Causally estimating the effect of YouTube's recommender system using counterfactual bots.

In recent years, critics of online platforms have raised concerns about the ability of recommendation algorithms to amplify problematic content, with potentially radicalizing consequences. However, attempts to evaluate the effect of recommenders have suffered from a lack of appropriate counterfactuals-what a user would have viewed in the absence of algorithmic recommendations-and hence cannot disentangle the effects of the algorithm from a user's intentions. Here we propose a method that we call "counterfactual bots" to causally estimate the role of algorithmic recommendations on the consumption of highly partisan content on YouTube. By comparing bots that replicate real users' consumption patterns with "counterfactual" bots that follow rule-based trajectories, we show that, on average, relying exclusively on the YouTube recommender results in less partisan consumption, where the effect is most pronounced for heavy partisan consumers. Following a similar method, we also show that if partisan consumers switch to moderate content, YouTube's sidebar recommender "forgets" their partisan preference within roughly 30 videos regardless of their prior history, while homepage recommendations shift more gradually toward moderate content. Overall, our findings indicate that, at least since the algorithm changes that YouTube implemented in 2019, individual consumption patterns mostly reflect individual preferences, where algorithmic recommendations play, if anything, a moderating role.

MiRAGE: mining relationships for advanced generative evaluation in drug repositioning.

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.

Showing high-achieving college applicants past admissions outcomes increases undermatching.

More than 40% of US high school students have access to Naviance, a proprietary tool designed to guide college search and application decisions. The tool displays, for individual colleges, the standardized test scores, grade-point averages, and admissions outcomes of past applicants from a student's high school, so long as a sufficient number of students from previous cohorts applied to a given college. This information is intended to help students focus their efforts on applying to the most suitable colleges, but it may also influence application decisions in undesirable ways. Using data on 70,000 college applicants across 220 public high schools, we assess the effects of access to Naviance on application undermatch, or applying only to schools for which a candidate is academically overqualified. By leveraging variation in the year that high schools adopted the tool, we estimate that Naviance increased application undermatching by more than 50% among 17,000 high-achieving students in our dataset. This phenomenon may be due to increased conservatism: Students may be less likely to apply to colleges when they know their academic qualifications fall below the average of admitted students from their high school. These results illustrate how information on college competitiveness, when not appropriately presented and contextualized, can lead to unintended consequences.

A comparison of embedding aggregation strategies in drug-target interaction prediction.

The prediction of interactions between novel drugs and biological targets is a vital step in the early stage of the drug discovery pipeline. Many deep learning approaches have been proposed over the last decade, with a substantial fraction of them sharing the same underlying two-branch architecture. Their distinction is limited to the use of different types of feature representations and branches (multi-layer perceptrons, convolutional neural networks, graph neural networks and transformers). In contrast, the strategy used to combine the outputs (embeddings) of the branches has remained mostly the same. The same general architecture has also been used extensively in the area of recommender systems, where the choice of an aggregation strategy is still an open question. In this work, we investigate the effectiveness of three different embedding aggregation strategies in the area of drug-target interaction (DTI) prediction. We formally define these strategies and prove their universal approximator capabilities. We then present experiments that compare the different strategies on benchmark datasets from the area of DTI prediction, showcasing conditions under which specific strategies could be the obvious choice.

Creating a computer assisted ICD coding system: Performance metric choice and use of the ICD hierarchy.

OBJECTIVE: Machine learning methods hold the promise of leveraging available data and generating higher-quality data while alleviating the data collection burden on healthcare professionals. International Classification of Diseases (ICD) diagnoses data, collected globally for billing and epidemiological purposes, represents a valuable source of structured information. However, ICD coding is a challenging task. While numerous previous studies reported promising results in automatic ICD classification, they often describe input data specific model architectures, that are heterogeneously evaluated with different performance metrics and ICD code subsets. This study aims to explore the evaluation and construction of more effective Computer Assisted Coding (CAC) systems using generic approaches, focusing on the use of ICD hierarchy, medication data and a feed forward neural network architecture. METHODS: We conduct comprehensive experiments using the MIMIC-III clinical database, mapped to the OMOP data model. Our evaluations encompass various performance metrics, alongside investigations into multitask, hierarchical, and imbalanced learning for neural networks. RESULTS: We introduce a novel metric, , tailored to the ICD coding task, which offers interpretable insights for healthcare informatics practitioners, aiding them in assessing the quality of assisted coding systems. Our findings highlight that selectively cherry-picking ICD codes diminish retrieval performance without performance improvement over the selected subset. We show that optimizing for metrics such as NDCG and AUPRC outperforms traditional F1-based metrics in ranking performance. We observe that Neural Network training on different ICD levels simultaneously offers minor benefits for ranking and significant runtime gains. However, our models do not derive benefits from hierarchical or class imbalance correction techniques for ICD code retrieval. CONCLUSION: This study offers valuable insights for researchers and healthcare practitioners interested in developing and evaluating CAC systems. Using a straightforward sequential neural network model, we confirm that medical prescriptions are a rich data source for CAC systems, providing competitive retrieval capabilities for a fraction of the computational load compared to text-based models. Our study underscores the importance of metric selection and challenges existing practices related to ICD code sub-setting for model training and evaluation.

