Search

Motivation: Drug repositioning, the identification of new therapeutic uses for existing drugs, is crucial for accelerating drug discovery and reducing development costs. Some methods rely on heterogeneous networks, which may not fully capture the complex relationships between drugs and diseases. However, integrating diverse biological data sources offers promise for discovering new drug-disease associations (DDAs). Previous evidence indicates that the combination of information would be conducive to the discovery of new DDAs. However, the challenge lies in effectively integrating different biological data sources to identify the most effective drugs for a certain disease based on drug-disease coupled mechanisms., Results: In response to this challenge, we present MiRAGE, a novel computational method for drug repositioning. MiRAGE leverages a three-step framework, comprising negative sampling using hard negative mining, classification employing random forest models, and feature selection based on feature importance. We evaluate MiRAGE on multiple benchmark datasets, demonstrating its superiority over state-of-the-art algorithms across various metrics. Notably, MiRAGE consistently outperforms other methods in uncovering novel DDAs. Case studies focusing on Parkinson's disease and schizophrenia showcase MiRAGE's ability to identify top candidate drugs supported by previous studies. Overall, our study underscores MiRAGE's efficacy and versatility as a computational tool for drug repositioning, offering valuable insights for therapeutic discoveries and addressing unmet medical needs., (© The Author(s) 2024. Published by Oxford University Press.)

User identification is an essential technical support for downstream tasks such as recommendation systems, information retrieval, and collaborative filtering. Computing the similarity between user display names through classifiers is an effective solution for user identification across social networks. However, there are two problems with existing methods. Applying expert domain knowledge to extract handcrafted features of display names ignores the semantic information, resulting in poor performance of these methods. Selecting influential display names, and handcrafted features in user identification problems are also one of the difficulties. To solve these two problems, we propose a method based on the multi-feature fusion of display names using gated units. First, we extract the deep semantic features of display names through the BERT pre-trained multi-language model. Then, the gated mechanism is applied to select the handcrafted features we extracted to retain the essential features. Then, the adaptive factors are used to fuse handcrafted features and deep features to obtain user identification results across social networks. Finally, the efficiency of our model is verified on three constructed real-world multilingual display names datasets across multiple online social networks and compared with existing state-of-the-art methods. Experimental results show that the proposed algorithm outperforms the compared algorithms. [ABSTRACT FROM AUTHOR]

The internet has become inundated with vast amounts of information, making it increasingly difficult for users to find precise and reliable content in their respective domains. Recommendation algorithms have emerged as a solution to this problem, enabling personalized content recommendations based on user preferences. One domain that greatly benefits from recommendation systems is music, with its diverse genres and countless songs. In this research paper, we present a novel approach to music recommendation that leverages user likes, plays, ratings, and other factors to generate personalized playlists. The proposed hybrid recommendation system analyses songs using six features and incorporates new features such as ELLT and DVS designed for dimensionality reduction to enhance accuracy. It continuously adapts to evolving user preferences and music trends, making personalised recommendations using cosine similarity and song weights. We test our approach through extensive experimentation and achieve promising precision, recall, and F1 scores. This contribution advances personalized content recommendation and hybrid recommendation systems, demonstrating their potential to improve music listening experiences. [ABSTRACT FROM AUTHOR]

Summary: Existing research on recommender systems primarily focuses on improving a single objective, such as prediction accuracy, often ignoring other crucial aspects of recommendation performance such as temporal factor, user satisfaction, and acceptance. To solve this problem, we proposed an explicable recommendation model using many‐objective optimization and a time‐assisted knowledge graph, which utilizes user interaction times within the graph to prioritize recommending recently frequently visited items and is further optimized using a many‐objective optimization algorithm. In this model, the temporal weight of user actions at different times is first determined through a time decay function. Additionally, if a user clicks on the same item again, the current action's temporal weight is set to one. This strategy prioritizes recent user actions and frequently visited items, reflecting current interests and preferences better. Next, the created knowledge graph is used to create a list of potential recommendations. Embedding methods obtain the vectors for entities and relations in the path. These vectors, combined with the temporal weight of actions, quantify the explainability of user recommendations. Optimizing the rest of the recommendation performance with many objective algorithms while focusing on the user's recent frequent visits to the item. Finally, the outcomes of the research study indicate that, compared to other explicable recommended methods, our model, considering temporal factor, improved average accuracy by 11%, diversity by 1%, and explainability by 21% in the Useraction1 data set. Results in other data sets also indicate that the proposed model maintains accuracy, diversity, and novelty while enhancing explainability. [ABSTRACT FROM AUTHOR]

Personalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately learn the embeddings of users, items, and tags. To address this issue, we propose a contrastive learning-based personalized tag recommendation algorithm, namely CLPTR. Specifically, CLPTR generates augmented views of user–tag and item–tag interaction graphs by injecting noises into implicit feature representations rather than dropping nodes and edges. Hence, CLPTR is able to greatly preserve the underlying semantics of the original user–tag or the item–tag interaction graphs and avoid destroying their structural information. In addition, we integrate the contrastive learning module into a graph neural network-based personalized tag recommendation model, which enables the model to extract self-supervised signals from user–tag and item–tag interaction graphs. We conduct extensive experiments on real-world datasets, and the experimental results demonstrate the state-of-the-art performance of our proposed CLPTR compared with traditional personalized tag recommendation models. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) technologies have been increasingly developed and applied in the audiovisual sector. Over-the-top (OTT) services, directly distributed to viewers via the Internet, are associated with a shift towards automation through algorithmic mediation in audiovisual content led by digital platforms. However, scientific knowledge regarding algorithmic recommender systems and automation in OTT services is not yet systemized; researchers, practitioners, and the public thus lack full awareness about the still largely opaque phenomena. To address this gap, we conduct a systematic literature review in the communication domain (2010–2022) and answer four key research questions: What research objectives have been pursued? What concepts have been developed and/or applied? What methodologies have been privileged? Which OTT platforms have received the most research attention? Challenges and opportunities are highlighted, and an agenda for future research is advanced. [ABSTRACT FROM AUTHOR]

