Search

A primary strategy for constructing click-through rate models based on deep learning involves combining a multi-layer perceptron (MLP) with custom networks that can effectively capture the interactions between different features. This is due to the widespread recognition that relying solely on a vanilla MLP network is not effective in acquiring knowledge about multiplicative feature interactions. These custom networks often employ product methods, such as inner, Hadamard, and outer products, to construct dedicated architectures for this purpose. Among these methods, the outer product has shown superiority in capturing feature interactions. However, the resulting quadratic form from the outer product operation limits the conveyance of informative higher-order interactions to the MLP. Efforts to address this limitation have led to models attempting to increase interaction degrees to higher orders. However, utilizing matrix factorization techniques to reduce learning parameters has resulted in information loss and decreased performance. Furthermore, previous studies have constrained the MLP's potential by providing it with inputs consisting of homogeneous outer products, thus limiting available information diversity. To overcome these challenges, we introduce DONN, a model that leverages a composite-wise bilinear module incorporating factorized bilinear pooling to mitigate information loss and facilitate higher-order interaction development. Additionally, DONN utilizes a feature-wise bilinear module for outer product computations between feature pairs, augmenting the MLP with combined information. By employing heterogeneous outer products, DONN enhances the MLP's prediction capabilities, enabling the recognition of additional nonlinear interdependencies. Our evaluation on two benchmark datasets demonstrates that DONN surpasses state-of-the-art models in terms of performance. [ABSTRACT FROM AUTHOR]

Recommendation systems are crucial in boosting companies' revenues by implementing various strategies to engage customers and encourage them to invest in products or services. Businesses constantly desire to enhance these systems through different approaches. One effective method involves using hybrid recommendation systems, known for their ability to create high-performance models. We introduce a hybrid recommendation system that leverages two types of recommendation systems: first, a novel deep learning-based recommendation system that utilizes users' and items' content data, and second, a traditional recommendation system that employs users' past behaviour data. We introduce a novel deep learning-based recommendation system called convolutional autoencoder recommendation system (CAERS). It uses a convolutional autoencoder (CAE) to capture high-order meaningful relationships between users' and items' content information and decode them to predict ratings. Subsequently, we design a traditional model-based collaborative filtering recommendation system (CF) that leverages users' past behaviour data, utilizing singular value decomposition (SVD). Finally, in the last step, we combine the two method's predictions with linear regression. We determine the optimal weight for each prediction generated by the collaborative filtering and the deep learning-based recommendation system. Our main objective is to introduce a hybrid model called CAERS-CF that leverages the strengths of the two mentioned approaches. For experimental purposes, we utilize two movie datasets to showcase the performance of CAERS-CF. Our model outperforms each constituent model individually and other state-of-the-art deep learning or hybrid models. Across both datasets, the hybrid CAERS-CF model demonstrates an average RMSE improvement of approximately 3.70% and an average MAE improvement of approximately 5.96% compared to the next best models. [ABSTRACT FROM AUTHOR]

Deep neural networks are vulnerable to attacks, posing significant security concerns across various applications, particularly in computer vision. Adversarial training has demonstrated effectiveness in improving the robustness of deep learning models by incorporating perturbations into the input space during training. Recently, adversarial training has been successfully applied to deep recommender systems. In these systems, user and item embeddings are perturbed through a minimax game, with constraints on perturbation directions, to enhance the model's robustness and generalization. However, they still fail to defend against iterative attacks, which have shown an over 60% increase in effectiveness in the computer vision domain. Deep recommender systems may therefore be more susceptible to iterative attacks, which might lead to generalization failures. In this paper, we adapt iterative examples for deep recommender systems. Specifically, we propose a Deep Recommender with Iteration Directional Adversarial Training (DRIDAT) that combines attention mechanism and directional adversarial training for recommendations. Firstly, we establish a consumer-product collaborative attention to convey consumers different preferences on their interested products and the distinct preferences of different consumers on the same product they like. Secondly, we train the DRIDAT objective function using adversarial learning to minimize the impact of iterative attack. In addition, the maximum direction attack could push the embedding vector of input attacks towards instances with distinct labels. We mitigate this problem by implementing suitable constraints on the direction of the attack. Finally, we perform a series of evaluations on two prominent datasets. The findings show that our methodology outperforms all other methods for all metrics. [ABSTRACT FROM AUTHOR]

Prohibited item detection is crucial for the safety of public places. Deep learning, one of the mainstream methods in prohibited item detection tasks, has shown superior performance far beyond traditional prohibited item detection methods. However, most neural network architectures in deep learning still lack sufficient local feature representation ability for overlapping and small targets, and ignore the problem of semantic conflicts caused by direct feature fusion. In this paper, we propose MFPIDet, a novel prohibited item detection neural network architecture based on improved YOLOV7 to achieve reliable prohibited item detection in complex environments. Specifically, a multi-scale attention module (MAM) backbone is proposed to filter the redundant information of target regions and further applied to enhance the local feature representation ability of overlapping objects. Here, to reduce the redundant information of target regions, a squeeze-excitation (SE) block is used to filter the background. Then, aiming at enhancing the feature expression ability of overlapping objects, a multi-scale feature extraction module (MFEM) is designed for local feature representation. In addition, to obtain richer context information, We design an adaptive fusion feature pyramid network (AF-FPN) to combine the adaptive context information fusion module (ACIFM) with the feature fusion module (FFM) to improve the neck structure of YOLOV7. The proposed method is validated on the PIDray dataset, and the tested results showed that our method obtained the highest mAP (68.7%), which is improved by 3.5% than YOLOV7 methods. Our approach provides a new design pattern for prohibited item detection in complex environments and shows the development potential of deep learning in related fields. [ABSTRACT FROM AUTHOR]

The Internet era is an era of information explosion. By 2022, the global Internet users have reached more than 4 billion, and the social media users have exceeded 3 billion. People face a lot of news content every day, and it is almost impossible to get interesting information by browsing all the news content. Under this background, personalized news recommendation technology has been widely used, but it still needs to be further optimized and improved. In order to better push the news content of interest to different readers, users' satisfaction with major news websites should be further improved. This study proposes a new recommendation algorithm based on deep learning and reinforcement learning. Firstly, the RL algorithm is introduced based on deep learning. Deep learning is excellent in processing large-scale data and complex pattern recognition, but it often faces the challenge of low sample efficiency when it comes to complex decision-making and sequential tasks. While reinforcement learning (RL) emphasizes learning optimization strategies through continuous trial and error through interactive learning with the environment. Compared with deep learning, RL is more suitable for scenes that need long-term decision-making and trial-and-error learning. By feeding back the reward signal of the action, the system can better adapt to the unknown environment and complex tasks, which makes up for the relative shortcomings of deep learning in these aspects. A scenario is applied to an action to solve the sequential decision problem in the news dissemination process. In order to enable the news recommendation system to consider the dynamic changes in users' interest in news content, the Deep Deterministic Policy Gradient algorithm is applied to the news recommendation scenario. Opposing learning complements and combines Deep Q-network with the strategic network. On the basis of fully summarizing and thinking, this paper puts forward the mode of intelligent news dissemination and push. The push process of news communication information based on edge computing technology is proposed. Finally, based on Area Under Curve a Q-Leaning Area Under Curve for RL models is proposed. This indicator can measure the strengths and weaknesses of RL models efficiently and facilitates comparing models and evaluating offline experiments. The results show that the DDPG algorithm improves the click-through rate by 2.586% compared with the conventional recommendation algorithm. It shows that the algorithm designed in this paper has more obvious advantages in accurate recommendation by users. This paper effectively improves the efficiency of news dissemination by optimizing the push mode of intelligent news dissemination. In addition, the paper also deeply studies the innovative application of intelligent edge technology in news communication, which brings new ideas and practices to promote the development of news communication methods. Optimizing the push mode of intelligent news dissemination not only improves the user experience, but also provides strong support for the application of intelligent edge technology in this field, which has important practical application prospects. [ABSTRACT FROM AUTHOR]

