducted to compare the effectiveness of SDB when integrated with existing attributes against scenarios employing only existing attributes. These experiments cover a range of attack sizes while maintaining a fixed 50% filler size. The results of thorough comparative analyses demonstrate the consistent superiority of the SDB-integrated approach, resulting in higher accuracy across all attack types compared to scenarios using only existing attributes. Notably, the random attack scenario shows the most significant accuracy improvement among the evaluated scenarios. Conclusion: The approach achieves a detection accuracy of 97.08% for random shilling attacks, affirming its robustness. Furthermore, in the context of data sparsity, the approach notably enhances recommendation quality.

A novel approach to enhance the quality of health care recommender system using fuzzy-genetic approach

In recent generations of the digital world medical data in Recommender Systems. Health Care Recommender System (HCRS) analyses the medical data and then predicts the user’s or patient’s illness. Nowadays, healthcare data is used by various users or patients in recommendation systems which are useful for everyone. Analysing and predicting medical data provides awareness to users and these data predictions may be enriched using various techniques of RS. Machine learning techniques are used to make sure that health data is reliable and of high quality. In every RS the issues are targeted such as scalability, sparsity and cold start problems. In many social networking applications, these issues are resolved using ML algorithms. However, there is a significant gap between IT systems and medical diagnosis. The fuzzy genetic method is used in HCRS in order to bridge the gap between IT and healthcare applications. Through the use of the mutation and crossover operators, a real-value genetic method is used in this to compute similarity. With the user’s extra personalized information, fuzzy rules are later generated for the database. The Hybrid fuzzy-genetic method, also known as this situation, combines both techniques to improve recommendation quality. Utilizing this method will improve the quality of the recommendation process by discovering the most precise similarity measures among different users. Six factors are subjected to fuzzification, including age, gender, employment, height, weight, and region. Genre-interesting measure weights are then used, including Very Light, Light, Average, Heavy, and Very Heavy. Finally, the evaluation metrics used MAE and RMSE to evaluate the recommendation accuracy which showed the best results in comparison with baseline approaches such as Convolutional Neural Networks and Restricted Boltzman Machine.

Promoting Sustainable Travel Experiences: A Weighted Parallel Hybrid Approach for Personalized Tourism Recommendations and Enhanced User Satisfaction

With the growing significance of the tourism industry and the increasing desire among travelers to discover new destinations, there is a need for effective recommender systems that cater to individual interests. Existing tourism mobile applications incorporate recommendation systems to alleviate information overload. However, these systems often overlook the varying importance of different items, resulting in suboptimal recommendations. In this research paper, a novel approach is proposed: a weighted parallel hybrid recommendation system. By considering item weights and leveraging parallel processing techniques, this method significantly enhances the accuracy of the similarity between items, leading to improved recommendation quality and precision. With this approach, users can efficiently and effectively explore new destinations that align with their unique preferences and interests, thereby enhancing their overall tourism experience and satisfaction. To evaluate the effectiveness of the proposed weighted parallel hybrid recommendation system, we conducted experiments using a dataset consisting of 20 users. The results demonstrated that the proposed approach achieved an impressive classification accuracy of 80%. A comparative analysis revealed that the proposed approach outperformed that of existing systems and achieved the best results in terms of classification accuracy. This finding highlights the effectiveness and efficiency of the proposed method in generating and promoting sustainable travel experiences by developing a personalized recommendations system for the unique preferences and interests of individual users.

A Social Recommendation Model Based on Basic Spatial Mapping and Bilateral Generative Adversarial Networks.

Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data. Therefore, how to effectively fuse interaction information and social information becomes a hot research topic in social recommendation, and how to mine and exploit the heterogeneous information in the interaction and social space becomes the key to improving recommendation performance. In this paper, we propose a social recommendation model based on basic spatial mapping and bilateral generative adversarial networks (MBSGAN). First, we propose to map the base space to the interaction and social space, respectively, in order to overcome the issue of heterogeneous information fusion in two spaces. Then, we construct bilateral generative adversarial networks in both interaction space and social space. Specifically, two generators are used to select candidate samples that are most similar to user feature vectors, and two discriminators are adopted to distinguish candidate samples from high-quality positive and negative examples obtained from popularity sampling, so as to learn complex information in the two spaces. Finally, the effectiveness of the proposed MBSGAN model is verified by comparing it with both eight social recommendation models and six models based on generative adversarial networks on four public datasets, Douban, FilmTrust, Ciao, and Epinions.