Sequential decision‐making involves making informed decisions based on continuous interactions with a complex environment. This process is ubiquitous in various applications, including recommendation systems and clinical treatment design. My research has concentrated on addressing two pivotal challenges in sequential decision‐making: (1) How can we design algorithms that efficiently learn the optimal decision strategy with minimal interactions and limited sample data? (2) How can we ensure robustness in decision‐making algorithms when faced with distributional shifts due to environmental changes and the sim‐to‐real gap? This paper summarizes and expands upon the talk I presented at the AAAI 2024 New Faculty Highlights program, detailing how my research aims to tackle these challenges. [ABSTRACT FROM AUTHOR]

Object ratings in recommendation algorithms are used to represent the extent to which a user likes an object. Most existing recommender systems use these ratings to recommend the top-K objects to a target user. To improve the accuracy and diversity of recommender systems, we proposed a neighbourhood-based diffusion recommendation algorithm (NBD) that distributes the resources among objects using the rating scores of the objects based on the likings of the target user neighbours. Specifically, the Adamic–Adar similarity index is used to calculate the similarity between the target user and other users to select the top K similar neighbours to begin the diffusion process. In this approach, greater significance is put on common neighbours with fewer neighbour nodes. This is to reduce the effect of popular objects. At the end of the diffusion process, a modified redistribution algorithm using the sigmoid function is explored to finally redistribute the resources to the objects. This is to ensure that the objects recommended are personalized to target users. The evaluation has been conducted through experiments using four real-world datasets (Friendfeed, Epinions, MovieLens-100 K, and Netflix). The experiment results show that the performance of our proposed NBD algorithm is better in terms of accuracy when compared with the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

As a critical task for large-scale commercial recommender systems, reranking rearranges items in the initial ranking lists from the previous ranking stage to better meet users' demands. Foundational work in reranking has shown the potential of improving recommendation results by uncovering mutual influence among items. However, rather than considering the context of initial lists as most existing methods do, an ideal reranking algorithm should consider the counterfactual context—the position and the alignment of the items in the reranked lists. In this work, we propose a novel pairwise reranking framework, Utility-oriented Reranking with Counterfactual Context (URCC), which maximizes the overall utility after reranking efficiently. Specifically, we first design a utility-oriented evaluator, which applies Bi-LSTM and graph attention mechanism to estimate the listwise utility via the counterfactual context modeling. Then, under the guidance of the evaluator, we propose a pairwise reranker model to find the most suitable position for each item by swapping misplaced item pairs. Extensive experiments on two benchmark datasets and a proprietary real-world dataset demonstrate that URCC significantly outperforms the state-of-the-art models in terms of both relevance-based metrics and utility-based metrics. [ABSTRACT FROM AUTHOR]

The study investigates user perceptions of news media's employment of news recommender systems (NRS) and their relation to trust in media outlets. A cross-sectional survey (n = 5079) in the United Kingdom, United States, Poland, the Netherlands, and Switzerland shows that higher algorithmic knowledge, users' perceived skills, and news aggregator use correspond to increased perceptions that news media use NRS. Moreover, higher perceived NRS use of specific news outlets is associated with lower trust in those outlets but perceived benefits and concerns related to NRS moderate this relationship. Our findings highlight the need for media organizations to ensure a responsible and transparent use of such systems, highlight benefits for users, and address concerns to avoid misperceptions of their NRS use and maintain user trust. [ABSTRACT FROM AUTHOR]

Sequence recommendation is a prominent research area within recommender systems, focused on predicting items that users may be interested in by modeling their historical interaction sequences. However, due to data sparsity, user interaction sequences in sequence recommendation are typically short. A common approach to address this issue is filling sequences with zero values, significantly reducing the effective utilization of input space. Furthermore, traditional sequence recommendation methods based on self-attention mechanisms exhibit quadratic complexity with respect to sequence length. These issues affect the performance of recommendation algorithms. To tackle these challenges, we propose a multi-task sequence recommendation model, Blin, which integrates bidirectional KL divergence and linear attention. Blin abandons the conventional zero-padding strategy, opting instead for random repeat padding to enhance sequence data. Additionally, bidirectional KL divergence loss is introduced as an auxiliary task to regularize the probability distributions obtained from different sequence representations. To improve the computational efficiency compared to traditional attention mechanisms, a linear attention mechanism is employed during sequence encoding, significantly reducing the computational complexity while preserving the learning capacity of traditional attention. Experimental results on multiple public datasets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

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, at both 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. [ABSTRACT FROM AUTHOR]

Movie Recommender systems are frequently used in academics and industry to give users with relevant, engaging material based on their rating history. However, most traditional methods suffer from the cold-start problem, which is the initial lack of item ratings and data sparsity. The Hybrid Machine Learning (ML) technique is proposed for a movie recommendation system. Demographic data is collected from the Movie Lens dataset, and attributes are evaluated using the Attribute Analysis module. The Aquila Optimization Algorithm is used to select the best attributes, while Random Forest classifier is used for classification. Data is clustered using Fuzzy Probabilistic Cmeans Clustering Algorithm (FPCCA), and the Correspondence Index Assessment Phase (CIAP) uses Bhattacharyya Coefficient in Collaborative Filtering (BCCF) for similarity index calculation. The Outcomes gives the proposed method obtained low error, such as MAE has 0.44, RMSE has 0.63 compared with the baseline methods. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) technologies have been increasingly developed and applied in the audiovisual sector. Over-the-top (OTT) services, directly distributed to viewers via the Internet, are associated with a shift towards automation through algorithmic mediation in audiovisual content led by digital platforms. However, scientific knowledge regarding algorithmic recommender systems and automation in OTT services is not yet systemized; researchers, practitioners, and the public thus lack full awareness about the still largely opaque phenomena. To address this gap, we conduct a systematic literature review in the communication domain (2010–2022) and answer four key research questions: What research objectives have been pursued? What concepts have been developed and/or applied? What methodologies have been privileged? Which OTT platforms have received the most research attention? Challenges and opportunities are highlighted, and an agenda for future research is advanced.

