Sparsity Issue Research Articles

RDERL: Reliable deep ensemble reinforcement learning-based recommender system

Recommender systems (RSs) have been employed for many real-world applications including search engines, social networks, and information retrieval systems as powerful intelligent techniques for creating personalized recommendations. RSs mainly utilize different data resources such as user-item ratings, tag data, and social relationships in their recommendation process to overcome the data sparsity issue. One of the main challenges is how to integrate the results obtained by these data resources. Moreover, most of the existing RSs focus on the recommendation accuracy, and do not consider the reliability of the recommendations. To address these challenges, in this study, a reliable recommendation method is developed, which employs deep neural networks and reinforcement learning. The proposed method firstly uses a stacked denoising autoencoder model to obtain the latent features from the rating, tag, and trust data. The similarity value between each pair of users is then calculated in three different aspects according to the extracted latent features. An ensemble approach is developed by integrating the three similarities using reinforcement learning to determine the final similarity value. The ensemble similarity values are used in the rating prediction process, and the reliability of the predicted ratings is evaluated using an effective measure. Finally, a recommendation strategy is developed based on the integration of the predicted ratings and their reliability values. We evaluated the effectiveness of the proposed method by conducting numerous experiments on three datasets where the results show that the proposed method is far superior to other recommendation models in making more accurate recommendations.

Interaction Modelling of High Dimensional Production Data

The final goal of this study is to present a practical interaction modeling methodology for big and complex industrial data in which there are mixed difficulty of high dimension, sparsity, interaction, multicollinearity, series bias, low signal noise ratio, nonlinearity, and so on. Particularly, this paper focuses on the issues of high dimension, sparsity, and interactions. In addition, it is necessary to estimate unknown factors and interactions in order to improve overall efficiency in complex and diverse situations of industry. The main purpose here is to summarize the applicability and challenges of Factorization Machines (FMs) to manufacturing data. FMs has possibility because of the ad-vantage of to identify unknown factors and its robustness to data with more than 95% missing values which has already been reported for recommendation problems. Manufacturing data assumed here incudes the inspected quality of the final products, and a set of various variables (settings, sensing results, etc.) of the series production process which may relate to the quality. Common characteristics of manufacturing data include mixture of numerical and categorical variables, high dimensionality, many missing values, and so on. Therefore, this paper particularly focuses on sparse high-dimensional type-mix data. So far, while interaction modeling of high-dimensional data has been discussed and verified, mainly for screening methods, still there is very few studies to apply FMs to the manufacturing data with many numerical variables. There-fore, we report the evaluation results using some synthesis data and simulation data from actual oracle model to summarize FMs applicability as the first step. The second step is to compare the performance of sparse FMs which has feature selection function, beside our proposal.

XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph augmentations of the user-item bipartite graph. This self-supervised approach allows for the extraction of general features from raw data, thereby mitigating the issue of data sparsity. Despite the effectiveness of this paradigm, the factors contributing to its performance gains have yet to be fully understood. This paper provides novel insights into the impact of CL on recommendation. Our findings indicate that CL enables the model to learn more evenly distributed user and item representations, which alleviates the prevalent popularity bias and promoting long-tail items. Our analysis also suggests that the graph augmentations, previously considered essential, are relatively unreliable and of limited significance in CL-based recommendation. Based on these findings, we put forward an e <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">X</b> tremely <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sim</b> ple <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> raph <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ontrastive <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</b> earning method ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">XSimGCL</b> ) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to generate views for CL. A comprehensive experimental study on four large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code and used datasets are released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Coder-Yu/SELFRec</uri> .

An Assessment of Crop-Specific Land Cover Predictions Using High-Order Markov Chains and Deep Neural Networks