Enhanced Collaborative Filtering Algorithm for Movies Recommendation using Big Five Personality Traits

Recommender System suffers from data sparsity and cold start problems which arises when there is no sufficient rating history for user who has recently log into the system and no proper recommendations can be made. This paper develops an Enhanced collaborative filtering algorithm for Movie recommender system Using genre and Big five Personality traits (EMUBP) as system’s input. The experimental result shows that the EMUBP system improved recommendation quality and accuracy by 8.33% compared with the existing state-of-the-art using precision, recall and MAE.

A hybrid recommendation algorithm based on user comment sentiment and matrix decomposition

In order to improve recommendation quality of recommendation algorithms, this paper proposes a hybrid recommendation algorithm based on user comments sentiment and matrix decomposition (abbreviate as RACSMD). This algorithm first calculates the sentiment tendency towards the user’s comment through the LSTM algorithm, and then integrates the sentiment value of the user’s rating to increase the accuracy of the user’s actual rating before combining the matrix decomposition recommendation algorithm to improve recommendation quality. This paper theoretically verifies the feasibility of RACSMD through an algorithm example. Moreover, corresponding experimental analysis is conducted on the basis of three data sets of Beeradvocate, Modcloth and Amazon. Experimental results show that the introduction to sentiment tendencies towards user comments can effectively improve recommendation quality of recommendation algorithms.

Human-Centric Aggregation via Ordered Weighted Aggregation for Ranked Recommendation in Recommender Systems

In this paper, we propose an approach to recommender systems that incorporates human-centric aggregation via Ordered Weighted Aggregation (OWA) to prioritize the suggestions of expert rankers over the usual recommendations. We advocate for ranked recommendations where rankers are assigned weights based on their ranking position. Our approach recommends books to university students using linguistic data summaries and the OWA technique. We assign higher weights to the highest-ranked university to improve recommendation quality. Our approach is evaluated on eight parameters and outperforms traditional recommender systems. We claim that our approach saves storage space and solves the cold start problem by not requiring prior user preferences. Our proposed scheme can be applied to decision-making problems, especially in the context of recommender systems, and offers a new direction for human-specific task aggregation in recommendation research.

Graph-Augmentation-Free Self-Supervised Learning for Social Recommendation

Social recommendation systems can improve recommendation quality in cases of sparse user–item interaction data, which has attracted the industry’s attention. In reality, social recommendation systems mostly mine real user preferences from social networks. However, trust relationships in social networks are complex and it is difficult to extract valuable user preference information, which worsens recommendation performance. To address this problem, this paper proposes a social recommendation algorithm based on multi-graph contrastive learning. To ensure the reliability of user preferences, the algorithm builds multiple enhanced user relationship views of the user’s social network and encodes multi-view high-order relationship learning node representations using graph and hypergraph convolutional networks. Considering the effect of the long-tail phenomenon, graph-augmentation-free self-supervised learning is used as an auxiliary task to contrastively enhance node representations by adding uniform noise to each layer of encoder embeddings. Three open datasets were used to evaluate the algorithm, and it was compared to well-known recommendation systems. The experimental studies demonstrated the superiority of the algorithm.

