Item Features Research Articles

Model verification for population detection of counterfeits.

The quality of counterfeit items has increased dramatically, with modern global manufacturing being able to duplicate the materials, construction, and visual features of items. Detection of fraudulent coinage can parallel authentication of food, beverages, and manufactured goods by studying product-inherent features. Counterfeit detection is performed by comparing an Example group with a Questioned group. A model is developed for both groups using standard tests on individual pieces. Coin weight is used here as an illustration. The model should also follow the natural science of the system. In this case, the manufacturing process variation is known and steady, and the underlying distribution is known or can be determined from authentic pieces. The proposed detection method uses testing of many individual pieces, then using reverse-quality-engineering methods to identify possible sources. This strategy looks at the variation between individual pieces to determine the process capability of a machine, assembly line, or plant to create product consistency for a manufacturer. Fraudulent items may be manufactured within specification, but demonstrate a manufacturing process capability different than that of the authentic manufacturer. In this report, we examine the model previously reported and use reconstruction techniques to re-create the evidence set to validate the model, increase model accuracy, and confirm the conclusion previously reached, showing that the Questioned set is likely over 37% non-conforming by weight. In this case, the decision outcome of the analysis was improved by using additional methods not included in the modeling software package originally used.

AsCDPR: a novel framework for ratings and personalized preference hotel recommendation using cross-domain and aspect-based features

PurposeThe explosion of data due to the sophistication of information and communication technology makes it simple for prospective tourists to learn about previous hotel guests' experiences. They prioritize the rating score when selecting a hotel. However, rating scores are less reliable for suggesting a personalized preference for each aspect, especially when they are in a limited number. This study aims to recommend ratings and personalized preference hotels using cross-domain and aspect-based features.Design/methodology/approachWe propose an aspect-based cross-domain personalized recommendation (AsCDPR), a novel framework for rating prediction and personalized customer preference recommendations. We incorporate a cross-domain personalized approach and aspect-based features of items from the review text. We extracted aspect-based feature vectors from two domains using bidirectional long short-term memory and then mapped them by a multilayer perceptron (MLP). The cross-domain recommendation module trains MLP to analyze sentiment and predict item ratings and the polarities of the aspect based on user preferences.FindingsExpanded by its synonyms, aspect-based features significantly improve the performance of sentiment analysis on accuracy and the F1-score matrix. With relatively low mean absolute error and root mean square error values, AsCDPR outperforms matrix factorization, collaborative matrix factorization, EMCDPR and Personalized transfer of user preferences for cross-domain recommendation. These values are 1.3657 and 1.6682, respectively.Research limitation/implicationsThis study assists users in recommending hotels based on their priority preferences. Users do not need to read other people's reviews to capture the key aspects of items. This model could enhance system reliability in the hospitality industry by providing personalized recommendations.Originality/valueThis study introduces a new approach that embeds aspect-based features of items in a cross-domain personalized recommendation. AsCDPR predicts ratings and provides recommendations based on priority aspects of each user's preferences.

An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems.

Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.

A Hybrid Solution For The Cold Start Problem In Recommendation

Abstract Recommender systems are becoming more and more significant in today’s digital world and in the modern economy. They make a substantial contribution to company operations by offering tailored advice and decreasing overwhelm. Collaborative filtering, being popular in the domain of recommendation, is used to offer recommendations to attract the target audience based on the feedback of people with comparable interests. This method has some limitations, such as a cold-start issue, which makes the system less effective in anticipating unknown objects. We provide a hybrid deep-learning-based strategy centered on a method to enrich user and item profiles to address the cold-start issue in the recommendation process using a collaborative filtering approach. We employ pretrained deep learning models to produce rich user and item feature vectors that aid in the creation of useful suggestions and handling of user and item cold-start issues. The creation of more precise and tailored similarity matrices is made possible by adding metadata to the extracted features of the user and item. The results of the experiment demonstrate that in terms of precision and rate coverage, the proposed method performs better than the baseline techniques.

Gulliksen's pool: A quick tool for preliminary detection of problematic items in item factor analysis.