High-Order Markov Chains (HOMC) are conventional models, based on transition probabilities, that are used by the United States Department of Agriculture (USDA) National Agricultural Statistics Service (NASS) to study crop-rotation patterns over time. However, HOMCs routinely suffer from sparsity and identifiability issues because the categorical data are represented as indicator (or dummy) variables. In fact, the dimension of the parametric space increases exponentially with the order of HOMCs required for analysis. While parsimonious representations reduce the number of parameters, as has been shown in the literature, they often result in less accurate predictions. Most parsimonious models are trained on big data structures, which can be compressed and efficiently processed using alternative algorithms. Consequently, a thorough evaluation and comparison of the prediction results obtain using a new HOMC algorithm and different types of Deep Neural Networks (DNN) across a range of agricultural conditions is warranted to determine which model is most appropriate for operational crop specific land cover prediction of United States (US) agriculture. In this paper, six neural network models are applied to crop rotation data between 2011 and 2021 from six agriculturally intensive counties, which reflect the range of major crops grown and a variety of crop rotation patterns in the Midwest and southern US. The six counties include: Renville, North Dakota; Perkins, Nebraska; Hale, Texas; Livingston, Illinois; McLean, Illinois; and Shelby, Ohio. Results show the DNN models achieve higher overall prediction accuracy for all counties in 2021. The proposed DNN models allow for the ingestion of long time series data, and robustly achieve higher accuracy values than a new HOMC algorithm considered for predicting crop specific land cover in the US.

Multi-criteria– Recommendations using Autoencoder and Deep Neural Networks with Weight Optimization using Firefly Algorithm

Demand for personalized recommendation systems elevated recently by e-commerce, news portals etc., to grab the customer interest on the sites. Collaborative filtering proves to be powerful technique but it always suffers from data sparsity, cold-start and robustness issues. These issues have been tackled by some approaches resulting in higher accuracy. Few of them take user profiles, item attributes and rating time as the side information along with ratings to give interpretative personalized recommendations. These type of approaches tries to find which factors mainly impacted the user to rate an item. Another approach extends the single-criteria ratings of collaborative filtering to multi-criteria ratings. Our approach exploits non-linear interpretative recommendations by exploring Multi-criteria ratings by combination of Autoencoders with dropout layer and firefly algorithm optimized weights for deep neural networks. Our approach solves data sparsity, scalability issues and fetch accurate recommendations. Experimental evaluations have been done using Yahoo! Movie and MovieLens datasets. Our approach outperforms in robustness and accuracy with respect to previous research works.

A Classification Method for English Texts Based on Hybrid Recurrent Neural Network and Graph Construction in Social Recommendation Systems

Text classification (TC) methods are widely used in the field of recommendation systems. Text data has the characteristics of short length, large capacity, and variable data distribution, resulting in sparsity and concept drift issues, which pose challenges to text classification methods. In view of this, a recursive neural network and graph construction method has been proposed for classifying English texts in social recommendation systems. First, the English text document serves as the original dataset. Then, the data is preprocessed through tokenization, removal of stop words, stemming, and min-max normalization. Meanwhile, the principal component analysis is used to extract text features from English texts. Finally, feature selection is performed using information gain technology to improve text classification performance. The simulation results show that compared with the comparison method, the proposed algorithm has ideal results in accuracy, precision, recall, F1-score, true positive rate, and false positive rate. Meanwhile, based on experimental data, it was found that the proposed method outperforms state-of-the-art methods in text analysis of English text works.

Expert Recommendation in Community Question Answering via Heterogeneous Content Network Embedding

Expert Recommendation (ER) aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering (CQA) web services. How to model questions and users in the heterogeneous content network is critical to this task. Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues. Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling. However, they often fail to distinguish the nodes’ personalized preferences and only consider the textual content of a part of the nodes in network embedding learning, while ignoring the semantic relevance of nodes. In this paper, we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively. Specifically, we learn topology-based embeddings through a hierarchical attentive network learning strategy, in which the proximity information and the personalized preference of nodes are encoded and preserved. Meanwhile, we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model. In addition, the user’s relative answer quality is incorporated to promote the ranking performance. Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together. The performance of the proposed work is analyzed in terms of MRR, P@K, and MAP and is proven to be more advanced than the existing methodologies.

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

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

Exploring the optimization of autoencoder design for imputing single-cell RNA sequencing data

Autoencoders are the backbones of many imputation methods that aim to relieve the sparsity issue in single-cell RNA sequencing (scRNA-seq) data. The imputation performance of an autoencoder relies on both the neural network architecture and the hyperparameter choice. So far, literature in the single-cell field lacks a formal discussion on how to design the neural network and choose the hyperparameters. Here, we conducted an empirical study to answer this question. Our study used many real and simulated scRNA-seq datasets to examine the impacts of the neural network architecture, the activation function, and the regularization strategy on imputation accuracy and downstream analyses. Our results show that (i) deeper and narrower autoencoders generally lead to better imputation performance; (ii) the sigmoid and tanh activation functions consistently outperform other commonly used functions including ReLU; (iii) regularization improves the accuracy of imputation and downstream cell clustering and DE gene analyses. Notably, our results differ from common practices in the computer vision field regarding the activation function and the regularization strategy. Overall, our study offers practical guidance on how to optimize the autoencoder design for scRNA-seq data imputation.