Evolution of Deep Learning-Based Sequential Recommender Systems: From Current Trends to New Perspectives

The recommender system which gets higher in practical use in applying the Apriori algorithm in the early 2000s has revolutionized our daily life as it currently is widely used by big-tech platform companies. In the early stages of the development of recommender systems, services that can be provided to users were simply derived to the extent that only related products were recommended. However, the new research wave like deep learning-based recommender systems due to the development of information technology and the complexity of users’ online behavior extensively grabs researchers’ and academia’s attention in the field of recommender systems. This paper describes the algorithms and characteristics of the recent popular deep learning-based representative models such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), generative adversarial networks (GANs), and graph neural networks (GNNs) in the view of the sequential recommendation. The sequential recommendation of understanding user preferences in chronological order is useful for analyzing user-item interaction more accurately and flexibly. Therefore, the models specialized in sequential recommendation take advantage of understanding user behavior through temporal factors and improving recommendation quality by easily realizing the correlation between user and items. Also, the transformer-based model was developed to improve the problem of long-term dependency between users and items through factors, such as points, lines, and nodes, experienced in the early models of RNN and CNN and self-supervised learning (SSL)-based models, which are originally purposed to solve the data sparsity issues of recommender systems, will be discussed in this paper.

Trust-aware location recommendation in location-based social networks: A graph-based approach

With the increase in the use of mobile devices having location-related capabilities, the use of Location-Based Social Networks (LBSN) has also increased, allowing users to share location-embedded information with other users in the social network. By leveraging check-in activities provided by LBSNs, personalized recommendations can be provided. Trust is an important concept in social networks to improve recommendation quality. In this work, we develop a method for predicting the trust scores of LBSN users and propose a trust-aware recommendation technique, TLoRW, to recommend locations to users based on their previous check-ins, the social network, and predicted trust scores of users. In the proposed model, global trust score of user is generated on the basis of check-in history. In addition to trust, spatial context is anther important aspect of TLoRW to generate location recommendations based on the current location of a user. The proposed algorithm runs on a contextual subgraph rather full graph, relaxing the computing resource requirement. We represent a given LBSN with a undirected graph model. Recommendation scores of the locations are generated as the result of the random walk performed on the trust augmented LBSN subgraph. A comprehensive evaluation of TLoRW is conducted by comparing its recommendation performance against baseline techniques, as well as state-of-the-art trust-aware recommendation approaches in the literature, based on benchmark datasets. The experiments reveal that the trust information incorporated into random-walk-based approach improves the accuracy of the recommended locations @5 by minimum 5%.

Anthropomorphism and social presence in Human–Virtual service assistant interactions: The role of dialog length and attitudes

In this study, we delve into the perceived quality of recommendations provided by AI-based virtual service assistants (VSAs). Specifically, the role of the social presence of VSAs in influencing recommendation perceptions is investigated. We also explore how the social presence of a VSA is formed and how perceived anthropomorphism plays a vital role in shaping social presence and eventually instilling trust in VSAs among consumers. These relationships are examined in the context of online government services. The results indicate that consumer interaction with VSAs - manifesting via perceived anthropomorphism, social presence, dialog length, and attitudes - improves recommendation quality perceptions, which further instills trust in VSA-based recommendations. Perceived anthropomorphism was found to strongly influence the formation of social presence, whereas trust and recommendation quality - the outcomes of social presence - were found to be partially conditional on the dialog length and the degree of positive attitudes toward VSAs. The findings additionally suggest that a VSA can be considered a social actor that possesses the capability to bring a “human touch” to online services, therefore improving the overall online service experience.

Knowledge Graph Extrapolation Network with Transductive Learning for Recommendation

A knowledge graph is introduced into the personalized recommendation algorithm due to its strong ability to express structural information and exploit side information. However, there is a long tail phenomenon and data sparsity in real knowledge graphs, and most items are related to only a few triples. This results in a significant reduction in the amount of data available for training, and makes it difficult to make accurate recommendations. Motivated by these limitations, the Knowledge Graph Extrapolation Network with Transductive Learning for Recommendation (KGET) is proposed to improve recommendation quality. To be specific, the method first learns the embedding of users and items by knowledge propagation combined with collaborative signal to obtain high-order structural information, and the attention mechanism is used to distinguish the contributions of different neighbor nodes in propagation. In order to better solve with data sparsity and long tail phenomenon, transductive learning is designed to model links between unknown items to enrich feature representation to further extrapolate the knowledge graph. We conduct experiments with two datasets about music and books, the experiment results reveal that our proposed method outperforms state-of-the-art recommendation methods. KGET also achieves strong and stable performance in sparse data scenarios where items have merely a few triples.