Recommendation (recommender) systems (RS) have played a significant role in both research and industry in recent years. In the area of academia, there is a need to help researchers discover the most appropriate and relevant scientific information through recommendations. Nevertheless, we argue that there is a major gap between academic state-of-the-art RS and real-world problems. In this paper, we present a novel multi-staged RS based on clustering, graph modeling and deep learning that manages to run on a full dataset (scientific digital library) in the magnitude of millions users and items (papers). We run several tests (experiments/evaluation) as a means to find the best approach regarding the tuning of our system; so, we present and compare three versions of our RS regarding recall and NDCG metrics. The results show that a multi-staged RS that utilizes a variety of techniques and algorithms is able to face real-world problems and large academic datasets. In this way, we suggest a way to close or minimize the gap between research and industry value RS. [ABSTRACT FROM AUTHOR]

Capturing dynamic preference features from user historical behavioral data is widely applied to improve the accuracy of recommendations in sequential recommendation tasks. However, existing deep neural network-based sequential recommendation methods often ignore the noise information in user behavioral data that influence recommendation effectiveness, making recommendation models sensitive to noisy data. Additionally, these deep learning-based recommendation models often require a large number of parameters to capture user behavior patterns, leading to higher time complexity and susceptibility to overfitting due to noise fluctuations. To address these issues, in this paper, we apply the moving average concept from the field of time-series analysis to sequential recommendation tasks. The approach smooths sequence data, removes noise, making the data more stable and reliable, increases the model's insensitivity to noise information, and better understands the evolution of user interests and behavioral patterns. Specifically, in our experiments, the moving average algorithm effectively denoises sequential data with low time complexity. Therefore, we propose a Sequential Recommendation with Exponential Moving Average with MLP architecture that makes the model more competitive in terms of time complexity. Experimental results conducted on two datasets demonstrate that EMARec outperforms state-of-the-art sequential recommendation methods across various common evaluation metrics. [ABSTRACT FROM AUTHOR]

Recommender systems are essential tools for many e-commerce services, such as Amazon, Netflix, etc. to recommend new items to users. Among various recommendation techniques, collaborative filtering has shown tremendous performance by using the rating patterns of users. Traditional collaborative filtering, matrix factorization, and deep matrix factorization are the most representative collaborative filtering techniques. However, despite their extensive utility, the selection of the method which provides better recommendation performance is still a major concern in multi-criteria recommender systems. Most recommender systems (RSs) work only on the single criterion rating, i.e., the overall rating. Single-criterion collaborative filtering (CF) generates less reliable recommendations because it suffers from correlation-based similarity problems. However, predictions based on multiple criteria have proven more accurate. This paper compares traditional collaborative filtering, matrix factorization and deep matrix factorization in recommender systems on multi-criteria datasets. We describe details of these techniques in various aspects of recommendation quality, such as how those methods handle cold-start problems, which typically happen in collaborative filtering. We performed several experiments extensively over two real-world datasets to evaluate the performance of each method in terms of qualitative and quantitative measures and observe that deep matrix factorization techniques is superior to all other techniques. [ABSTRACT FROM AUTHOR]

The prevalence of Recommender Systems (RS) has surged due to the widespread growth of the Internet and its related technologies. The efficiency of the RS is dependent on the quality of the underlying datasets used for training. Sparse datasets present a challenge for training such systems and negatively impacts their efficiency. This research paper presents novel synergistic approaches that combine Fuzzy C-Means (FCM), Restricted Boltzmann Machines (RBM), and Extreme Learning Machines (ELM), to enhance Collaborative Filtering (CF) in RS. The study introduces two clustering-based approaches, FCM-ELM and FCM-RBM-ELM, to address the issue of non-optimal hidden biases and input weights in ELM caused by random assignment in order to overcome the data sparsity effect in RS. The efficiency of proposed approaches against different clustering methods has been evaluated using two benchmark datasets and four metrics. The empirical results indicate that the proposed methods can generate better recommendation results compared to other traditional techniques. [ABSTRACT FROM AUTHOR]

Improving the accuracy of recommendation systems is a hot research topic, and existing methods have not considered the differences in various types of data. To address this issue, we propose a collaborative filtering recommendation method that combines evaluation relationships and emotional relationships. The emotional relationship is derived from implicit feedback data, and we can exploit the neural network to learn the emotional relationship between users and items. The evaluation relationship is derived from explicit feedback data; similarly, we can exploit the neural network to learn the evaluation relationship between users and items. To obtain emotional and evaluation relationships, we design vector representation and interaction functions based on explicit and implicit feedback data. Moreover, we propose that deep neural networks can be used to integrate evaluation and emotional relationships. To effectively integrate emotional and evaluation relationships, we design multiple data fusion strategies, loss functions, and training strategies. Experimental studies were conducted on five benchmark datasets, and the results show that the collaborative filtering recommendation method based on emotional evaluation relationships can further improve the accuracy of recommendation systems. [ABSTRACT FROM AUTHOR]

With the rise of online shopping due to the COVID-19 pandemic, Recommender Systems have become increasingly important in providing personalized product recommendations. Recommender Systems face the challenge of efficiently extracting relevant items from vast data. Numerous methods using deep learning approaches have been developed to classify fashion images. However, those models are based on a single model that may or may not be reliable. We proposed a deep ensemble classifier that takes the probabilities obtained from five pre-trained models such as MobileNet, DenseNet, Xception, and the two varieties of VGG. The probabilities obtained from the five pre-trained models are then passed as inputs to a deep ensemble classifier for the prediction of the given item. Several similarity measures have been studied in this work and the cosine similarity metric is used to recommend the products for a classified product given by a deep ensemble classifier. The proposed method is trained and validated using benchmark datasets such as Fashion product images dataset and Shoe dataset, demonstrating superior accuracy compared to existing models. The results highlight the potential of leveraging transfer learning and deep ensemble techniques to enhance fashion recommendation systems. The proposed model achieves 96% accuracy compared to the existing models. [ABSTRACT FROM AUTHOR]