Rethinking Health Recommender Systems for Active Aging: An Autonomy-Based Ethical Analysis.

Health Recommender Systems are promising Articial-Intelligence-based tools endowing healthy lifestyles and therapy adherence in healthcare and medicine. Among the most supported areas, it is worth mentioning active aging. However, current HRS supporting AA raise ethical challenges that still need to be properly formalized and explored. This study proposes to rethink HRS for AA through an autonomy-based ethical analysis. In particular, a brief overview of the HRS' technical aspects allows us to shed light on the ethical risks and challenges they might raise on individuals' well-being as they age. Moreover, the study proposes a categorization, understanding, and possible preventive/mitigation actions for the elicited risks and challenges through rethinking the AI ethics core principle of autonomy. Finally, elaborating on autonomy-related ethical theories, the paper proposes an autonomy-based ethical framework and how it can foster the development of autonomy-enabling HRS for AA.

Improvement of multi-task learning by data enrichment: application for drug discovery.

Multi-task learning in deep neural networks has become a topic of growing importance in many research fields, including drug discovery. However, applying multi-task learning poses new challenges in improving prediction performance. This study investigated the potential of training data enrichment to enhance multi-task model prediction quality in drug discovery. The study evaluated four scenarios with varying degrees of information capacity of the training data and applied two types of test data to evaluate prediction performance. We used three datasets: ViralChEMBL, which consisted of binary activities of compounds against viral species, was applied for the classification task; pQSAR(159) and pQSAR(4267), which consisted of bio-activities of compounds and assays from the research of the profile-QSAR method, were applied for regression tasks. We built multi-task models based on the feed-forward DNNs using the PyTorch framework. Our findings showed that training data enrichment could be an effective means of enhancing prediction performance in multi-task learning, but the degree of improvement depends on the quality of the training data. The more unique compounds and targets the training data included, the more new compound-target interactions are required for prediction improvement. Also, we found out that even using multi-task learning, one could not predict the interactions of compounds that are highly dissimilar from those used for model training. The study provides some recommendations for effectively employing multi-task learning in drug discovery to improve prediction accuracy and facilitate the discovery of novel drug candidates.

Development and Evaluation of Health Recommender Systems: Systematic Scoping Review and Evidence Mapping.

BACKGROUND: Health recommender systems (HRSs) are information retrieval systems that provide users with relevant items according to the users' needs, which can motivate and engage users to change their behavior. OBJECTIVE: This study aimed to identify the development and evaluation of HRSs and create an evidence map. METHODS: A total of 6 databases were searched to identify HRSs reported in studies from inception up to June 30, 2022, followed by forward citation and grey literature searches. Titles, abstracts, and full texts were screened independently by 2 reviewers, with discrepancies resolved by a third reviewer, when necessary. Data extraction was performed by one reviewer and checked by a second reviewer. This review was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) statement. RESULTS: A total of 51 studies were included for data extraction. Recommender systems were used across different health domains, such as general health promotion, lifestyle, and generic health service. A total of 23 studies had reported the use of a combination of recommender techniques, classified as hybrid recommender systems, which are the most commonly used recommender techniques in HRSs. In the HRS design stage, only 10 of 51 (19.6%) recommender systems considered personal preferences of end users in the design or development of the system; a total of 29 studies reported the user interface of HRSs, and most HRSs worked on users' mobile interfaces, usually a mobile app. Two categories of HRS evaluations were used, and evaluations of HRSs varied greatly; 62.7% (32/51) of the studies used the offline evaluations using computational methods (no user), and 33.3% (17/51) of the studies included end users in their HRS evaluation. CONCLUSIONS: Through this scoping review, nonmedical professionals and policy makers can visualize and better understand HRSs for future studies. The health care professionals and the end users should be encouraged to participate in the future design and development of HRSs to optimize their utility and successful implementation. Detailed evaluations of HRSs in a user-centered approach are needed in future studies.