A Systematic Analysis on the Impact of Contextual Information on Point-of-Interest Recommendation

As the popularity of Location-based Social Networks increases, designing accurate models for Point-of-Interest (POI) recommendation receives more attention. POI recommendation is often performed by incorporating contextual information into previously designed recommendation algorithms. Some of the major contextual information that has been considered in POI recommendation are the location attributes (i.e., exact coordinates of a location, category, and check-in time), the user attributes (i.e., comments, reviews, tips, and check-in made to the locations), and other information, such as the distance of the POI from user’s main activity location and the social tie between users. The right selection of such factors can significantly impact the performance of the POI recommendation. However, previous research does not consider the impact of the combination of these different factors. In this article, we propose different contextual models and analyze the fusion of different major contextual information in POI recommendation. The major contributions of this article are as follows: (i) providing an extensive survey of context-aware location recommendation; (ii) quantifying and analyzing the impact of different contextual information (e.g., social, temporal, spatial, and categorical) in the POI recommendation on available baselines and two new linear and non-linear models, which can incorporate all the major contextual information into a single recommendation model; and (iii) evaluating the considered models using two well-known real-world datasets. Our results indicate that while modeling geographical and temporal influences can improve recommendation quality, fusing all other contextual information into a recommendation model is not always the best strategy.

Modeling Product’s Visual and Functional Characteristics for Recommender Systems

An effective recommender system can significantly help customers to find desired products and assist business owners to earn more income. Nevertheless, the decision-making process of users is highly complex, not only dependent on the personality and preference of a user, but also complicated by the characteristics of a specific product. For example, for products of different domains (e.g., clothing versus office products), the product aspects that affect a user’s decision are very different. As such, traditional collaborative filtering methods that model only user-item interaction data would deliver unsatisfactory recommendation results. In this work, we focus on fine-grained modeling of product characteristics to improve recommendation quality. Specifically, we first divide a product’s characteristics into visual and functional aspects—i.e., the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">visual appearance</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">functionality</i> of the product. One insight is that, the visual characteristic is very important for products of visually-aware domain (e.g., clothing), while the functional characteristic plays a more crucial role for visually non-aware domain (e.g., office products). We then contribute a novel probabilistic model, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Visual and Functional Probabilistic Matrix Factorization</i> (VFPMF), to unify the two factors to estimate user preferences on products. Nevertheless, such an expressive model poses efficiency challenge in parameter learning from implicit feedback. To address the technical challenge, we devise a computationally efficient learning algorithm based on alternating least squares. Furthermore, we provide an online updating procedure of the algorithm, shedding some light on how to adapt our method to real-world recommendation scenario where data continuously streams in. Extensive experiments on four real-word datasets demonstrate the effectiveness of our method with both offline and online protocols.

Improving recommendation quality through outlier removal

Improving recommendation quality through outlier removal

RTN-GNNR: Fusing Review Text Features and Node Features for Graph Neural Network Recommendation

Recent recommendation systems have achieved good results by applying Graph Neural Network (GNN) to user-item interaction graphs. However, these recommendation systems can only handle structured interaction data and cannot handle unstructured review text data well. Based on the user-item interaction graph, combining review text can effectively solve the problem of data sparsity and improve recommendation quality. Most of the current recommendation methods combining review texts stitch the data from different modalities, leading to insufficient interactions and degrading the recommendations’ performance. A model called RTN-GNNR to fuse Review Text feature and Node feature for Graph Neural Network Recommendation is proposed to solve these problems and get better item recommendations. RTN-GNNR consists of four modules. The review text feature extraction module proposes a Bi-directional Gated Recurrent Unit (Bi-GRU) text analysis method that combines Bidirectional Encoder Representation from Transformers (BERT) and attention mechanism to enable the model to focus on more valuable reviews. The node feature extraction module proposes a GNN combined with the attention mechanism for the interactive node extraction method, which enables the model to have better higher-order feature extraction capability. The feature fusion module proposes the method of tandem Factorization Machine (FM) and Multilayer Perceptron (MLP) to realize interactive learning among multi-source features. The prediction module inner-products the fused higher-order features to achieve recommendation effect. We conducted experiments on five publicly available datasets from Amazon, showing that RTN-GNNR outperforms state-of-the-art personalized recommendation methods in both RMSE and MSE, especially in the sparser two datasets. The effectiveness of each module of the model is also demonstrated by a comparison of the ablation experiments.