In practice, the most important aspect has been to suggest items of interest to users based on their prior choices. In recent decades, recommendation systems have been highly successful in achieving this goal by using a variety of methods. Profile reliance is generally used as a critical element in traditional recommendation systems. Considering this impact is difficult to address, academics have been interested in analyzing user behavior in an ongoing session. Based on this insight, Researchers developed session-based recommendation to address this challenge of recommending products to users based on their ongoing interactions. Session-based Recommendation is a sequential method of determining user-item interactions that doesn't require access to the user's profile information or their entire history of preferences. Due to its capacity to analyze non-linear data, a novel gradient descent-based temporal convolution neural network is developed in this study to meet the session-based recommendation. Non-linear distortion, knowledge discovery, sequence mapping, and adaptability are the key benefits of adopting Deep Learning for recommendation systems. Utilizing the box-cox transformation paradigm, the primary data transformation stage is implemented to change the invalid data into valid information. Second, a novel gradient descent temporal convolution neural network (GDTCNN), created specifically for e-commerce applications, is proposed to carry out the session-based recommendations. When compared to the current methods, the suggested model has a better accuracy rating of 99.49, demonstrating its superiority. [ABSTRACT FROM AUTHOR]

With the massive amount of data available on the Internet, many users face problems when they need access to the information and goods they need. Adapting information to user needs has become a complex and time-consuming process. Recommender systems are powerful tools for guiding users in electronic settings to information, services, and goods of interest. With the ability to identify users and predict their preferences, recommender systems can extract information likely to be of interest to users from vast amounts of data and save time and energy by providing them with relevant recommendations. Therefore, in this paper, a framework for a recommender system is proposed, which consists of four main phases. In the first phase, the preprocessing operation is performed. The purpose of this phase is to create an ontology model for products based on the convolutional neural network method. Data collection operations are carried out in the second phase. The purpose of this phase is to receive and store user information based on behavior and different criteria. The third phase is related to creating an ontology. The purpose of this phase is to create an ontology model for user behavior using OWL libraries. Finally, in the last phase, finding similarities and presented a proposal. The purpose of this phase is the necessary calculations of the proposed framework in the similarity finding section using ontology models. Simulation results show that the proposed framework measures MAE (more than 10 and 15%), RMSE (more than 12 and 16%), precision (less than 10 and 13%), recall (more than 25 and 28%), F1-score (higher than 25 and 30%) and Score of User (higher than 15 and 17%) outperform two related approaches, namely CF and CF+ Ontology, respectively. [ABSTRACT FROM AUTHOR]

Knowledge Graphs (KGs) have already proven their strength as a source of high-quality information for different tasks such as data integration, search, text summarization, and personalization. Another prominent research field that has been benefiting from the adoption of KGs is that of Recommender Systems (RSs). Feeding a RS with data coming from a KG improves recommendation accuracy, diversity, and novelty, and paves the way to the creation of interpretable models that can be used for explanations. This possibility of combining a KG with a RS raises the question whether such an addition can be performed in a plug-and-play fashion – also with respect to the recommendation domain – or whether each combination needs a careful evaluation. To investigate such a question, we consider all possible combinations of (i) three recommendation tasks (books, music, movies); (ii) three recommendation models fed with data from a KG (and in particular, a semantics-aware deep learning model, that we discuss in detail), compared with three baseline models without KG addition; (iii) two main encyclopedic KGs freely available on the Web: DBpedia and Wikidata. Supported by an extensive experimental evaluation, we show the final results in terms of accuracy and diversity of the various combinations, highlighting that the injection of knowledge does not always pay off. Moreover, we show how the choice of the KG, and the form of data in it, affect the results, depending on the recommendation domain and the learning model. [ABSTRACT FROM AUTHOR]

Fairness has become a critical value online, and the latest studies consider it in many problems. In recommender systems, fairness is important since the visibility of items is controlled by systems. Previous fairness-aware recommender systems assume that sufficient relationship data between users and items are available. However, it is common that new users and items are frequently introduced, and they have no relationship data yet. In this paper, we study recommendation methods to enhance fairness in a cold-start state. Fairness is more significant when the preference of a user or the popularity of an item is unknown. We propose a meta-learning-based cold-start recommendation framework called FaRM to alleviate the unfairness of recommendations. The proposed framework consists of three steps. We first propose a fairness-aware meta-path generation method to eliminate bias in sensitive attributes. In addition, we construct fairness-aware user representations through the meta-path aggregation approach. Then, we propose a novel fairness objective function and introduce a joint learning method to minimize the trade-off between relevancy and fairness. In extensive experiments with various cold-start scenarios, it is shown that FaRM is significantly superior in fairness performance while preserving relevance accuracy over previous work. [ABSTRACT FROM AUTHOR]

In e-commerce, the session-based personalized recommendation remains challenging due to the limited user information within a single session. Merely relying on a user's local data is insufficient. It is vital to consider global data, extracting insights from sessions across all users to glean collaborative information. However, using all session information will waste computing resources. Moreover, much of the global data may not be pertinent to the current user, thereby undermining the quality of recommendations. To address this, we introduce the concept of personalized next session (PNS), selectively referencing sessions most relevant to the user to enhance the limited local data. This work is the first to adopt a deep network architecture study that incorporates the concept of PNS to recommend the next item for a user in the current session. We evaluated our approach on several real-world datasets, and the results show that our model outperforms state-of-the-art recommendation methods. [ABSTRACT FROM AUTHOR]

Social networks are widely used platforms for sharing various information and content, including text, images, and videos.The main challenge in social networking today is the verification of data credibility and the identification of genuine social media profiles. Cybercriminals take advantage of this by utilizing fake profiles to disseminate false information. However, current research mainly concentrates on spam filtering and analyzing malicious behavior separately, disregarding the interrelated nature of these issues. We propose a more desirable global, hybrid solution that encompasses both malicious profile detection and spam detection to mitigate the spread of spam effectively. This paper offers a deep learning-based method for detecting malicious profiles and spam tweets. For the profiles to interact with them as legitimate profiles, we first provide the detection of fake profiles using an automated honeypot. Next, we detect those who make interactions as malicious profiles, and finally, we collect their shared content to find spam tweets using a convolution neural network algorithm. We suggest using collaborative filtering and content filtering algorithms from recommender systems to define accounts similar to harmful profiles and spam similar to spam material picked up by convolution neural networks. We get a highly compelling and intriguing outcome with higher accuracy (99.23%) and lesser loss than typical learning algorithms. [ABSTRACT FROM AUTHOR]