In the realm of e-commerce, personalized recommendations are a crucial component in enhancing user experience and optimizing sales efficiency. To address the inherent sparsity challenge prevalent in collaborative filtering algorithms within personalized recommendation systems, we propose a novel hybrid e-commerce recommendation algorithm based on the User-Nearest-Neighbor model. By integrating the user nearest neighbor model with other recommendation algorithms, this approach effectively mitigates data sparsity and facilitates a more nuanced understanding of the user-product relationship, consequently elevating recommendation quality and enhancing user experience. Taking into account considerations such as data scale and recommendation performance, we conducted experiments utilizing the Spark distributed platform. Empirical findings demonstrate the superiority of our hybrid algorithm over standalone collaborative filtering algorithms across various recommendation indicators. [ABSTRACT FROM AUTHOR]

Consumers can use automated prediction algorithms, like navigation apps and recommendation systems, to forecast the outcome of to-be-determined events like how long a drive will take or how much they will enjoy a movie. However, little is known about what drives consumers' preferences for prediction algorithms. The authors propose that consumers prefer prediction algorithms that replicate the event being predicted by going through the same process that generates event outcomes. In seven studies, the authors find that consumers like replicative prediction algorithms, even when they may lead to worse performance. Furthermore, the authors find that consumers shift toward choosing better performing algorithms after receiving performance feedback but still prefer replicative algorithms holding performance constant. These findings suggest that marketers can increase adoption of prediction algorithms by framing them as replicating (or designing them to replicate) the process that generates event outcomes. [ABSTRACT FROM AUTHOR]

In order to meet the protection needs of user privacy data in social networks, this paper proposes a computer intelligent collaborative filtering algorithm for personalized network data recommendation systems. This algorithm predicts user preferences for specific items by utilizing user evaluation information on groups of similar feature items, thereby achieving personalized recommendations. The experimental results show that as the number of project feature selections N increases, the MAE, RMSE, and NDCG5 of the algorithm gradually improve. This is mainly attributed to increasing the number of features under a fixed similarity threshold, which makes the data granularity finer and helps to describe project features more accurately. In the case of a fixed number of project feature selections N, the impact of the number of nearest neighbors s in similar groups on algorithm performance was further studied. The results showed that with the increase of s, MAE, RMSE, and NDCG5 showed a decreasing trend. Although the algorithm suffers from certain losses in recommendation accuracy, it is still within an acceptable range. It is worth noting that due to the system only using generalized data as input, user privacy data is effectively protected. Based on the comprehensive experimental results, this algorithm has significant value in practical applications. [ABSTRACT FROM AUTHOR]

Human beings have created numerous laws, sayings and proverbs that still influence behaviors and decision-making processes of people. Some of the laws, sayings or proverbs are used by people to understand the phenomena that may take place in daily life. For example, Murphy's law states that "Anything that can go wrong will go wrong." Murphy's law is helpful for project planning with analysis and the consideration of risk. Similar to Murphy's law, the old saying "Two heads are better than one" also influences the determination of the ways for people to get jobs done effectively. Although the old saying "Two heads are better than one" has been extensively discussed in different contexts, there is a lack of studies about whether this saying is valid and can be applied in evolutionary computation. Evolutionary computation is an important optimization approach in artificial intelligence. In this paper, we attempt to study the validity of this saying in the context of evolutionary computation approach to the decision making of ridesharing systems with trust constraints. We study the validity of the saying "Two heads are better than one" by developing a series of self-adaptive evolutionary algorithms for solving the optimization problem of ridesharing systems with trust constraints based on the saying, conducting several series of experiments and comparing the effectiveness of these self-adaptive evolutionary algorithms. The new finding is that the old saying "Two heads are better than one" is valid in most cases and hence can be applied to facilitate the development of effective self-adaptive evolutionary algorithms. Our new finding paves the way for developing a better evolutionary computation approach for ridesharing recommendation systems based on sayings created by human beings or human intelligence. [ABSTRACT FROM AUTHOR]

Food Recommender Systems (RecSys) are innovative knowledge systems that inform consumers of food choices according to criteria, including nutritional content, health concerns, production method, carbon footprint or other social and ethical considerations. They raise important questions at the intersection of technology accuracy and today evolving consumers' knowledge seeking behaviours, which implies to unpack the epistemic value of food RecSys. This study investigates the drivers of the perceived value of food RSs consumption by proposing a model that establishes via PLS-SEM (n = 253) a positive relationship between the Yuka company's food RecSys' epistemic value and its perceived value. The model demonstrates that Yuka RecSys' epistemic value relies on the disciplinary drivers of compatibility, self-confidence, and consumer innovativeness, and the problematising drivers of memory and learning, which come from using the application. The perceived value of food RecSys is found to relate to RecSys epistemic value beyond the functional accuracy aspects of recommendation algorithms. Results highlight the importance of developing a refined understanding of epistemic value considering the consumption of RecSys. RecSys' developers, retailers, food manufacturers and policy makers must work on better mapping and adjusting information through consumers socialised RecSys' usage to shape the design of the next generation RecSys. [ABSTRACT FROM AUTHOR]