5G Multimedia Precision Marketing Based on the Improved Multisensor Node Collaborative Filtering Recommendation Algorithm

The rapid development of web technology has brought new problems and challenges to the recommendation system: on the one hand, the traditional collaborative filtering recommendation algorithm has been difficult to meet the personalized recommendation needs of users; on the other hand, the massive data brought by web technology provides more useful information for recommendation algorithms. How to extract features from this information, alleviate sparsity and dynamic timeliness, and effectively improve recommendation quality is a hot issue in the research of recommendation system algorithms. In view of the lack of an effective multisource information fusion mechanism in the existing research, an improved 5G multimedia precision marketing based on an improved multisensor node collaborative filtering recommendation algorithm is proposed. By expanding the input vector field, the features of users’ social relations and comment information are extracted and fused, and the problem of collaborative modelling of these two kinds of important auxiliary information is solved. The objective function is improved, the social regularization term and the internal regularization term in the vector domain are analysed and added from the perspective of practical significance and vector structure, which alleviates the overfitting problem. Experiments on a large number of real datasets show that the proposed method has higher recommendation quality than the classical and mainstream baseline algorithm.

Investigating course choice motivations in university environments

Recommendation systems need a deeper understanding of users and their motivations to improve recommendation quality and provide more personalized suggestions. This is especially true in the education domain, the more about the student is known, the more useful recommendations can be made. However, although many studies on the course recommendation exist, studies on the students’ course selection motivations in universities are limited. This study investigates the factors that contribute to students’ choice when selecting courses in universities to better understand student perceptions, attitudes, and needs and leverage data-driven approaches for recommending and explaining the recommendations in university environments. A qualitative interview for university students (N = 10) comprised of open-ended questions as well as a questionnaire for students (N = 81) was conducted, aiming to investigate the main reasons behind their choices. The results of this study show that students highly value the course contents and the benefits of the course towards their future careers. Furthermore, students are influenced by other reasons such as the possibility of obtaining a higher grade, the popularity of professors, and recommendations from peers. Next, we extract the main categories of students’ motivations and analyzed the questionnaire data by employing statistical analysis methods as well as the k-means clustering algorithm to identify different types of students in terms of course selection. Based on our findings, we discuss implications for designing more personalized course recommendation systems.

Improving cold-start recommendations using item-based stereotypes

Recommender systems (RSs) have become key components driving the success of e-commerce and other platforms where revenue and customer satisfaction is dependent on the user’s ability to discover desirable items in large catalogues. As the number of users and items on a platform grows, the computational complexity and the sparsity problem constitute important challenges for any recommendation algorithm. In addition, the most widely studied filtering-based RSs, while effective in providing suggestions for established users and items, are known for their poor performance for the new user and new item (cold-start) problems. Stereotypical modelling of users and items is a promising approach to solving these problems. A stereotype represents an aggregation of the characteristics of the items or users which can be used to create general user or item classes. We propose a set of methodologies for the automatic generation of stereotypes to address the cold-start problem. The novelty of the proposed approach rests on the findings that stereotypes built independently of the user-to-item ratings improve both recommendation metrics and computational performance during cold-start phases. The resulting RS can be used with any machine learning algorithm as a solver, and the improved performance gains due to rate-agnostic stereotypes are orthogonal to the gains obtained using more sophisticated solvers. The paper describes how such item-based stereotypes can be evaluated via a series of statistical tests prior to being used for recommendation. The proposed approach improves recommendation quality under a variety of metrics and significantly reduces the dimension of the recommendation model.