In the present scenario, the product recommendation system is important to boost sales on many e-commerce websites. The majority of the existing product recommendation systems completely rely on the customer's website browsing history or historical transaction records to precisely predict the user's preferences for online product recommendations that are constrained by the limited information available on the e-commerce websites. Usually, processing the customer's feedback is a difficult procedure, where it is tough in interpreting and analyzing the text information. Therefore, an effective deep learning-based recommendation framework is implemented in this research manuscript. After acquiring text information from the amazon product reviews database, the data pre-processing is carried-out by using stemming, lemmatization, and stop word removal techniques. The undertaken pre-processing techniques remove both inconsistent and duplicate data that eases the process of data interpretation and use. Further, the computational time of the model is decreased by removing inconsistent and duplicate data from the original dataset. Then, the feature values are extracted from the pre-processed text data using the term frequency-inverse document frequency (TF-IDF) technique. The extracted feature values are fed to the enhanced convolutional-neural-networks (CNNs) for sentiment analysis. The enhanced CNN model uses Glove as a pre-trained model with a skip-gram in the word-embedding layer for identifying the relevant product ratings based on the user's experience to further enhance product sentiment analysis. The embedding layer in the enhanced CNN-model effectively converts every word into fixed feature vectors that helps in better word representation along with reduced dimensions. The enhanced CNN model obtained a mean recall of 94.80%, the precision of 93.64%, and accuracy of 96.92% on the amazon product reviews database and it is superior to the traditional CNN. [ABSTRACT FROM AUTHOR]

Low-light image enhancement based on deep learning has achieved breakthroughs recently. However, the current methods based on deep learning have problems with inadequate resolution enhancement or inadequate contrast. To address these problems, this paper proposes a resolution and contrast fusion network with ConvLSTM (RCFNC) for low-light image enhancement. The network is mainly constructed by four parts, including resolution enhancement branch, contrast enhancement branch, multi-scale feature fusion block (MFFB), and convolution long short-time memory block (ConvLSTM). Specifically, to improve the resolution of the low-light image, a resolution enhancement branch consisting of multi-scale differential feature blocks is proposed, using residual features at different scales to enhance the spatial details of image. To enhance the contrast of the image, a contrast enhancement branch consisting of adaptive convolution residual blocks is introduced to learn the mapping relationship between global and local features in the image. In addition, a weighted fusion is performed using MFFB to better balance the resolution and contrast features obtained from the above branches. Finally, to improve the learning capability of the model, ConvLSTM is added to filter redundant information. Experiments on the LOL, MIT5K, and five benchmark datasets show that RCFNC outperforms current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Currently, there is a significant amount of research being conducted in the field of artificial intelligence to improve the explainability and interpretability of deep learning models. It is found that if end-users understand the reason for the production of some output, it is easier to trust the system. Recommender systems are one example of systems that great efforts have been conducted to make their output more explainable. One method for producing a more explainable output is using counterfactual reasoning, which involves altering minimal features to generate a counterfactual item that results in changing the output of the system. This process allows the identification of input features that have a significant impact on the desired output, leading to effective explanations. In this paper, we present a method for generating counterfactual explanations for both tabular and textual features. We evaluated the performance of our proposed method on three real-world datasets and demonstrated a +5% improvement on finding effective features (based on model-based measures) compared to the baseline method. [ABSTRACT FROM AUTHOR]

Session-aware recommender systems capture user-specific preferences that emerge within multiple user sessions by leveraging the sequential nature of user interactions. Existing session-aware recommendation methods face challenges in finding the right balance between exploration and exploitation leading to less diverse recommendations and also suffering from overestimation bias. This bias problem refers to the tendency for value estimates to be higher than their true values resulting in slower convergence, suboptimal, and less diverse recommendations. This paper proposes a Double Deep Q-network based session-aware recommender system, DDQN-SaRS, which takes care of the overestimation bias and generates diverse recommendations capturing the user's dynamic interests. The proposed system works in two phases. The first phase generates embedding for users, items, and sessions using a Graph Convolutional Network (GCN). The obtained embedding vectors are then given to Double Deep Q-Network (DDQN), a Double Deep Reinforcement Learning (DDRL) technique for suggesting items of interest to the user(s) in the second phase. DDQN decouples the task of action selection and action evaluation by utilizing two networks viz. main and target networks and resolves the overestimation bias problem while maintaining diversity in recommendations. The proposed system learns recommendation policies and corresponding rewards from a pure offline setting. It is validated on two real-world datasets: Diginetica from the CIKM Cup Challenge 2016 and Retailrocket from the Kaggle competition. Experimental results show that our proposed system, DDQN-SaRS outperformed various baseline algorithms viz. S-POP, Item-KNN, GRU4Rec, STAMP, HRNN, NSAR,IDSR, and GNN-GNF. [ABSTRACT FROM AUTHOR]

Floor localization is crucial for various applications such as emergency response and rescue, indoor positioning, and recommender systems. The existing floor localization systems have many drawbacks, like low accuracy, poor scalability, and high computational costs. In this paper, we first frame the problem of floor localization as one of learning node embeddings to predict the floor label of a subgraph. Then, we introduce FloorLocator, a deep learning-based method for floor localization that integrates efficient spiking neural networks with powerful graph neural networks. This approach offers high accuracy, easy scalability to new buildings, and computational efficiency. Experimental results on using several public datasets demonstrate that FloorLocator outperforms state-of-the-art methods. Notably, in building B0, FloorLocator achieved recognition accuracy of 95.9%, exceeding state-of-the-art methods by at least 10%. In building B1, it reached an accuracy of 82.1%, surpassing the latest methods by at least 4%. These results indicate FloorLocator's superiority in multi-floor building environment localization. [ABSTRACT FROM AUTHOR]

Developing online educational platforms necessitates the incorporation of new intelligent procedures in order to improve long-term student experience. Presently, e-learning Recommender Systems rely on deep learning methods to recommend appropriate e-learning materials to the students based on their learner profiles. Fine-grained sentiment analysis (FSA) can be leveraged to enrich the recommender system. Users posted reviews and rating data are vital in accurately directing the student to the appropriate e-learning resources based on posted comments by comparable learners. Innovative has been made in this work to propose a new e-learning recommendation system based on individualization and FSA. A new framework is proposed based on collaborative filtering models (CFMs) integrating with fine-grained sentiment analysis (FSA) for hybrid recommendation (CFISAR) for effective recommendations. CFMs attempt to capture the learner's latent factors based on their selections of interest to build the learner profile. FSA models are introduced to deliver e-content with the highest ranked ratings related to the learner's area and interests based on the extracted learner model. Moreover, a new approach is proposed to update the system continuously and not keep it bound to certain items by adding new books, where the initial rating of these new books is predicted based on FSA models. CFISAR is explored utilizing six CFMs to generate the prediction matrix and derive the learner model, resulting in a low MSE of 0.699 for Asymmetric SVD. The system used multiplication word embeddings for stronger corpus representation that were trained on a dataset generated for an educational context, and leveraging the goodness of deep learning, which predicted an accuracy of 0.9264% for the Peephole algorithm, that performed better than other models. [ABSTRACT FROM AUTHOR]