Exploratory factor analysis is widely used for item analysis in the earlier stages of scale development, usually with large pools of items. In this scenario, the presence of inappropriate or ineffective items can hamper the process of analysis, making it very difficult to correctly assess dimensionality and structure. To minimize, this (quite frequent) problem, we propose and implement a simple procedure designed to flag potentially problematic items before we specify any particular factorial solution. The procedure defines regions of item appropriateness and efficiency based on the combined impact of two prior item features: extremeness and consistency. The general proposal is related to the most widely used frameworks for item analysis. The limits of the appropriateness regions are obtained by extensive simulation in conditions that mimic those found in applications. An Item Response Theory index of prior item efficiency is then defined, and a combined approach for selecting the most effective and problem-free item sub-set is proposed. The proposal is useful to normal-range measures, such as questionnaire surveys that elicit reports about non-extreme attitudes, facts, beliefs or states, or personality questionnaires that measure normal-range constructs. The procedure is implemented in a freeware software.

Multi-aspect features of items for time-ordered sequential recommendation

The key to sequential recommendation modeling is to capture dynamic users’ interests. Existing sequential recommendation methods (e.g., self-attention mechanism) have achieved extraordinary success in modeling users’ interests. However, these models ignore that users have different levels of preferences for different aspects of items, failing to capture users’ most concerning aspects. In addition, they are highly dependent on the quality of training data, which may lead to overfitting of the model when the training data is insufficient. To address the above issues, we propose a novel sequence-aware model (Multi-Aspect Features of Items for Time-Ordered Sequential Recommendation, MFITSRec), which combines the features of items with user behavior sequences to learn more complex item-item and item-attribute relationships. Moreover, the model uses a self-attention network based on an absolute time relationship, which can better represent the changes in users’ interests and capture users’ preferences for particular aspects of items. Extensive experiments on five datasets demonstrate that our model outperforms various baseline models. In particular, the model’s prediction accuracy has been significantly improved on sparse datasets.

Attentional factorization machine with review-based user–item interaction for recommendation

In recommender systems, user reviews on items contain rich semantic information, which can express users’ preferences and item features. However, existing review-based recommendation methods either use the static word vector model or cannot effectively extract long sequence features in reviews, resulting in the limited ability of user feature expression. Furthermore, the impact of different or useless feature interactions between users and items on recommendation performance is ignored. Therefore, we propose an attentional factorization machine with review-based user–item interaction for recommendation (AFMRUI), which first leverages RoBERTa to obtain the embedding feature of each user/item review, and combines bidirectional gated recurrent units with attention network to highlight more useful information in both user and item reviews. Then we adopt AFM to learn user–item feature interactions to distinguish the importance of different user–item feature interactions and further to obtain more accurate rating prediction, so as to promote recommendation. Finally, we conducted performance evaluation on five real-world datasets. Experimental results on five datasets demonstrated that the proposed AFMRUI outperformed the state-of-the-art review-based methods regarding two commonly used evaluation metrics.

Heterogeneity in Measures and Rates of Reported Dementia and Subjective Memory Complaints Across U.S. National Surveys.

Several U.S. health surveillance surveys contain items related to self- and proxy reports of dementia and subjective memory complaints (SMC). Despite their similar content, these items differ in terminology, item specificity, and time frame. The goal of this study was to analyze whether item features might influence endorsement rates for dementia and SMC. We calculated design-appropriate estimates for the endorsement of dementia and SMC across U.S.-based national surveys and employed pairwise comparisons to evaluate endorsement rates across surveys. We also examined item characteristics to explore possible effects on endorsement rates. Endorsement rates were wide-ranging for dementia (ranging from 2.7% to 9.9%) and SMC (5.6% to 46.6%). Pairwise comparisons revealed statistically significant differences on most dementia-related items (76%), and all SMC comparisons (100%). Items varied substantially in the terminology used to assess dementia and SMC (e.g., "dementia" vs "Alzheimer's disease") and used different time frames (e.g., "past month" vs "5 years"). National survey data on reported dementia and SMC can have important research, training, and policy implications, yet endorsement rates vary widely across surveys. That variability could emerge from subtle but influential item characteristics, and our findings highlight the need for item harmonization, in even their most basic characteristics. Standardizing items across national surveillance surveys facilitates comparison across surveys so that we can better understand the true burden of these conditions to inform public health initiatives.