A growing body of empirical evidence suggests the existence of a Paradox of Choice, whereby a larger choice set leads to a lower expected payoff to the decisionmaker. These empirical findings contradict traditional choice-theoretic results in microeconomics and even social psychology, suggesting profound yet unexplained aspects of choice settings/behavior. The Paradox remains largely as a theoretically-rootless empirical phenomenon. We neither understand the mechanisms and conditions that generate it, nor whether the Paradox stems from choice behavior, choice setting, or both. We present a general search model of consumer choice under incomplete information to examine the theoretical existence and conditions for the Paradox. The model departs from traditional microeconomic choice theory in assuming no "cognitive free lunches." Search and evaluative efforts require time, focus, and opportunity cost in the model, as in real life. The model shows that conditions for Paradox readily exist, diminishing returns to potential value of the choice in choice set size is a necessary condition for a Paradox outcome, that a Paradox outcome can occur with or without a "choice overload" response by the decisionmaker, and that avoidance of a Paradox outcome is an impossibility in some choice settings (primitive to setting regardless of choice behavior). Lastly, we develop a pareto-improving choice set reduction algorithm that eliminates weakly dominated choice set elements and presents the restricted choice set to the decisionmaker. As such, it is shown that the algorithm acts to treat or mitigate the Paradox of Choice, as well as to pareto-improve choice-supporting evaluation more generally. Like established AI recommender systems, the novel algorithm filters choices. In the present case, the filtering is based upon identification of weakly dominated choice set elements. [ABSTRACT FROM AUTHOR]

In recent years, graph neural networks (GNNs) have been widely applied in recommender systems. However, existing recommendation algorithms based on GNNs still face challenges in node aggregation and feature extraction processes because they often lack the ability to capture the interactions between users and items, as well as users' multiple intentions. This hinders accurate understanding of users' needs. To address the aforementioned issues, we propose a recommendation model called multi-intent-aware interactive graph convolutional network (Multi-IAIGCN). This model is capable of integrating multiple user intents and adopts an interactive convolution approach to better capture the information on the interaction between users and items. First, before the interaction between users and items begins, user intents are divided and mapped into a graph. Next, interactive convolutions are applied to the user and item trees. Finally, by aggregating different features of user intents, predictions of user preferences are made. Extensive experiments on three publicly available datasets demonstrate that Multi-IAIGCN outperforms existing state-of-the-art methods or can achieve results comparable to those of existing state-of-the-art methods in terms of recall and NDCG, thus verifying the effectiveness of Multi-IAIGCN. [ABSTRACT FROM AUTHOR]

Traditional educational models struggle to meet the demands of students seeking personalized online learning resources (OLRs). Collaborative filtering (CF) algorithms are widely employed for personalized OLR recommendations, yet they encounter issues such as poor scalability, cold start, and sparse data issues. In response, an enhanced CF algorithm is proposed, incorporating a fusion of time weighting and a credibility selection strategy. Initially, interactions and ratings among learners are analyzed. Subsequently, the algorithm integrates learner similarity and trust, calculating the credibility value weight between learners. Dynamic time weighting is then introduced separately into CF algorithms based on OLRs and learners, respectively. Ultimately, the algorithm predicts learner ratings for unknown OLRs. Experimental comparisons demonstrate that the performance metrics of the hybrid algorithm presented in this paper show significant improvement over traditional and other improved algorithms. [ABSTRACT FROM AUTHOR]

The concept of privacy-preserving collaborative filtering (PPCF) has been gaining significant attention. Due to the fact that model-based recommendation methods with privacy are more efficient online, privacy-preserving memory-based scheme should be avoided in favor of model-based recommendation methods with privacy. Several studies in the current literature have examined ant colony clustering algorithms that are based on non-privacy collaborative filtering schemes. Nevertheless, the literature does not contain any studies that consider privacy in the context of ant colony clustering-based CF schema. This study employed the ant colony clustering model-based PPCF scheme. Attacks like shilling or profile injection could potentially be successful against privacy-preserving model-based collaborative filtering techniques. Afterwards, the scheme's robustness was assessed by conducting a shilling attack using six different attack models. We utilize masked data-based profile injection attacks against a privacy-preserving ant colony clustering-based prediction algorithm. Subsequently, we conduct extensive experiments utilizing authentic data to assess its robustness against profile injection attacks. In addition, we evaluate the resilience of the ant colony clustering model-based PPCF against shilling attacks by comparing it to established PPCF memory and model-based prediction techniques. The empirical findings indicate that push attack models exerted a substantial influence on the predictions, whereas nuke attack models demonstrated limited efficacy. [ABSTRACT FROM AUTHOR]

To address the issue of insufficient accuracy in consumer recommendation systems, a new biased network inference algorithm is proposed based on traditional network inference algorithms. This new network inference algorithm can significantly improve the resource allocation ability of the original one, thereby improving recommendation performance. Then, the performance of this algorithm is verified through comparative experiments with network-based inference algorithms, network inference algorithms with initial resource optimization, and heterogeneous network inference algorithms. The results showed that the accuracy of the new network inference algorithm was 24.5%, which was superior to traditional one. In terms of system performance testing, the recommendation hit rate of the new network inference algorithm increased by 13.97%, which was superior to the other three comparative algorithms. The experimental results indicated that a novel network inference algorithm with bias can improve the performance of consumer recommendation systems, providing new ideas for improving the performance of consumer recommendation systems. [ABSTRACT FROM AUTHOR]