M2: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation.

Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions (M2) for the next-basket recommendation. This method models three important factors in next-basket generation process: 1) users' general preferences, 2) items' global popularities and 3) transition patterns among items. Unlike existing recurrent neural network-based approaches, M2 does not use the complicated networks to model the transitions among items, or generate embeddings for users. Instead, it has a simple encoder-decoder based approach (ed-Trans) to better model the transition patterns among items. We compared M2 with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket. Our experimental results demonstrate that M2 significantly outperforms the state-of-the-art methods on all the datasets in all the tasks, with an improvement of up to 22.1%. In addition, our ablation study demonstrates that the ed-Trans is more effective than recurrent neural networks in terms of the recommendation performance. We also have a thorough discussion on various experimental protocols and evaluation metrics for next-basket recommendation evaluation.

A systematic literature review on educational recommender systems for teaching and learning: research trends, limitations and opportunities.

Recommender systems have become one of the main tools for personalized content filtering in the educational domain. Those who support teaching and learning activities, particularly, have gained increasing attention in the past years. This growing interest has motivated the emergence of new approaches and models in the field, in spite of it, there is a gap in literature about the current trends on how recommendations have been produced, how recommenders have been evaluated as well as what are the research limitations and opportunities for advancement in the field. In this regard, this paper reports the main findings of a systematic literature review covering these four dimensions. The study is based on the analysis of a set of primary studies (N = 16 out of 756, published from 2015 to 2020) included according to defined criteria. Results indicate that the hybrid approach has been the leading strategy for recommendation production. Concerning the purpose of the evaluation, the recommenders were evaluated mainly regarding the quality of accuracy and a reduced number of studies were found that investigated their pedagogical effectiveness. This evidence points to a potential research opportunity for the development of multidimensional evaluation frameworks that effectively support the verification of the impact of recommendations on the teaching and learning process. Also, we identify and discuss main limitations to clarify current difficulties that demand attention for future research. Supplementary Information: The online version contains supplementary material available at 10.1007/s10639-022-11341-9.

Deep reinforcement learning for personalized treatment recommendation.

In precision medicine, the ultimate goal is to recommend the most effective treatment to an individual patient based on patient-specific molecular and clinical profiles, possibly high-dimensional. To advance cancer treatment, large-scale screenings of cancer cell lines against chemical compounds have been performed to help better understand the relationship between genomic features and drug response; existing machine learning approaches use exclusively supervised learning, including penalized regression and recommender systems. However, it would be more efficient to apply reinforcement learning to sequentially learn as data accrue, including selecting the most promising therapy for a patient given individual molecular and clinical features and then collecting and learning from the corresponding data. In this article, we propose a novel personalized ranking system called Proximal Policy Optimization Ranking (PPORank), which ranks the drugs based on their predicted effects per cell line (or patient) in the framework of deep reinforcement learning (DRL). Modeled as a Markov decision process, the proposed method learns to recommend the most suitable drugs sequentially and continuously over time. As a proof-of-concept, we conduct experiments on two large-scale cancer cell line data sets in addition to simulated data. The results demonstrate that the proposed DRL-based PPORank outperforms the state-of-the-art competitors based on supervised learning. Taken together, we conclude that novel methods in the framework of DRL have great potential for precision medicine and should be further studied.

Teammate Invitation Networks: The Roles of Recommender Systems and Prior Collaboration in Team Assembly.

Teammate invitation networks are foundational for team assembly, and recommender systems (similar to dating websites, but for selecting potential teammates) can aid the formation of such networks. This paper extends Hinds, Carley, Krackhardt, and Wholey's (2000) influential model of team member selection by incorporating online recommender systems. Exponential random graph modeling of two samples (overall N = 410; 63 teams; 1,048 invitations) shows the invitation network is predicted by online recommendations, beyond previously-established effects of prior collaboration/familiarity, skills/competence, and homophily. Importantly, online recommendations are less heeded when there is prior collaboration (effect replicates across samples). This study highlights technology-enabled team assembly from a network perspective.

Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction.

Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model.

A Ranking Recommendation Algorithm Based on Dynamic User Preference.

In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods.

A Data Warehouse-Based System for Service Customization Recommendations in Product-Service Systems.