Consumer perceptions of helpfulness remain an open question due to the lack of semantic and spatial features of review content. This paper aims to explore three aspects of the contents of a review: time, rating, and location, to assess the helpfulness of hotel reviews. A multi-view graph convolutional network (MVGCN) and attention mechanisms that capture multimodal semantic information are designed. The experimental results on Yelp and TripAdvisor are evaluated. The findings indicate that this facilitates the filtering of helpful information and avoids information overload when reading to customers. The results show that the proposed model outperforms the baseline and illustrates the interpretability of the models in each view. Our work is essential for professionals of both hotel and travel platforms that can utilize our findings to optimize their sales systems. Also, the results can help visitors or users acquire beneficial information and avoid information overload. This study is one of the few articles that can promote a model interpretable for information overload, which aims to guide research on evaluating the helpfulness of reviews in the hotel sector. This study contributes also to the methodology by developing extracting features of multimodal data, giving a multi-view feature with several novel assessments, and a novel framework involving deep learning. [ABSTRACT FROM AUTHOR]

Currently, generative applications are reshaping different fields, such as art, computer vision, speech processing, and natural language. The computer science personalization area is increasingly relevant since large companies such as Spotify, Netflix, TripAdvisor, Amazon, and Google use recommender systems. Then, it is rational to expect that generative learning will increasingly be used to improve current recommender systems. In this paper, a method is proposed to generate synthetic recommender system datasets that can be used to test the recommendation performance and accuracy of a company on different simulated scenarios, such as large increases in their dataset sizes, number of users, or number of items. Specifically, an improvement in the state-of-the-art method is proposed by applying the Wasserstein concept to the generative adversarial network for recommender systems (GANRS) seminal method to generate synthetic datasets. The results show that our proposed method reduces the mode collapse, increases the sizes of the synthetic datasets, improves their ratings distributions, and maintains the potential to choose the desired number of users, number of items, and starting size of the dataset. Both the baseline GANRS and the proposed Wasserstein-based WGANRS deep learning architectures generate fake profiles from dense, short, and continuous embeddings in the latent space instead of the sparse, large, and discrete raw samples that previous GAN models used as a source. To enable reproducibility, the Python and Keras codes are provided in open repositories along with the synthetic datasets generated to test the proposed architecture (https://github.com/jesusbobadilla/ganrs.git). [ABSTRACT FROM AUTHOR]

Tourists share opinions about Points of Interest (POIs) through online posts and social media platforms. Opinion mining is a popular technique for extracting feedback from tourists who visited various places hidden in reviews, which are used in several tourist applications that generally reflect their preference towards POI. On the other hand, a trip schema is difficult for tourists because they must pick up sequential POIs in unknown areas that meet their limitations and preferences. However, most prior trip suggestion methods are suboptimal for several reasons, including that they do not consider valuable user reviews and rely exclusively on left-to-right unidirectional discovery sequence models. This study proposes a Neural Network-Long Short-Term Memory (LSTM) POI recommendation system for calculating user similarity based on opinions and preferences. In addition, it presents a method for discovering sequential trip recommendations with Bidirectional Encoder Representations from Transformer (BERT) using a deep learning method. Furthermore, this neural hybrid framework identifies a list of optimal trip candidates by combining personalized POIs with multifaceted context. Furthermore, this method employs the valuable information contained in user posts and their demographic information on social media to mitigate the well-known cold start issue. In the experimental evaluation based on two datasets, Tripadvisor and Yelp, this hybrid method outperforms other state-of-the-art methods when considering F-Score, nDCG, RMSE, and MAP. [ABSTRACT FROM AUTHOR]

In recent years, the rapid advancement of artificial intelligence (AI) technology has made remarkable strides in the music industry, profoundly impacting various aspects of our lives. This progress has extended to revolutionizing industries, streamlining processes, and enhancing personalization in music. AI's expanding capabilities have driven computer vision, natural language processing, and machine learning breakthroughs. As music enthusiasts increasingly turn to online platforms, the need for effective recommendation systems has become more pressing. The exponential growth of musical content poses a challenge in discovering music tailored to individual tastes. This paper proposed a personalized music recommendation system powered by deep learning, explicitly utilizing convolutional neural networks (CNNs) to address the challenges posed by expanding music libraries and diverse song resources. In today's era of ever-growing music databases and increasing content diversity, more than traditional retrieval methods are needed to efficiently connect users with their preferred track. Traditional music platforms rely solely on retrieval mechanisms, necessitating manual inputs such as artist names and titles to locate specific songs. However, this approach needs in-depth music data analysis and delivers personalized recommendations generated by various deep learning-based algorithms. This paper bridges this gap by harnessing deep learning algorithms for comprehensive music data analysis and personalized song suggestions. The proposed CNN-based recommendation system explores the domains of deep learning and content-based approaches, empowering users to discover their favorite tunes swiftly. This innovative mechanism leverages CNNs and deep learning algorithms to offer efficient, personalized, and data-driven music recommendations, transforming the user experience with their music collections. In experimental results, the proposed CNN model is compared with various deep learning algorithms, including DNN, RNN, and LSTM, as well as traditional algorithms like SVM, KNN, RF, and DT. Impressively, the CNN model achieved the highest accuracy at 95%, surpassing all other algorithms. [ABSTRACT FROM AUTHOR]

The cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario is crucial. This research proposes a new hybrid recommender system named CoDFi-DL which combines demographic and enhanced collaborative filtering. The demographic filtering is performed through a deep neural network (DNN) and used to solve the new user cold start problem. The enhanced collaborative filtering component of our model focuses on delivering personalized recommendations through a neighborhood-based method. The major contribution in this research is the DNN-based demographic filtering which overcomes the new user cold start problem and enhances the collaborative filtering process. Our system significantly improves the relevancy of the recommendation task and thus provides personalized recommended items to cold users. To evaluate the effectiveness of our approach, we conducted experiments on real multi-label datasets, 1M and 100K MovieLens. CoDFi-DL recommender system showed higher performance in comparison with baseline methods, achieving lower RMSE rates of 0.5710 on the 1M MovieLens dataset and 0.6127 on the 100K MovieLens dataset. [ABSTRACT FROM AUTHOR]

Copy-move forgery detection poses a significant challenge because the brightness and contrast of forged and real regions are highly consistent, and the forensic clues are weakened by various affine transformations and post-processing operations. Existing deep learning models ignore the hierarchical dependencies of the features and pay less attention to information purification. To solve these problems, we propose a novel two-stage model to detect copy-move forgery, dubbed by CCAIR-Net. First, in the coarse localization stage, we propose a cross-scale condition aggregation module to integrate multi-level features from global to local. This aggregation structure can eliminate semantic disparities and capture multi-scale hierarchical dependencies of features. In particular, the condition aggregation block enables feature purification and filtering of interfering information. Second, in the refinement stage, the designed weighted fusion mechanism can guide the model to remove falsely detected regions and supplement the miss-detected regions by adaptively weighted fusion of coarse-grained and fine-grained features. Furthermore, the stage-wise training strategy takes advantage of different losses to train the network to detect tampered regions at various scales. Extensive experiments demonstrate that the proposed CCAIR-Net performs better than state-of-the-art methods. It can detect and segment forged and real areas more accurately, even for affine transformations and post-processing attack images. [ABSTRACT FROM AUTHOR]