To improve the accuracy of multiple target tracking in the clutter environment, a new joint probabilistic data association (JPDA) algorithm based on variational Bayesian adaptive moment estimation is proposed. First, considering the existence of measurements, the posterior distribution of the target state in JPDA is composed of two parts of probability weighting, that is, the posterior distribution of the target state that the real measurement exists in the association gate and the posterior distribution of the target state that the real measurement does not exist in the association gate. By combining the conjugate properties of the prior and posterior distributions, the prior distributions of the target state in the two cases are classified to provide more accurate a priori information to filter, so as to improve the accuracy of data association. Second, considering the coupling effect between state estimation and data association process, combined with variational Bayesian inference, the problem of minimizing Kullback–Leibler divergence is transformed into the problem of maximizing the evidence lower bound, thereby effectively measuring the distance between the posterior distribution of target state estimation and the real posterior distribution, so as to improve the accuracy of data association again from the perspective of optimizing nonlinear filter. Finally, the adaptive momentum estimation strategy is introduced to iteratively solve the variable distribution that meets the maximization of the evidence lower bound, and the optimization of the posterior distribution of the target state is completed. Theoretical derivation and simulation experiments are conducted to verify the feasibility and effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Time–frequency algorithms help discern and filter hidden information from signals but their growing abundance induces non-uniqueness thus, complicating selection. Classification of these algorithms into approaches can bring simplification and structure to improve our selection and estimates. This study focuses on algorithms we classify here as fixed window-based projection approach, wavelet-based projection approach, greedy-based approach and combinational-based approach while omitting heuristic-based approach and numerical-autoregressive-based approach classes. It describes the basic theory of transforms under the classes and compares them for effective stability, effective localization and resolution capabilities of time–frequency spectra for wavelet estimation and interfering beds with results demonstrating subtle advantages for each depending on nature of signal and model behind the algorithm. The combinational-based mixed-model approach wavelet-assisted constrained least squares spectral analysis concatenates a wavelet-based approach with a fixed window-based approach and effectively functions to reassign complex amplitude coefficients from their apparent positions to their true positions. A comparison of the results suggests that it demonstrates good scope as an effective alternative general tool for hydrocarbon detection and resolution of thin beds. [ABSTRACT FROM AUTHOR]

In Computing Taste , Nick Seaver conducts an anthropological study of the technologists who design algorithmic music recommendation systems. He explores their ways of thinking and talking about music, taste, and computation to better understand their technological design approaches. By highlighting the humans behind the machines, Computing Taste shows how to think about computer algorithms as sociotechnical systems. Jacob Pleasants publishes book review of The Humans and Algorithms of Music Recommendation: A Review of Computing Taste (2022) [ABSTRACT FROM AUTHOR]

How to improve the high resolution and remove the noise of composite infrared thermal wave detection image have become important research topics in machine vision. Therefore, this paper proposes a composite image enhancement algorithm based on edge adaptive total variation of direction. Using the improved adaptive directional total variation model to construct the guidance image of the guidance filter can provide better structural information for the guidance filter and conduct the guidance filter. This process is iterated to eliminate noise and ladder effect. Experimental results show that this algorithm is superior to other advanced methods in objective evaluation index and subjective vision. The algorithm proposed in this paper can not only effectively eliminate noise and ladder effect, but also highlight image details and structure information, which proves the effectiveness of this algorithm. Discover the cutting-edge algorithm for high-resolution improvement and noise elimination in infrared thermal wave detection images. Our innovative composite image enhancement technique, based on edge adaptive total variation, outperforms traditional methods. The improved directional model provides better structural information, optimizing the guidance filter process. Experimental results reveal its superiority in objective evaluation and subjective vision. This algorithm effectively eliminates noise and ladder effect while highlighting image details, validating its remarkable effectiveness. [ABSTRACT FROM AUTHOR]

With the rapid advancement of internet technology, various industries have accumulated vast amounts of data, including on user behavior and personal preferences. Traditional museums can leverage this user data to uncover individual preferences and offer personalized services to their visitors. However, the exponential growth of information has also led to the problem of information overload, making it challenging for users to find relevant information within the vast data landscape. Consequently, the utilization rate of available information decreases. By harnessing the power of cloud computing, big data analytics, and recommendation systems, museums can enhance visitors' touring experiences by helping them discover collections aligned with their interests and connecting with like-minded individuals. To address this objective, the research focuses on optimizing the initial clustering centers of the fuzzy clustering algorithm and parallelizing the optimized algorithm using MapReduce, resulting in the development of a novel MapReduce-based k-prototype fuzzy c-means (MRKPFCM) algorithm. Subsequently, the MRKPFCM algorithm is combined with the classical collaborative filtering algorithm to create a hybrid and parallelized collaborative filtering recommendation algorithm, incorporating elements such as MRKPFCM, audience, and collection. This hybrid algorithm is further supplemented by a content-based recommendation approach to generate comprehensive and refined recommendation results. Experimental findings demonstrate that the predictive scoring errors, as measured by RMSE and MAE, exhibited a downward trend when the number of nearest neighbors for target users fell within the range of 10–20. For instance, the studied algorithm's MAE value decreased from 0.7512 to 0.7179, surpassing the corresponding figures for the two comparison algorithms. Moreover, with an increase in the number of nearest neighbors within the same range, all three algorithms experienced improved accuracy in prediction results. In particular, the accuracy rate rose from 17.84% to 18.82%, outperforming the two comparison algorithms. In summary, the enhanced hybrid recommendation algorithm achieved through this study displays superior recommendation accuracy and holds significant practical value. [ABSTRACT FROM AUTHOR]

Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended to users. Matrix factorization is widely used in collaborative filtering algorithms because of its simplicity and efficiency. However, the simple dot-product method cannot establish a nonlinear relationship between user latent features and item latent features or make full use of their personalized information. The model of a neural network combined with an attention mechanism can effectively establish a nonlinear relationship between the potential features of users and items and improve the recommendation accuracy of the model. However, it is difficult for the general attention mechanism algorithm to solve the problem of attention interaction when the number of features between the users and items is not the same. To solve the above problems, this paper proposes an attention interaction matrix factorization (AIMF) model. The AIMF model adopts a symmetric structure using MLP calculation. This structure can simultaneously extract the nonlinear features of user latent features and item latent features, thus reducing the computation time of the model. In addition, an improved attention algorithm named slide-attention is included in the model. The algorithm uses the sliding query method to obtain the user's attention to the latent features of the item and solves the interaction problem among different dimensions of the user, and the latent features of the item. [ABSTRACT FROM AUTHOR]

Multi-criteria recommender systems provide efficient solutions to deal with information overload problem by producing personalized recommendations considering multiple criteria. Even though multicriteria recommender systems provide more accurate and personalized recommendations to their users compared with traditional recommender systems, sparsity becomes a major problem for such systems due to the increasing number of criteria. Due to the lack of corated items among users, finding out neighbors and producing accurate predictions become harder. Especially similarity-based multi-criteria recommendation approaches are significantly affected by the sparsity problem. Thus, aiming to minimize the negative impacts of that problem, a hybrid similarity-based multi-criteria recommendation method, that utilizes complex, low-dimensional and latent features obtained from both reviews and criteria ratings by autoencoders, is proposed in this work. The empirical results performed on a real data set with a sparsity percentage of 99.7235% show that the proposed work can provide more accurate predictions compared with other neighborhood-based multi-criteria approaches. [ABSTRACT FROM AUTHOR]

This paper proposes an explainable recommendation algorithm based on deep learning for developing a transparent and explainable recommendation system. The proposed algorithm combines a multi-feature fusion model for text sentiment analysis and the innovative DeepxDeepFM recommendation model to provide accurate and interpretable recommendations. First, Bi-LSTM and MCNN are employed to extract multi-dimensional features from comment data. Then, the DeepxDeepFM recommendation model is used explicitly for comment data with numerous feature vectors and significant linear changes. Finally, experimental results demonstrate that our proposed explainable recommendation algorithm increases the accuracy by 1.57% and decreases the root mean square error by 2.69%, contributing to higher model performance. Compared to other models, the improved interpretable recommendation model is smaller in size and more accurate, so it can maximize the click-through rate of e-commerce recommendation systems, which is crucial for achieving precise recommendations in the field of e-commerce. [ABSTRACT FROM AUTHOR]

With the growing popularity of movies as a source of entertainment and relaxation in modern society, movie recommendation systems have become increasingly important for helping viewers navigate a vast selection of movie products. However, existing methods may not accurately capture the preferences and opinions of viewers. To address this gap, we propose a novel approach that utilizes the Pythagorean hesitant fuzzy distance measure in combination with the VIKOR method to deal with the extracted review information and evaluate the similarity between different movies in a given genre. We then transform this information into Pythagorean hesitant fuzzy attribute evaluation terms using the Probabilistic Linguistic Term Set (PLTS) and apply conflict degree theory to calculate similarity scores. The algorithm proposed in this paper employs the VIKOR method to select recommended movie products that match the preferences of users and satisfy their needs. Comparative analysis demonstrates its reliability and stability. In addition, according to the comparative data, its performance is better than the comparable method in the selection of alternative schemes, which highlights its contribution in the field of movie recommendation systems. [ABSTRACT FROM AUTHOR]

User preferences and ratings may be anticipated by recommendation systems, which are widely used in social networking, online shopping, healthcare, and even energy efficiency. Constructing trustworthy recommender systems for various applications, requires the analysis and mining of vast quantities of user data, including demographics. This study focuses on holding elections with vague voter and candidate preferences. Collaborative user ratings are used by filtering algorithms to provide suggestions. To avoid information overload, consumers are directed towards items that they are more likely to prefer based on the profile data used by recommender systems. Better interactions between governments, residents, and businesses may result from studies on recommender systems that facilitate the use of e-government services. To broaden people's access to the democratic process, the concept of "e-democracy" applies new media technologies. This study provides a framework for an electronic voting advisory system that uses machine learning. [ABSTRACT FROM AUTHOR]

Intelligent tourism can increase the interest of nomadic tourists in discovering new cities. However, many Points of Interest (POIs) are available, creating an information overload for tourists when choosing POIs to visit. For this reason, CARS (Context-Aware Recommendation Systems) can play an important role by exploiting the experiences of previous tourists and their contexts to recommend attractive POIs. Consequently, choosing the right POI recommendation algorithm (RA) for CARS is crucial because it involves the costly intervention of real tourists during the test phase. In order to make this phase more cost-effective, we can test several RAs simultaneously in order to assess their limitations in terms of cold start and tourist satisfaction. To compare these RAs, we propose in this article an approach called SEPRA (Systematic Evaluation for POI Recommendation Algorithms), which allows us to carry out an initial online evaluation of each tourist during their visit and a second offline evaluation of each CARS after the end of each POI path. To achieve this objective, we designed and implemented a new smart tourism tool that makes POI recommendations using two algorithms: the first is based on tourist/tourist similarity, and the second uses POI/POI similarity. These algorithms use memory-based collaborative filtering and are executed in parallel by our tool in the form of CARSs, incorporating time or weather as context variables. To evaluate these systems during their test phases, Our approach enables: (1) the calculation of prediction accuracy; (2) the examination of the relevance of the recommended POIs; and (3) the estimation of the acceptance rate of the recommendation process. Finally, the experimental results obtained with our approach show that the algorithm based on tourist similarity is more resistant to the cold start problem during the test phase and has a better satisfaction rate than the algorithm based on POI similarity. [ABSTRACT FROM AUTHOR]