ROME: A Graph Contrastive Multi-View Framework From Hyperbolic Angular Space for MOOCs Recommendation

As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does not take into account the user’s learning needs with some particular subjects. However, all existing graph models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts, which may lead to biased recommendations, or by constructing improper contrasting pairs, which may result in graph noise. To overcome both challenges, we propose a g <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> aph c <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</u> ntrastive <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> ulti-view fram <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> work (ROME) from hyperbolic angular space to learn user and concept representations based on user-user and concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as different views of graph and maximize the mutual information between them. Furthermore, we maximize the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power. Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users.

Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive end-to-end ASR systems is hindered by the scarcity of speaker-level data and performance sensitivity to transcription errors. To address these issues, a set of compact and data efficient speaker-dependent (SD) parameter representations are used to facilitate both speaker adaptive training and test-time unsupervised speaker adaptation of state-of-the-art Conformer ASR systems. The sensitivity to supervision quality is reduced using a confidence score-based selection of the less erroneous subset of speaker-level adaptation data. Two lightweight confidence score estimation modules are proposed to produce more reliable confidence scores. The data sparsity issue, which is exacerbated by data selection, is addressed by modelling the SD parameter uncertainty using Bayesian learning. Experiments on the benchmark 300-hour Switchboard and the 233-hour AMI datasets suggest that the proposed confidence score-based adaptation schemes consistently outperformed the baseline speaker-independent (SI) Conformer model and conventional non-Bayesian, point estimate-based adaptation using no speaker data selection. Similar consistent performance improvements were retained after external Transformer and LSTM language model rescoring. In particular, on the 300-hour Switchboard corpus, statistically significant WER reductions of 1.0%, 1.3%, and 1.4% absolute (9.5%, 10.9%, and 11.3% relative) were obtained over the baseline SI Conformer on the NIST Hub5'00, RT02, and RT03 evaluation sets respectively. Similar WER reductions of 2.7% and 3.3% absolute (8.9% and 10.2% relative) were also obtained on the AMI development and evaluation sets.

Matrix reconstruction with reliable neighbors for predicting potential MiRNA-disease associations.

Numerous experimental studies have indicated that alteration and dysregulation in mircroRNAs (miRNAs) are associated with serious diseases. Identifying disease-related miRNAs is therefore an essential and challenging task in bioinformatics research. Computational methods are an efficient and economical alternative to conventional biomedical studies and can reveal underlying miRNA-disease associations for subsequent experimental confirmation with reasonable confidence. Despite the success of existing computational approaches, most of them only rely on the known miRNA-disease associations to predict associations without adding other data to increase the prediction accuracy, and they are affected by issues of data sparsity. In this paper, we present MRRN, a model that combines matrix reconstruction with node reliability to predict probable miRNA-disease associations. In MRRN, the most reliable neighbors of miRNA and disease are used to update the original miRNA-disease association matrix, which significantly reduces data sparsity. Unknown miRNA-disease associations are reconstructed by aggregating the most reliable first-order neighbors to increase prediction accuracy by representing the local and global structure of the heterogeneous network. Five-fold cross-validation of MRRN produced an area under the curve (AUC) of 0.9355 and area under the precision-recall curve (AUPR) of 0.2646, values that were greater than those produced by comparable models. Two different types of case studies using three diseases were conducted to demonstrate the accuracy of MRRN, and all top 30 predicted miRNAs were verified.

TRUST: A Novel Framework for Vehicle Trajectory Recovery from Urban-Scale Videos.

We study a new type of path inference query against urban-scale video databases. Given a vehicle image query, our goal is to recover its historical trajectory from the footprints captured by surveillance cameras deployed across the road network. The problem is challenging because visual matching inherently suffers from object occlusion, low camera resolution, varying illumination conditions, and viewing angles. Furthermore, with limited computation resources, only a fraction of video frames can be ingested and indexed, causing severe data sparsity issues for visual matching. To support efficient and accurate trajectory recovery, we develop a select-and-refine framework in a heterogeneous hardware environment with both CPUs and GPUs. We construct a proximity graph from the top-k visually similar frames and propose holistic scoring functions based on visual and spatial-temporal coherence. To avoid enumerating all the paths, we also propose a coarse-grained scoring function with monotonic property to reduce search space. Finally, the derived path is refined by examining raw video frames to fill the missing cameras. For performance evaluation, we construct two largest-scale video databases generated from cameras deployed upon real road networks. Experimental results validate the efficiency and accuracy of our proposed trajectory recovery framework.