Nowadays, the volume of online information is growing and it is difficult to find the required information. Effective strategies such as recommender systems are required to overcome information overload. Collaborative filtering is a widely used type of recommender system in e-commerce environments and can simply provide suggestions for users. Recently, deep learning approaches were applied in collaborative filtering to tackle some drawbacks. This systematic review aims to provide a comprehensive review of recent research efforts on deep learning-based collaborative filtering recommender systems. We explain the research methodology and paper selection process and the search query. 102 papers are selected out of 719 papers that were published between 2019 and May 2023. Furthermore, the approaches in the selected papers are classified into two main categories: memory-based and model-based techniques. The main ideas, advantages, disadvantages, used tools, type of neural network, applications, and evaluation parameters of each selected paper are also discussed in detail. It was found that CNN (Convolutional Neural Network), AE (Autoencoder), DNN (Deep neural network), and Hybrid networks are the four mostly used neural networks in recommender systems. Also, Python, MATLAB, and Java are the most frequently used tools in the reviewed papers. Regarding the applications of the recommender systems in the reviewed papers, movies, products, and music recommendation are three most frequent applications. We point out the open issues and future research directions. Some key challenges such as cold start, data sparsity, scalability, and accuracy are still open to be addressed. [ABSTRACT FROM AUTHOR]

Most e-commerce sites such as Amazon provide a comment function, and with the rapid growth of the number of comments, selecting and presenting useful comments helps users with decision-making. Recently, recommender systems using reviews instead of rating matrix enhance the recommendation quality by extracting the user preferences and item characteristics from the reviews. Some deep learning methods such as the attention mechanisms are used in these models to judge the review usefulness. However, these approaches rely on the historical data and do not perform well on the unseen reviews. In addition, the existing models ignore the sequential information embedded in the item reviews. In this work, we propose a deep learning model called review-based recommender with attentive properties (RRAP), which combines the review properties and sequential information to mitigate the problems in the traditional recommender systems. We perform experiments to compare the performance of the proposed recommender system with other recommender systems presented in the literature by using Amazon's four publicly available datasets. We use mean square error as an evaluation metric. The results show that the proposed RRAP reduces the prediction error and improves the interpretability of the model to a certain extent. [ABSTRACT FROM AUTHOR]

A recommendation system (RS) can help overcome information overload issues by offering personalized predictions for users. Typically, RS considers the overall ratings of users on items to generate recommendations for them. However, users may consider several aspects when evaluating items. Hence, a multi-criteria RS considers n-aspects of items to generate more accurate recommendations than a single-criteria RS. This research paper proposes two deep encoder–decoder models based on shared learning for a multi-criteria RS, multi-modal deep encoder–decoder-based shared learning (MMEDSL) and multi-criteria deep encoder–decoder-based shared learning (MCEDSL). MMEDSL employs the shared learning technique by concentrating on the multi-modality concept in deep learning, while MCEDSL focuses on the training process to apply the shared learning technique. The shared learning captures useful shared information during the learning process since the multi-criteria may have hidden inter-relationships. A set of experiments were conducted to compare the proposed models with recent baseline approaches. The Yahoo! Movies multi-criteria dataset was utilized. The results demonstrate that the proposed models outperform other algorithms. In addition, the results show that integrating the shared learning technique with the RS produces precise recommendation predictions. [ABSTRACT FROM AUTHOR]

During the past decades, several academic paper recommendation systems were introduced in literature aiming to assist users in finding relevant papers close to their needs. In particular, those models have used users' past preferences combined with papers' side information to personalize their recommendations. Unfortunately, the majority of those models fail to utilize the implicit relationship between the crucial elements along with the semantic relations of the nodes in a Heterogeneous Information Network (HIN), which can further improve the accuracy of the models. In this paper, we propose a research article recommendation model that aims to tackle those issues by exploiting both textual and graph representations, simultaneously. The model employs SPECTER document embedding to learn context-preserving research article representations. In particular, it learns the features from a HIN, which is a knowledge graph of the node entities and their relationships. Then, an attention module strengthens the semantic feature extraction process and learns enhanced representations. The combined semantic and structural features are then provided as input to a Deep Neural Network (DNN) in order to learn high-level representations of query and candidate papers. We have evaluated our model against state-of-the-art models over two popular datasets. The results indicate a significant improvement in terms of MAP, recall, and MRR. [ABSTRACT FROM AUTHOR]

Paper recommendation with personalized methods helps researchers to track the latest academic trends and master cutting-edge academic trends efficiently. Meanwhile, the methods of previous paper recommendation suffer from three problems: data sparsity of content-based and collaborative filtering methods; Graph-based recommendations do not fully consider the personalized information of authors and their articles; Cold start based on deep learning. To overcome those difficulties, we propose a personalized paper recommendation method based on a knowledge graph and Transformer encoder (KGTE) with a self-attention mechanism. Firstly, we add auxiliary information (article title, publication year, citation times, and abstract) as attributes to the nodes of knowledge graph(KG), which contain author, digital object unique identifier(DOI) and keywords. Secondly, BERT is used to represent the semantic information features of the article and Transformer is introduced to fully integrate the feature context. After that, by using RippleNet, we traverse the knowledge graph, filter the user preference distribution and form a set of pre recommended nodes with multi_hop nodes. Finally, the prediction layer sorts the set and gets a Top_n paper recommendation. In the experiments on the DBLP and Aminer datasets, the precision value of KGTE improved by an average of 2.59% over the existing baseline methods DER and 4.23% improvement in NDCG. [ABSTRACT FROM AUTHOR]

In the age of artificial intelligence (AI), trust in AI systems is becoming more important. Explainable recommenders, which explain why an item is recommended, have recently been proposed in the field of learning technology to improve transparency, persuasiveness, and trustworthiness. However, the methods for generating explanations are limited and do not consider the learner's cognitive perceptions or personality. This study draws inspiration from tailored intervention research in public health and investigates the effectiveness of personality-based tailored explanations by implementing them for the recommended quizzes in an explainable recommender system. High school students (n = 217) were clustered into three distinct profiles labeled Diligent (n = 77), Fearful (n = 72), and Agreeable (n = 68), based on the Big Five personality traits. The students were divided into a tailored intervention group (n = 106) and a control group (n = 111). In the tailored intervention group, personalized explanations for recommended quizzes were provided based on student profiles, with explanations based on quiz characteristics. In the control group, only non-personalized explanations based on quiz characteristics were provided. An 18-day A/B experiment showed that the tailored intervention group had significantly higher recommendation usage than the control group. These results suggest that personality-based tailored explanations with a recommender approach are effective for e-learning engagement and imply improved trustworthiness of AI learning systems. [ABSTRACT FROM AUTHOR]