The article discusses the problem of information overload caused by the rapid development of the Internet and the large amount of available electronic resources. To address this issue, recommender systems are used to filter and classify data based on user behavior and interests. The article highlights various algorithms used in recommender systems, such as content-based systems, collaborative filtering, and hybrid recommender systems. It also introduces a special issue on new trends in algorithms for intelligent recommendation systems, featuring seven research articles that cover topics such as artificial general recommenders, sequential pattern-based e-commerce recommendation systems, addressing the cold-start problem, hybrid recommender systems for the tourism domain, managing natural noises in recommender systems, using graph neural networks for social recommendations, and information retrieval and machine learning methods for academic expert finding. [Extracted from the article]

In today's digital entertainment environment, movie recommendation algorithms are essential for intensifying user ecstasy and content engagement. Online streaming services like Netflix can potentially increase revenue by implementing a recommendation system that offers tailored movie suggestions to users based on their past interactions with the platform. The strategies we'll discuss here are not simply limited to films; they may be used for any product for which you want to develop a Recommendation System (RS). This paper gives a preamble of several types of recommendation strategies based on user preferences, ratings, domain knowledge, users’ demographic data, user’s context. This work also envisions the singular value decomposition plus-plus (SVD++) and collaborative filtering-based movie recommendation method. The suggested method is compared to well-known machine learning methods such as k closest neighbour (K-NN), singular value decomposition (SVD), and co-clustering. The suggested method is experimentally tested using MovieLens 100 K datasets, and the error of the RS is assessed using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). In order to address issues like scalability, data sparsity, and the cold start problem, our study is driven by the requirement to determine the most efficient method for offering individualized movie suggestions. This technique is used by numerous e-commerce companies, including Amazon, Flipkart, and Mantra, to understand their customers' purchasing patterns and provide recommendations to them about the goods they are most likely to purchase. [ABSTRACT FROM AUTHOR]

The optimization and allocation of transport cost savings among stakeholders are two important issues that influence the satisfaction of information providers, drivers and passengers in ridesharing recommendation systems. For optimization issues, finding optimal solutions for nonconvex constrained discrete ridesharing optimization problems poses a challenge due to computational complexity. For the allocation of transport cost savings issues, the development of an effective method to allocate cost savings in ridesharing recommendation systems is an urgent need to improve the acceptability of ridesharing. The hybridization of different metaheuristic approaches has demonstrated its advantages in tackling the complexity of optimization problems. The principle of the hybridization of metaheuristic approaches is similar to a marriage of two people with the goal of having a happy ending. However, the effectiveness of hybrid metaheuristic algorithms is unknown a priori and depends on the problem to be solved. This is similar to a situation where no one knows whether a marriage will have a happy ending a priori. Whether the hybridization of the Firefly Algorithm (FA) with Particle Swarm Optimization (PSO) or Differential Evolution (DE) can work effectively in solving ridesharing optimization problems needs further study. Motivated by deficiencies in existing studies, this paper focuses on the effectiveness of hybrid metaheuristic algorithms for solving ridesharing problems based on the hybridization of FA with PSO or the hybridization of FA with DE. Another focus of this paper is to propose and study the effectiveness of a new method to allocate ridesharing cost savings to the stakeholders in ridesharing systems. The developed hybrid metaheuristic algorithms and the allocation method have been compared with examples of several application scenarios to illustrate their effectiveness. The results indicate that hybridizing FA with PSO creates a more efficient algorithm, whereas hybridizing FA with DE does not lead to a more efficient algorithm for the ridesharing recommendation problem. An interesting finding of this study is very similar to what happens in the real world: "Not all marriages have happy endings". [ABSTRACT FROM AUTHOR]

In existing sequential recommendation systems, user behavior data are directly used as training data for the model to complete the training process and address recommendation tasks. However, user-generated behavioral data inevitably contains noise, and the use of the Transformer's recommendation model may lead to overfitting on such noisy data. To address this issue, we introduce a sequence recommendation algorithm model named FAT-Rec, which incorporates fusion filters and converters through joint training. By employing joint training methods, we establish both a transformer prediction layer and a CTR prediction layer. Toward the end of the model, we assign weights and sum up the losses from the Transformer and CTR prediction layers to derive the final loss function. Experimental results on two widely used datasets, MovieLens and Goodbooks, demonstrate a significant enhancement in the performance of the proposed FAT-Rec recommendation algorithm compared with seven comparative models. This validates the efficacy of the fusion filter and transformer within the context of sequence recommendation tasks under the joint training mechanism. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Heterogeneous information networks (HINs) contain a rich network structure and semantic information, which makes them commonly used in recommendation systems. However, most of the existing HIN-based recommendation systems rely on meta-paths for information extraction, lack meta-path information supplements, and rarely learn complex structure information in heterogeneous graphs. To address these issues, we develop a novel recommendation algorithm that integrates the attention mechanism, meta-paths, and neighbor node information (AMNRec). In the heterogeneous information network, the missing information of the meta-path is supplemented by extracting the information of users and items' neighbor nodes. The rich interactions between nodes are captured through convolution, and the embedded representation of nodes and meta-paths is obtained through the attention mechanism. TOP-N recommendation is completed by combining users, items, neighbor nodes, and meta-paths. Experiments on three public datasets show that AMNRec not only has the best recommendation performance but also has good interpretability of the recommendation results compared with the six recommendation benchmark algorithms. [ABSTRACT FROM AUTHOR]