Nowadays, manufacturers are shifting from a traditional product-centric business paradigm to a service-centric one by offering products that are accompanied by services, which is known as Product-Service Systems (PSSs). PSS customization entails configuring products with varying degrees of differentiation to meet the needs of various customers. This is combined with service customization, in which configured products are expanded by customers to include smart IoT devices (e.g., sensors) to improve product usage and facilitate the transition to smart connected products. The concept of PSS customization is gaining significant interest; however, there are still numerous challenges that must be addressed when designing and offering customized PSSs, such as choosing the optimum types of sensors to install on products and their adequate locations during the service customization process. In this paper, we propose a data warehouse-based recommender system that collects and analyzes large volumes of product usage data from similar products to the product that the customer needs to customize by adding IoT smart devices. The analysis of these data helps in identifying the most critical parts with the highest number of incidents and the causes of those incidents. As a result, sensor types are determined and recommended to the customer based on the causes of these incidents. The utility and applicability of the proposed RS have been demonstrated through its application in a case study that considers the rotary spindle units of a CNC milling machine.

HAM: Hybrid Associations Models for Sequential Recommendation.

Sequential recommendation aims to identify and recommend the next few items for a user that the user is most likely to purchase/review, given the user's purchase/rating trajectories. It becomes an effective tool to help users select favorite items from a variety of options. In this manuscript, we developed hybrid associations models (HAM) to generate sequential recommendations. using three factors: 1) users' long-term preferences, 2) sequential, high-order and low-order association patterns in the users' most recent purchases/ratings, and 3) synergies among those items. HAM uses simplistic pooling to represent a set of items in the associations, and element-wise product to represent item synergies of arbitrary orders. We compared HAM models with the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings. Our experimental results demonstrate that HAM models significantly outperform the state of the art in all the experimental settings. with an improvement as much as 46.6%. In addition, our run-time performance comparison in testing demonstrates that HAM models are much more efficient than the state-of-the-art methods. and are able to achieve significant speedup as much as 139.7 folds.

MIGAN: Mutual-Interaction Graph Attention Network for Collaborative Filtering.

Many web platforms now include recommender systems. Network representation learning has been a successful approach for building these efficient recommender systems. However, learning the mutual influence of nodes in the network is challenging. Indeed, it carries collaborative signals accounting for complex user-item interactions on user decisions. For this purpose, in this paper, we develop a Mutual Interaction Graph Attention Network "MIGAN", a new algorithm based on self-supervised representation learning on a large-scale bipartite graph (BGNN). Experimental investigation with real-world data demonstrates that MIGAN compares favorably with the baselines in terms of prediction accuracy and recommendation efficiency.

Health Recommender Systems: Systematic Review.

BACKGROUND: Health recommender systems (HRSs) offer the potential to motivate and engage users to change their behavior by sharing better choices and actionable knowledge based on observed user behavior. OBJECTIVE: We aim to review HRSs targeting nonmedical professionals (laypersons) to better understand the current state of the art and identify both the main trends and the gaps with respect to current implementations. METHODS: We conducted a systematic literature review according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and synthesized the results. A total of 73 published studies that reported both an implementation and evaluation of an HRS targeted to laypersons were included and analyzed in this review. RESULTS: Recommended items were classified into four major categories: lifestyle, nutrition, general health care information, and specific health conditions. The majority of HRSs use hybrid recommendation algorithms. Evaluations of HRSs vary greatly; half of the studies only evaluated the algorithm with various metrics, whereas others performed full-scale randomized controlled trials or conducted in-the-wild studies to evaluate the impact of HRSs, thereby showing that the field is slowly maturing. On the basis of our review, we derived five reporting guidelines that can serve as a reference frame for future HRS studies. HRS studies should clarify who the target user is and to whom the recommendations apply, what is recommended and how the recommendations are presented to the user, where the data set can be found, what algorithms were used to calculate the recommendations, and what evaluation protocol was used. CONCLUSIONS: There is significant opportunity for an HRS to inform and guide health actions. Through this review, we promote the discussion of ways to augment HRS research by recommending a reference frame with five design guidelines.

A Systematic Review of Recommender Systems and Their Applications in Cybersecurity.

This paper discusses the valuable role recommender systems may play in cybersecurity. First, a comprehensive presentation of recommender system types is presented, as well as their advantages and disadvantages, possible applications and security concerns. Then, the paper collects and presents the state of the art concerning the use of recommender systems in cybersecurity; both the existing solutions and future ideas are presented. The contribution of this paper is two-fold: to date, to the best of our knowledge, there has been no work collecting the applications of recommenders for cybersecurity. Moreover, this paper attempts to complete a comprehensive survey of recommender types, after noticing that other works usually mention two-three types at once and neglect the others.

Efficient Graph Collaborative Filtering via Contrastive Learning.

Collaborative filtering (CF) aims to make recommendations for users by detecting user's preference from the historical user-item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user-item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.