Recommender systems using IoT and deep learning play a vital part in creating an engaging experience on online music streaming platforms. However, in the musical domain, it is quite challenging to build a recommender system as some of the tracks are short. Similarly, some are listened to several times or generally consumed in sessions with other tracks. The recommendation of the next track is highly context dependent. Traditional recommendation algorithms were not able to extract deep-level features from the audio signal and effectively mine user's preferred music. Therefore, this paper aims to propose a deep learning-based model to build a music recommendation algorithm. The algorithm first preprocesses the original data, and then generates the Mel spectrogram feature set through fast Fourier transform and Mel filter processing. After applying logarithmic operation, these spectrograms are then fed to the convolutional neural network algorithm to categorize music tracks. The inference results are used to understand the user's preferences and recommend their favorite music tracks. Experimental research and comparison on different data sets show that the algorithm has good performance in the recommendation effect. [ABSTRACT FROM AUTHOR]

With the explosive growth of music volume, music recommendation systems have become an important tool for online music platforms to alleviate the information overload problem. Through the use of deep learning, the multi-information fusion-based deep recommendation method has gained popularity in the field of music recommendation systems research. However, most existing studies only consider the different kinds of information of users or music and fail to capture information's internal and external associations. In this work, we propose a hierarchical multi-information fusion method for deep music recommendation (MMusic), to fully exploit the features of each type of information and to better learn the representation of users and music. Specifically, combined with the features of music recommendation, we identify various kinds of information describing users and music, respectively. Then, we learn about the interactions within and between different kinds of information for fusion. We conduct extensive experiments on the publicly available dataset NOWPLAYINGRS. The results show that MMusic achieves the best performance compared with the baselines, which verifies the effectiveness and rationality of our model. [ABSTRACT FROM AUTHOR]

Due to the rapid expansion of online platforms, review-based recommender systems have become the standard way to determine consumers' preferences for various goods. The purpose of this study is to address three significant issues with review-based approaches. First, these techniques suffer from a class-imbalance problem, where rating levels with lower proportions are partially neglected. As a result, their rating performance for such rare levels is unsatisfactory. To address this drawback, this paper proposes a flexible dual-optimizer network that enhances performance by utilizing classification and regression losses in the first attempt to solve this problem. Second, the typical review-based approach of preprocessing review texts with word embeddings will result in inadequate contextual information extraction. Thus, the bidirectional encoder representations from the transformers (BERT) method is introduced as the preprocessing technique to fully extract semantic information. Third, existing techniques make recommendations without considering that the user preferences may change over time. We suggest a time-varying feature extraction scheme that includes a multiscale convolutional neural network and bidirectional long short-term memory to solve this problem. We then develop an interactive component that summarizes the contextual information associated with the user-item pairings. The efficiency of the proposed time-varying attention with dual-optimizer (TADO) model is demonstrated through extensive tests on 12 benchmark datasets derived from Amazon Product Reviews. Regarding the existing state-of-the-art techniques, the proposed model attains a substantial performance increase of 22.69%, 8.75%, and 17.35%, respectively, over the Aspect-aware Latent Factor Model (ALFM), Multi-Pointer Co-Attention Networks for recommendation (MPCN), and Aspect-based Neural Recommender (ANR). Moreover, an ablation study demonstrates the importance of jointly employing the components developed for TADO. [ABSTRACT FROM AUTHOR]

The dress of a person can provide information like culture, status, gender, and personality. Dress classification can help us improve e-commerce, image-based search engines for the fashion industry, video surveillance, and social media image categorization. Deep learning is emerging as one of the most powerful classification techniques in many fields like medicine, business, and science. In the fashion industry, Convolutional Neural Networks have played a vital role in dress identification classification, but it is still a difficult task due to cluttered backgrounds, different poses, and lack of fashion datasets with rich classes and annotations. To complement the small-sized datasets, transfer learning is being widely used in training deep learning models. Current research applies transfer learning in two steps on the InceptionV3 model pre-trained on the ImageNet dataset. First, the pre-trained model is fine-tuned on DeepFashion dataset to transfer the domain of learned parameters toward fashion. In the second step, the model is fine-tuned on Pak Dataset a collection of Asian cultural fashion images having cluttered backgrounds. Experiments show the robustness and usefulness of two-step transfer learning in the classification of fashion images having cluttered backgrounds. Dress classification can be used for fashion image retrieval systems and recommendation systems. Dress classification can also be used in video surveillance systems for finding missing persons or crime suspects. [ABSTRACT FROM AUTHOR]

A scholarly recommendation system is an important tool for identifying prior and related resources such as literature, datasets, grants, and collaborators. A well-designed scholarly recommender significantly saves the time of researchers and can provide information that would not otherwise be considered. The usefulness of scholarly recommendations, especially literature recommendations, has been established by the widespread acceptance of web search engines such as CiteSeerX, Google Scholar, and Semantic Scholar. This article discusses different aspects and developments of scholarly recommendation systems. We searched the ACM Digital Library, DBLP, IEEE Explorer, and Scopus for publications in the domain of scholarly recommendations for literature, collaborators, reviewers, conferences and journals, datasets, and grant funding. In total, 225 publications were identified in these areas. We discuss methodologies used to develop scholarly recommender systems. Content-based filtering is the most commonly applied technique, whereas collaborative filtering is more popular among conference recommenders. The implementation of deep learning algorithms in scholarly recommendation systems is rare among the screened publications. We found fewer publications in the areas of the dataset and grant funding recommenders than in other areas. Furthermore, studies analyzing users' feedback to improve scholarly recommendation systems are rare for recommenders. This survey provides background knowledge regarding existing research on scholarly recommenders and aids in developing future recommendation systems in this domain. [ABSTRACT FROM AUTHOR]

Context-aware recommender systems are intended primarily to consider the circumstances under which a user encounters an item to provide better-personalized recommendations. Users acquire point-of-interest, movies, products, and various online resources as suggestions. Classical collaborative filtering algorithms are shown to be satisfactory in a variety of recommendation activities processes, but cannot often capture complicated interactions between item and user, along with sparsity and cold start constraints. Hence it becomes a surge to apply a deep learning-based recommender model owing to its dynamic modeling potential and sustained success in other fields of application. In this work, a trust-based attentive contextual denoising autoencoder (TACDA) for enhanced Top-N context-aware recommendation is proposed. Specifically, the TCADA model takes the sparse preference of the user that is integrated with trust data as input into the autoencoder to prevail over the cold start and sparsity obstacle and efficiently accumulates the context condition into the model via attention framework. Thereby, the attention technique is used to encode context features into a latent space of the user's trust data that is integrated with their preferences, which interconnects personalized context circumstances with the active user's choice to deliver recommendations suited to that active user. Experiments conducted on Epinions, Caio, and LibraryThing datasets make it obvious the efficiency of the TACDA model persistently outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recommendation problems are naturally tackled as a link prediction task in a bipartite graph between user and item nodes, labelled with rating information on edges. To provide personal recommendations and improve the performance of the recommender system, it is necessary to integrate side information along with user-item interactions. The integration of context is a key success factor in recommendation systems because it allows catering for user preferences and opinions, especially when this pertains to the circumstances surrounding the interaction between users and items. In this paper, we propose a context-aware Graph Convolutional Matrix Completion which captures structural information and integrates the user's opinion on items along with the surrounding context on edges and static features of user and item nodes. Our graph encoder produces user and item representations with respect to context, features and opinion. The decoder takes the aggregated embeddings to predict the user-item score considering the surrounding context. We have evaluated the performance of our model on 14 five publicly available datasets and compared it with state-of-the-art algorithms. Throughout this we show how it can effectively integrate user opinion along with surrounding context to produce a final node representation which is aware of the favourite circumstances of the particular node. [ABSTRACT FROM AUTHOR]