The book review discusses Ignacio Siles' book, "Living with Algorithms: Agency and User Culture in Costa Rica," which examines the ways in which users in Costa Rica interact with algorithms on platforms such as Spotify, Netflix, and TikTok. Siles argues that users have agency in their interactions with algorithms, but this agency is contextual and influenced by socio-political conditions. The book explores topics such as personalization, social practices, rituals, and resistance, highlighting the complex relationship between algorithms, culture, and individual agency. The review also emphasizes the importance of considering research from outside the Global North and suggests that Siles' book serves as an invitation to explore theories and frameworks from different regions. [Extracted from the article]

Collaborative Filtering remains the most widely used recommendation algorithm due to its simplicity and effectiveness. However, most studies addressing the trade-off between accuracy and diversity in collaborative filtering recommendation algorithms focus solely on optimizing the recommendation list, often neglecting users’ diverse demands for recommendation results. We propose a new user-based Two-Stage collaborative filtering method for Neighborhood Selection (TSNS) that considers both the similarity between users and the dissimilarity between neighbors in the neighborhood selection phase. Firstly, we define the user’s preference value for the attributes of evaluated items and determine the range and ranking of user preferences. Then, we construct a preference heterogeneity model to evaluate preference differences among users and obtain a preference heterogeneity matrix based on the range and ranking of preferences. Finally, to effectively ensure recommendation accuracy and diversity, we adopt a two-stage neighborhood selection method to identify a group of neighbors that are internally dissimilar but similar to target users. Deep representation learning methods can also be incorporated into this framework to calculate user similarity in the first stage. Experimental results on two datasets show that our proposed method outperforms the benchmark method, including those using deep learning, in terms of comprehensive performance. Our approach offers new insights into improving the accuracy and diversity of personalized recommendations. [ABSTRACT FROM AUTHOR]

This paper discusses the use of portfolio approaches based on bandit algorithms to optimize multicriteria decision-making in recommender systems (accuracy and diversity). While previous research has primarily focused on single-item recommendations, this study extends the research to consider the recommendation of several items per iteration. Two methods, Multiple-play Gorthaur and Budgeted-Gorthaur, are proposed to solve the algorithm selection problem and their performances on real-world datasets are compared. Both methods provide a generalization of the Gorthaur method, which enables it to operate with any Multi-Armed Bandit (MAB) and Contextual Multi-Armed Bandit (CMAB) algorithm as meta-algorithm in a multi-item recommendation scenario. For Multiple-play Gorthaur, an empirical evaluation shows that the use of Thompson Sampling for algorithm selection (Gorthaur-TS) yields better results than the original EXP3 method (Gorthaur-EXP3) and the exclusive use of the optimal algorithm in the portfolio in contextual recommendation problems. Additionally, the paper includes a theoretical regret analysis based on the TS sketch proof applied for this variant of the method. Concerning Budgeted-Gorthaur, experiments show that it allows more flexibility to achieve a suitable trade-off between criteria and a broader coverage of the Pareto set of solutions, overcoming a natural limit of "a-priori" methods. Finally, this paper provides a detailed review, including pseudocodes and theoretical bounds, for all the fundamental MAB and CMAB algorithms used in this study. • Bandit literature lacks formal algorithm review, hindering clarity and comparability. • There is no silver bullet: no algorithm can be the best performer in every instance. • Recommender systems need to balance accuracy, diversity, multi-item recommendations. • Optimal algorithm balances criteria, matching decision maker's preferred trade-off. • Dynamic selection ensures safe performance when optimal algorithm is unknown. [ABSTRACT FROM AUTHOR]

Nowadays, we are surrounded by various types of data from different modalities, such as text, images, audio, and video. The existence of this multimodal data provides us with rich information, but it also brings new challenges: how do we effectively utilize this data for accurate classification? This is the main problem faced by multimodal classification tasks. Multimodal classification is an important task that aims to classify data from different modalities. However, due to the different characteristics and structures of data from different modalities, effectively fusing and utilizing them for classification is a challenging problem. To address this issue, we propose a cross-attention contextual transformer with modality-collaborative learning for multimodal classification (CACT-MCL-MMC) to better integrate information from different modalities. On the one hand, existing multimodal fusion methods ignore the intra- and inter-modality relationships, and there is unnoticed information in the modalities, resulting in unsatisfactory classification performance. To address the problem of insufficient interaction of modality information in existing algorithms, we use a cross-attention contextual transformer to capture the contextual relationships within and among modalities to improve the representativeness of the model. On the other hand, due to differences in the quality of information among different modalities, some modalities may have misleading or ambiguous information. Treating each modality equally may result in modality perceptual noise, which reduces the performance of multimodal classification. Therefore, we use modality-collaborative to filter misleading information, alleviate the quality difference of information among modalities, align modality information with high-quality and effective modalities, enhance unimodal information, and obtain more ideal multimodal fusion information to improve the model's discriminative ability. Our comparative experimental results on two benchmark datasets for image-text classification, CrisisMMD and UPMC Food-101, show that our proposed model outperforms other classification methods and even state-of-the-art (SOTA) multimodal classification methods. Meanwhile, the effectiveness of the cross-attention module, multimodal contextual attention network, and modality-collaborative learning was verified through ablation experiments. In addition, conducting hyper-parameter validation experiments showed that different fusion calculation methods resulted in differences in experimental results. The most effective feature tensor calculation method was found. We also conducted qualitative experiments. Compared with the original model, our proposed model can identify the expected results in the vast majority of cases. The codes are available at https://github.com/KobeBryant8-24-MVP/CACT-MCL-MMC. The CrisisMMD is available at https://dataverse.mpisws.org/dataverse/icwsm18, and the UPMC-Food-101 is available at https://visiir.isir.upmc.fr/. [ABSTRACT FROM AUTHOR]