Contextualized Recommendation of Aviation Ancillary Services Based on Passenger Portraits

Ancillary services are crucial to Chinese domestic airlines’ profits. Personalized recommendations for ancillary aviation services must consider massive amounts of contextualized online and offline data. The issue of sparsity is more serious in massive data, which makes traditional collaborative filtering (CF) algorithms less accurate. This article adds instant contextualized travel-related factors to the modeling of air passengers’ ancillary services, thus achieving dynamic recommendations. It also proposes a four-tuple to construct a contextual ontology as a conceptual model of ancillary aviation services. The article establishes a context-aware air passenger portrait model based on four tag sets, including passenger attribute tags, ancillary service attribute tags, passenger interaction behavior tags, and contextual attribute tags. Further, it proposes a multidimensional method for calculating contextual portrait similarity; the method recommends a list of the top- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> items to the target passenger according to the similarity calculation. Compared with the traditional CF recommendation method, the proposed algorithm has better performance, improving the accuracy rate by 4.3% and the recall rate by 2.62%. The final experimental result demonstrates that the contextual recommendation method achieves higher passenger satisfaction, which can provide consolidated data and decision support for the management of aviation ancillary services.

The impact of multi-criteria ratings in social networking sites on the performance of online recommendation agents

Recommender Systems (RSs) have played an important role in online retailing portals and customers’ decision-making processes. Recommender systems that are based on the conventional Collaborative Filtering (CF) approach rely on single customers’ ratings on retailing websites. Multi-criteria CF (MCCF) approaches that rely on multi-aspects of the products have provided more reliable and effective recommendations on retailing websites. However, these approaches should be improved in terms of accuracy by solving sparsity issues and incorporating criteria ratings. In addition, most of the recommendation agents that are based on MCCF cannot learn automatically from the features of the products to model customers’ preferences and generate accurate recommendations on retailing websites. Besides, although previous studies have utilized single and multi-criteria ratings in recommendation agents of tourism websites, still, if there is a lack of ratings of items, most of these systems will fail to generate accurate recommendations to users. In this research, we develop a new recommendation agent based on a MCCF approach to effectively improve the performance of previous recommendation systems for tourism websites. The results demonstrated that the method can predict the most relevant products to users, particularly when the dataset is sparse.

Hybrid cluster based classification model for high dimensional disease prediction databases

As biomedical databases continue to expand, it becomes increasingly difficult to identify a crucial feature for a classification task due to big data size and sparsity issues. Traditional feature subset models rely on fixed-sized dimensions for the feature ranking and classification process, which is not suitable for addressing concerns with sparsity, missing values, and imbalance in the selection of crucial features for the data classification process. To enhance disease prediction effectiveness, this article proposes a hybrid ensemble feature selection method that employs an advanced cluster-based classification model. The model uses an ensemble of rated features to classify the disease with high accuracy and true positive rate. To improve the effectiveness of tree pruning and classification, we introduce a novel cluster-based classification model. We simulated experimental results using various training datasets to predict accuracy. Our proposed results demonstrate that the gene-chemical disease clustering-based classification framework outperforms traditional methods, statistical metrics, and classification models in terms of optimization.

GR(1)-Guided Deep Reinforcement Learning for Multi-Task Motion Planning under a Stochastic Environment