SMAR: Summary-Aware Multi-Aspect Recommendation

Extracting user preferences and item features from reviews to assist recommendations is becoming increasingly popular. However, on the one hand, existing works generally select reviews based on how well user reviews match item reviews. They ignore that reviews may contain noise such as irrelevant phrases, which will affect the accuracy of selecting important reviews. In contrast, summaries written by users are abstracts of reviews that contain critical item feature information. They can be adopted to identify crucial reviews and further capture user’s fine-grained preferences from reviews. In addition, current methods do not consider that different items have different aspects in the same domain. They normally set a fixed number of aspects of the entire domain to get coarse-grained user preferences and item features. However, when modeling the user’s preferences for the current item, it might be more important to capture the corresponding aspects of the item preferences. Therefore, in this paper, we are motivated to propose a Summary-Aware Multi-Aspect Recommendation (SMAR). Specifically, we first construct a Summary-Aware Review Selection Module which adopts summaries to alleviate noise in reviews, identifying key reviews accurately. We then design a Summary-Aware Multi-Aspect Module which captures targeted user preferences towards the current item’s aspects. Finally, we employ Latent Factor Model to complete the recommendation process. The experimental results on Amazon datasets show that our method significantly outperfoms state-of-art approaches in terms of rating prediction accuracy.

Harnessing Item Features to Enhance Recommendation Quality of Collaborative Filtering

Recommendation systems provide ways of directing users to items that may be relevant to them by guiding them to relevant items that will be suitable to the users according to their profiles. Collaborative filtering is one of the most successful and mature techniques of recommender system because of its domain independent ability. Bayesian Personalized Ranking Smart Linear Model (BPRSLIM) is model-based collaborative filtering (CF) recommendation algorithm that usually reconstructs a scanty user-item matrix directly; also, using only user-rating matrix usually prevents the algorithm from accessing relevant information that could enhance its recommendation accuracy. Therefore, this work reconstructs BPRSLIM user-item rating matrix via item feature information in order to improve its performance accuracy. Comprehensive experiments were carried out on a real-world dataset using different evaluation metrics. The performance of the model showed significant improvement in recommendation accuracy when compared with other top-N collaborative filtering-based recommendation algorithms, especially in precision and nDCG with 30.6% and 22.1% respectively.

Efficient federated item similarity model for privacy-preserving recommendation

Previous federated recommender systems are based on traditional matrix factorization, which can improve personalized service but are vulnerable to gradient inference attacks. Most of them adopt model averaging to fit the data heterogeneity of federated recommender systems, requiring more training costs. To address privacy and efficiency, we propose an efficient federated item similarity model for the heterogeneous recommendation, called FedIS, which can train a global item-based collaborative filtering model to eliminate user feature dependencies. Specifically, we extend the neural item similarity model to the federated model, where each client only locally optimizes the shared item feature matrix. We then propose a fast-convergent federated aggregation method inspired by meta-learning to address heterogeneous user updates and accelerate the convergence of global training. Furthermore, we propose a two-stage perturbation method to protect both local training and transmission while reducing communication costs. Finally, extensive experiments on four real-world datasets validate that FedIS can provide more competitive performance on federated recommendations. Our proposed method also shows significant training efficiency with less performance degradation.

Sparse attentional subsetting of item features and list-composition effects on recognition memory

Although knowledge is extremely high-dimensional, human episodic memory performance appears extremely low-dimensional, focused largely on stimulus-features that distinguish list items from one another. A cognitively plausible way this tension could be addressed is if selective attention selects a small number of features from each item. I consider an ongoing debate about whether stronger items (better encoded) interfere more than weaker items (less well encoded) with probe items during old/new episodic recognition judgements. This is called the list-strength effect, concerning whether or not effects of encoding strength are larger in lists of mixed strengths than in pure lists of a single strength. Analytic derivations with Anderson’s (1970) matched filter model show how storing only a small subset of features within high-dimensional representations, and assuming those same subsets tend to reiterate themselves item-wise at test, can support high recognition performance. In the sparse regime, the model produces a list-strength effect that is small in magnitude, resembling previous findings of so-called null list-strength effects. When the attended feature space is compact, such as for phonological features, attentional subsetting cannot be sparse. This introduces non-negligible cross-talk from other list items, producing a large-magnitude list-strength effect, similar to what is observed for the production effect (better recognition when reading aloud). This continuum-based account implies the existence of a continuous range of magnitudes of list-composition effects, including occasional inverted list-strength effects. This lays the foundation for propagating effects of task-relevant attention to sparse subsets of features through a broad range of models of memory behaviour.