In this paper, we describe a review concerning the Quantum Computing (QC) and Deep Learning (DL) areas and their applications in Computational Intelligence (CI). Quantum algorithms (QAs), engage the rules of quantum mechanics to solve problems using quantum information, where the quantum information is concerning the state of a quantum system, which can be manipulated using quantum information algorithms and other processing techniques. Nowadays, many QAs have been proposed, whose general conclusion is that using the effects of quantum mechanics results in a significant speedup (exponential, polynomial, super polynomial) over the traditional algorithms. This implies that some complex problems currently intractable with traditional algorithms can be solved with QA. On the other hand, DL algorithms offer what is known as machine learning techniques. DL is concerned with teaching a computer to filter inputs through layers to learn how to predict and classify information. Observations can be in the form of plain text, images, or sound. The inspiration for deep learning is the way that the human brain filters information. Therefore, in this research, we analyzed these two areas to observe the most relevant works and applications developed by the researchers in the world. [ABSTRACT FROM AUTHOR]

Link prediction on knowledge graphs has become increasingly important in various fields, including recommender systems, question answering, and social networks. To address this challenge, ConvKB, a state-of-the-art model in deep learning approaches, has been proposed. However, ConvKB is limited in its ability to exploit general information about relations because it uses the same filters for all relations. Additionally, ConvKB's design, consisting of a convolution layer and a linear layer, may not provide enough parameters to store necessary information during feature learning. To address these limitations, this paper proposes the ConvHyper model, which combines the ConvKB model with a HyperNetwork architecture to create relation-specific weights for convolutional neural network layers. Specifically, the embedding of relations is linearly combined through a HyperNetwork to generate weights for the base neural network. This HyperNetwork architecture helps reduce the complexity of the search space to identify optimal weights and create a relation-specific weight structure for neural network layers. Experimental results show that ConvHyper significantly improves on all metrics in four well-known datasets. ConvHyper improves on H@1 up to 5.5% and achieves better results on other metrics, ranging from 0.8% to 1%. We also compared ConvHyper with other CNN-based models and found that many metrics have better values, particularly from 1.1% to 4.7% on the H@10 metric. Furthermore, we analyzed the influence of hyperparameters and found that the learning rate and negative samples significantly affect the model's results. [ABSTRACT FROM AUTHOR]

Latent factor-based methods have been extensively employed in recommender systems to project users and items to the same feature space and use the dot product for predicting unknown ratings. Nevertheless, the dot product method cannot describe the various influences of latent features. Also, it only captures the linear relations between users and items leading to a negative impact on the efficiency of recommender systems. Deep learning models are known as state-of-the-art techniques to deal with the non-linear relation between user and item. In this paper, we develop a new deep hybrid recommender system called DHSIRS using multilayer perceptron neural network to combine side information and interaction matrix for item recommendation. Specifically, two feature learning components are developed to extract side information-based and interaction-based latent features. Therefore, two paralleled deep neural networks are utilized in the side information-based feature learning part to obtain the feature vector for users and items from side information. Moreover, the interaction-based feature learning part obtains the latent features from the user-item matrix. Finally, we introduce a deep learning model instead of the dot product method to predict unknown ratings by integrating the side information-based and interaction-based latent features. Unlike other methods that use the dot product, our method is able to efficiently learn the high-order non-linear relations between users and items. Extensive experiments on three publicly available datasets demonstrate that DHSIRS averagely improves the recommendation performance by around 4.18% in comparison to the second-best model over different evaluation metrics. [ABSTRACT FROM AUTHOR]

Reciprocal Recommender Systems (RRS) aim to recommend relevant matches to users based on the mutual agreement of their preferences. Explainability of reciprocal recommendations is important for developing a persuasive reciprocal recommender system, since it can improve the effectiveness and credibility of the reciprocal recommendation results. Explainable RRS provide an explanation highlighting why a recommendation would be relevant to the user. Explaining the rationale behind predictions with textual or visual artifacts help in increasing trustworthiness and transparency of the system which is crucial especially for models that are used in critical decision making. In this work, XSiameseBiGRU-UCB, a deep learning contextual bandits framework with post-hoc argumentation based explanations for RRS is proposed. XSiameseBiGRU-UCB is an explainable Siamese neural network-based framework that provides explanations to justify the generated reciprocal recommendations for both the parties involved. In RRS, dilemma between exploitation and exploration requires identifying the best possible recommendation from known information or collecting more information about the environment while generating reciprocal recommendations. To tackle this, we propose to use a contextual bandit policy with upper confidence bound, which adaptively exploits and explores user interests to achieve increased rewards in the long run. Experimental studies conducted with four real-world datasets validate the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

Recommender systems play a vital role in discovering contents of interest to users in this information explosion era. However, traditional recommender systems only consider user immediate feedback and tend to recommend similar items according to users' historical interactions. Moreover, in real-world online applications, they lack sufficient user interaction data. In this paper, we propose a novel interactive recommender system by using deep reinforcement learning, which can take both user immediate rewards and future rewards into account. In order to tackle the effect of interaction data insufficiency on recommendation performance, we leverage the knowledge and relation information among items in external knowledge graphs to enrich the item embedding. We concatenate the user representation and user top-l latest historical interactions as the state and feed into the Bi-LSTM model to capture user dynamic preferences. Extensive experiments on two real-world data sets demonstrate the effectiveness and generality of our proposed recommender system. [ABSTRACT FROM AUTHOR]

Adventure tourism is a popular and growing segment within the tourism industry that involves, but is not limited to, hiking, running, and climbing activities. These activities attract investment from foreign travelers interested in practicing sports while exploring other countries. As a result, many software companies started developing Artificial Intelligence solutions to enhance tourists' outdoor adventure experience. One of the leading technologies in this field is recommender systems, which provide personalized recommendations to tourists based on their preferences. While this topic is actively being researched in some sports (running and hiking), other adventure sports disciplines have yet to be fully explored. To standardize the development of intelligence-based recommender systems, we conducted a systematic literature review on more than a thousand scientific papers published in decision support system applications in three outdoor adventure sports, such as running, hiking, and sport climbing. Hence, the main focus of this work is, firstly, to summarize the state-of-the-art methods and techniques being researched and developed by scientists in recommender systems in adventure tourism, secondly, to provide a unified methodology for software solutions designed in this domain, and thirdly, to give further insights into open possibilities in this topic. This literature survey serves as a unified framework for the future development of technologies in adventure tourism. Moreover, this paper seeks to guide the development of more effective and personalized recommendation systems. [ABSTRACT FROM AUTHOR]