Motion planning has been used in robotics research to make movement decisions under certain movement constraints. Deep Reinforcement Learning (DRL) approaches have been applied to the cases of motion planning with continuous state representations. However, current DRL approaches suffer from reward sparsity and overestimation issues. It is also challenging to train the agents to deal with complex task specifications under deep neural network approximations. This paper considers one of the fragments of Linear Temporal Logic (LTL), Generalized Reactivity of rank 1 (GR(1)), as a high-level reactive temporal logic to guide robots in learning efficient movement strategies under a stochastic environment. We first use the synthesized strategy of GR(1) to construct a potential-based reward machine, to which we save the experiences per state. We integrate GR(1) with DQN, double DQN and dueling double DQN. We also observe that the synthesized strategies of GR(1) could be in the form of directed cyclic graphs. We develop a topological-sort-based reward-shaping approach to calculate the potential values of the reward machine, based on which we use the dueling architecture on the double deep Q-network with the experiences to train the agents. Experiments on multi-task learning show that the proposed approach outperforms the state-of-art algorithms in learning rate and optimal rewards. In addition, compared with the value-iteration-based reward-shaping approaches, our topological-sort-based reward-shaping approach has a higher accumulated reward compared with the cases where the synthesized strategies are in the form of directed cyclic graphs.

Personalized Relationships-Based Knowledge Graph for Recommender Systems with Dual-View Items

The knowledge graph has received a lot of interest in the field of recommender systems as side information because it can address the sparsity and cold start issues associated with collaborative filtering-based recommender systems. However, when incorporating entities from a knowledge graph to represent semantic information, most current KG-based recommendation methods are unaware of the relationships between these users and items. As such, the learned semantic information representation of users and items cannot fully reflect the connectivity between users and items. In this paper, we present the PRKG-DI symmetry model, a Personalized Relationships-based Knowledge Graph for recommender systems with Dual-view Items that explores user-item relatedness by mining associated entities in the KG from user-oriented entity view and item-oriented entity view to augment item semantic information. Specifically, PRKG-DI utilizes a heterogeneous propagation strategy to gather information on higher-order user-item interactions and an attention mechanism to generate the weighted representation of entities. Moreover, PRKG-DI provides a score feature as a filter for individualized relationships to evaluate users’ potential interests. The empirical results demonstrate that our approach significantly outperforms several state-of-the-art baselines by 1.6%, 2.1%, and 0.8% on AUC, and 1.8%, 2.3%, and 0.8% on F1 when applied to three real-world scenarios for music, movie, and book recommendations, respectively.

Cross-Domain Explicit–Implicit-Mixed Collaborative Filtering Neural Network

Collaborative filtering (CF) is a classical model for recommender systems. Though neural network-based CF models have been shown to perform well in some cases, they still suffer from the sparsity and cold-start issues. To address these issues, we propose a novel neural network-based CF model, termed the cross-domain explicit–implicit-mixed CF neural network (CEICFNet). The proposed model utilizes deep neural networks to learn latent factors not only from the explicit ratings and the implicit interactions but also in a cross-domain manner. In particular, domain-shared multilayer perception (MLP) networks are designed to learn the user rating latent factors and the user interaction latent factors from the explicit ratings and the implicit interactions, respectively, which act as bridges for transferring knowledge across domains. On the other hand, domain-specific MLP networks are designed to learn the item rating latent factors and the item interaction latent factors from the explicit ratings and the implicit interactions, respectively. Then, in each domain, based on the user rating latent factors and the item rating latent factors, the rating predictive representation for each user–item pair can be learned by an MLP. Similarly, the interaction predictive representation for each user–item pair can be learned. For integrating the explicit ratings and the implicit interactions, in each domain, a fully connected layer is used to automatically assign different weights to the rating predictive representations and the interaction predictive representations, based on which the final interaction probability can be generated. Extensive experiments are conducted on five datasets and the results have confirmed the effectiveness of our model.

Deep Rating and Review Neural Network for Item Recommendation.

To alleviate the sparsity issue, many recommender systems have been proposed to consider the review text as the auxiliary information to improve the recommendation quality. Despite success, they only use the ratings as the ground truth for error backpropagation. However, the rating information can only indicate the users' overall preference for the items, while the review text contains rich information about the users' preferences and the attributes of the items. In real life, reviews with the same rating may have completely opposite semantic information. If only the ratings are used for error backpropagation, the latent factors of these reviews will tend to be consistent, resulting in the loss of a large amount of review information. In this article, we propose a novel deep model termed deep rating and review neural network (DRRNN) for recommendation. Specifically, compared with the existing models that adopt the review text as the auxiliary information, DRRNN additionally considers both the target rating and target review of the given user-item pair as ground truth for error backpropagation in the training stage. Therefore, we can keep more semantic information of the reviews while making rating predictions. Extensive experiments on four publicly available datasets demonstrate the effectiveness of the proposed DRRNN model in terms of rating prediction.