A heterogeneous graph neural network model for list recommendation

List recommendation, an approach for recommending a set of items closely related to user preferences, plays a significant role in improving the user experience and has received growing attention in recent years. However, most existing models ignore list-level attributes and the heterogeneity of the interactions between the users and lists when predicting user preferences. In this paper, we propose a heterogeneous graph neural network list recommendation (HGLR) model to bridge these gaps. First, a representation learning module based on pre-training techniques is developed to learn the embeddings of the lists, by encoding textual information and aggregating the features of the constituent items. We then transform the user–list interaction into a bipartite graph and incorporate the list attributes into a heterogeneous information network (HIN). Propagation-based embedding learning is subsequently performed to generate user and list representation based on the message-passing mechanism of the graph neural network. Finally, an attentive fusion layer is designed to obtain the global representations for the recommendation. We also develop a new large-scale dataset containing multiple types of side information to evaluate the list recommendation model. Extensive experiments demonstrate that our model significantly outperforms state-of-the-art list recommendation methods and achieves performance gains over 8.96% and 14.59% in Recall and NDCG, respectively, against the strongest baselines.

A multi-graph neural group recommendation model with meta-learning and multi-teacher distillation

Group recommendation has garnered significant attention recently, aiming to suggest items of interest to groups. Most deep learning-based approaches for group recommendation focus on learning group representation through group–user interactions or by aggregating user preferences. However, these approaches face challenges due to the complexity of group representation learning and the limited availability of group–item interactions. To address these difficulties, we propose a multi-graph neural group recommendation model with meta-learning and multi-teacher distillation. Our model consists of three stages: multiple graphs representation learning (MGRL), meta-learning-based knowledge transfer (MLKT), and multi-teacher distillation (MTD). In the MGRL stage, we construct two bipartite graphs and an undirected weighted graph based on group–user interactions, group–item interactions, and similarity between groups, respectively. We then utilize a linear variational graph auto-encoder network to learn the semantic features of groups, users, and items. In the MLKT stage, we introduce a multilayer perceptron (MLP) network for the recommendation task and design a meta-learning-based knowledge transfer algorithm to train an initialization parameter that incorporates user preference knowledge. In the MTD stage, we use the trained parameters as initialization parameters for all teacher networks. We evenly divide the group–item interactions among the teachers and sequentially train the teacher networks. Finally, we employ a multi-teacher distillation approach to train student networks with superior performance. Furthermore, we conduct extensive experiments on six real-world datasets to evaluate the effectiveness of our proposed model. The experimental findings demonstrate that our model, in comparison to state-of-the-art approaches, achieves superior performance in terms of group recommendation.

Personalized recommendation with hybrid feedback by refining implicit data

In personalized recommender systems, the collaborative filtering (CF) recommendation approaches have been widely used to predict the preferences of users in real-world applications. Among them, Bayesian personalized ranking (BPR) attracts much attention as it can easily explore the binary form of implicit feedback. However, it still suffers from the absence problem of negative feedback. To address this issue, this paper proposes a hybrid-feedback collaborative filtering model by jointly exploiting the explicit and implicit feedback. Based on the assumption that users prefer items with high ratings, this work firstly introduces the definition of explicit rating data to the BPR model and further proposes an improved Bayesian personalized ranking (IBPR) model to jointly extract the implicit feedback features of users and items. The IBPR model alleviates the problem of lack of negative feedback and promotes the anti-noise performance of the recommender system. Then the IBPR and BiasSVD (Biased Singular Value Decomposition) models are combined to further extract explicit latent features of users as well as items and construct the hybrid-feedback CF model. In this model, the user–item ranking matrix is reconstructed based on the extracted implicit feedback features, and the rating matrix is constructed based on the extracted explicit feedback features. Our proposed method is evaluated on five public datasets and achieves the competitive performance.

A new deep graph attention approach with influence and preference relationship reconstruction for rate prediction recommendation

Graph neural networks have been frequently applied in recommender systems due to their powerful representation abilities for irregular data. However, these methods still suffer from the difficulties such as the inflexible graph structure, sparse and highly imbalanced data, and relatively shallow networks, limiting rate prediction ability for recommendations. This paper presents a novel deep dynamic graph attention framework based on influence and preference relationship reconstruction (DGA-IPR) for recommender systems to learn optimal latent representations of users and items. The entire framework involves a user branch and an item branch. An influence-based dynamic graph attention (IDGA) module, a preference-based dynamic graph attention (PDGA) module, and an adaptive fine feature extraction (AFFE) module are respectively constructed for each branch. Concretely, the first two attention modules concentrate on reconstructing influence and preference relationship graphs, breaking imbalanced and fixed constraints of graph structures. Then a deep feature aggregation block and an adaptive feature fusion operation are built, improving the network depth and capturing potential high-order information expressions. Besides, AFFE is designed to acquire finer latent features for users and items. The DGA-IPR architecture is formed by integrating IDGA, PDGA, and AFFE for users and items, respectively. Experiments reveal the superiority of DGA-IPR over existing recommendation models.

MKGCN: Multi-Modal Knowledge Graph Convolutional Network for Music Recommender Systems

With the emergence of online music platforms, music recommender systems are becoming increasingly crucial in music information retrieval. Knowledge graphs (KGs) are a rich source of semantic information for entities and relations, allowing for improved modeling and analysis of entity relations to enhance recommendations. Existing research has primarily focused on the modeling and analysis of structural triples, while largely ignoring the representation and information processing capabilities of multi-modal data such as music videos and lyrics, which has hindered the improvement and user experience of music recommender systems. To address these issues, we propose a Multi-modal Knowledge Graph Convolutional Network (MKGCN) to enhance music recommendation by leveraging the multi-modal knowledge of music items and their high-order structural and semantic information. Specifically, there are three aggregators in MKGCN: the multi-modal aggregator aggregates the text, image, audio, and sentiment features of each music item in a multi-modal knowledge graph (MMKG); the user aggregator and item aggregator use graph convolutional networks to aggregate multi-hop neighboring nodes on MMKGs to model high-order representations of user preferences and music items, respectively. Finally, we utilize the aggregated embedding representations for recommendation. In training MKGCN, we adopt the ratio negative sampling strategy to generate high-quality negative samples. We construct four different-sized music MMKGs using the public dataset Last-FM and conduct extensive experiments on them. The experimental results demonstrate that MKGCN achieves significant improvements and outperforms several state-of-the-art baselines.

Evaluation of the Recommendation Effect of Individual Interventions in a Recommender System

Collaborative filtering is a recommendation model that evaluates and recommends items that match the preferences of each user and with high purchase probability. However, some items are regularly purchased and do not necessarily require recommendation. Thus, identifying items with a high recommendation effect is one of the challenges when using recommendation models. The recommendation effect can be regarded as an intervention effect in causal inference by considering the recommendation of an item as intervention. The intervention effect of individual users can be estimated using models such as counterfactual regression (CFR). Nonetheless, because this model can only manage one type of intervention, it cannot be easily and directly applied to recommender systems when many recommended items appear as intervention. In this study, we extend this model to estimate the effects of individual interventions in multiple interventions using a single CFR by combining user and item features to form covariates of user–item pairs, thereby allowing the recommendation effects to be estimated for all user–item pairs. We demonstrate the effectiveness of the proposed method through experiments using artificial data.

Dynamic item feature modeling for rating prediction in recommender systems

Conventional recommendation methods focus on optimizing user and item representations using various modelling methods. While persistent features of items are well studied, time varying hidden features of items are largely neglected. We argue that it is desirable to model both static and dynamic representations of items in one framework. Moreover, dynamic features often exhibit periodic variation characteristics. Identifying dynamic features of items can help merchants recognize evolving trends of their product and provide better services to customers for more trading benefit. Based on our observations, a period-aware correlational-temporal user/item feature modeling method in the form of a double-chained BiGRU model with attention mechanism is proposed. Furthermore, heterogeneous graph-based meta-paths are incorporated to model static features of items. To the best of our knowledge, this is the first effort to model both static and dynamic representations of items in one setting. A heterogeneous correlational temporal framework (HCoTemp) fusing static and dynamic item representations along with dynamic user representation for sequential recommendation is proposed. Empirical studies of 4 Amazon review benchmark datasets demonstrate that our model outperforms state-of-the-art methods in both MSE and HR. We also conducted extensive ablation experiments, which reveal that each component of HCoTemp contributes to performance improvements. Randomly selected cases from the Amazon Game dataset also confirm our findings.

Generalizing Beyond the Test: Permutation-Based Profile Analysis for Explaining DIF Using Item Features

Profile analysis is one of the main tools for studying whether differential item functioning can be related to specific features of test items. While relevant, profile analysis in its current form has two restrictions that limit its usefulness in practice: It assumes that all test items have equal discrimination parameters, and it does not test whether conclusions about the item-feature effects generalize outside of the considered set of items. This article addresses both of these limitations, by generalizing profile analysis to work under the two-parameter logistic model and by proposing a permutation test that allows for generalizable conclusions about item-feature effects. The developed methods are evaluated in a simulation study and illustrated using Programme for International Student Assessment 2015 Science data.