Search

Now a day’s recommendation system take care of the issue of the massive amount of information overload problem and it provides the services to the candidates to concentrate on relevant information on job domain only. The job recommender system plays an important role in the recruitment process of fresher as well as experienced today. Existing job recommender system mainly focuses on content-based filtering to extricate profile content and on collaborative filtering to capture the behaviour of the user in the form of rating. Dynamic nature of job market leads cold start and scalability issues. This problem can be addressed by item-based collaborative filtering with a machine learning technique, it learns job embedding vector and finds similar jobs content-wise. Existing model in job recommender domain uses the confining model to address the cold start and scalability issue and provide better recommendation, but they fail to accept the complex relationships between job description and candidate profile. In this paper, we are proposing a Deep Semantic Structure Algorithm that overcome the issue of the existing system. Deep semantic structure modelling (DSSM) system uses the semantic representation of sparse data and it represent the job description and skill entities in character trigram format which increases the efficacy of the system. We are comparing the results to three variation of DSSM model with two different dataset (Naukari.com and CareerBuilder. com) and it gives satisfactory results. Experimental results shows that the DSSM Embedding model and its other variants are provides promising results in solving cold start problem in comparison with several variants of embedding model. We used Xavier initializer to initialise the model parameter and Adam optimizer to optimize the system performance.

Recommender system (RS) suggests relevant objects to generate personalized service and minimize information overload issue. User-based collaborative filtering (UBCF) plays a dominant role in practical RSs. However, traditional UBCF suffers from a recommendation overfitting problem, i.e., recommendations generated by UBCF usually concentrate on popular items, resulting in lower diversity. In addition, UBCF cannot maintain a reasonable tradeoff between the accuracy and diversity of recommendations because raising the diversity is often accompanied by a decrease in accuracy. In this article, we propose a novel approach, namely link-based collaborative filtering, to enhance the recommendation accuracy and diversity simultaneously without employing additional complex information. First, a user-item bipartite network is constructed based on the user-item rating matrix of RSs. Then, a global-local weighted bipartite modularity is presented to conduct link partition so that links with the same community can not only be relatively denser but also own the same characteristic. Furthermore, redundant links are removed from each community by utilizing a link reduction algorithm so that neighborhood of a target user can be selected according to the more efficient nonredundant links. Finally, rating prediction is executed based on the rating information of neighborhood. Also, items owning the highest predicted rating scores will be recommended to the target user. Experimental results from three real datasets of RSs suggest that, without taking advantage of special additional data, our proposed approach outperforms the state-of-the-art studies and is able to generate personalized recommendations with satisfying accuracy and diversity simultaneously.

News recommendation plays an important role in alleviating information overload and helping users find their interesting news. Most of the existing news recommendation methods make a recommendation based on static data. They ignore the time dynamic characteristics of the interaction between users and news, that is, the order in which users click on news implicitly indicates the user’s interest in news. In this paper, we propose a time sensitive heterogeneous graph neural network for news recommendation. The network consists of two subnetworks. One subnet utilizes convolutional neural network and improved LSTM to learn a user’s stay period on the page and click sequence characteristics as the temporal dimension feature. The other subnet constructs an attention-based heterogeneous graph to model the user-news-topic associations, and apply graph neural network to learn the structural features of the heterogeneous graph as spatial dimensional features. Experiments conducted show that our model outperforms the state-of-the-art models in accuracy and has better interpretability.

Information overload in recent years has tremendously sparked recommender systems (RSs). An RSs usually recommends valuable information for users based on historical experience high-dimensional and incomplete (HDI) data. Since each user cannot mark whole items, extracting latent factors (LF) learned by the stochastic gradient descent (SGD) optimization method is frequently used. However, interference from the adjustment of parameters induces an inferior convergence rate and low efficiency. To address this issue, the paper proposes a b rain storm optimization (BSO)-based a daptative l atent f actor a nalysis (BALFA) model consisting of the following three essential ideas: 1) divergent mechanism to avoid premature convergence, 2) particle retention technique to prevent invalid search, and 3) self-adaptive multidimensional leaning rate for more efficient application on varying data. Moreover, the convergence of the modified BSO used in BALFA is proofed based on the Markov chain . Comparison experiments on six HDI datasets in the SGD-based LF model indicate that the BALFA achieves state-of-art convergence rate and computational efficiency for HDI data analysis.

By enabling information networking among people and machines, the Internet has become one of the major foundations for our socio-economic systems. After several decades of research and development of the Internet, it is relatively easy for humans/machines to obtain information. However, there are new challenges in the post-Internet era, including information overload, fake information and the design of trustworthy, cost-effective autonomous systems. In order to address these challenges, we need to think about networking in a larger timescale. Actually, in order to facilitate humans' cooperation, we have invented technologies enabling networking for matter (grid of transportation), for energy (grid of energy), and for information (the Internet). In this article, we argue that the next networking paradigm could be intelligence networking, where intelligence can be easily obtained, like matter, energy, and information. Specifically, we present the motivations, scenarios and challenges of intelligence networking. In addition, we present a novel collective reinforcement learning scheme enabled by intelligence networking. Some simulation results are presented to show the effectiveness of the proposed intelligence networking paradigm.

The rapid development of the tourism industry and the Internet era has led to an increasingly severe problem of travel information overload, and travel recommendation methods are essential to solving the information overload problem. Traditional recommendation algorithms only target common travel scenarios during the daytime, combining the ratings and necessary attributes between users and items to calculate similarity for a recommendation. Still, the research on night travel recommendations is one of the few scenarios that needs to be explored urgently. This paper, based on histogram equalization, achieves better experimental results on image enhancement, combines convolutional neural network technology with night image and text comment feature extraction technology, and evaluates the resulting error with mean absolute error (MAE). This paper presents the first night travel recommendation system. It compares it with the traditional collaborative filtering method, and the model proposed in this paper can effectively reduce the prediction error.

In the era of big data, information overload problems are becoming increasingly prominent. It is challengingfor machines to understand, compress and filter massive text information through the use of artificial intelligencetechnology. The emergence of automatic text summarization mainly aims at solving the problem ofinformation overload, and it can be divided into two types: extractive and abstractive. The former finds somekey sentences or phrases from the original text and combines them into a summarization; the latter needs acomputer to understand the content of the original text and then uses the readable language for the human tosummarize the key information of the original text. This paper presents a two-stage optimization method forautomatic text summarization that combines abstractive summarization and extractive summarization. First,a sequence-to-sequence model with the attention mechanism is trained as a baseline model to generate initialsummarization. Second, it is updated and optimized directly on the ROUGE metric by using deep reinforcementlearning (DRL). Experimental results show that compared with the baseline model, Rouge-1, Rouge-2,and Rouge-L have been increased on the LCSTS dataset and CNN/DailyMail dataset.

The recommendation systems in the online platforms often suffer from the rating data sparseness and information overload issues. Previous studies on this topic often leverage review information to construct an accurate user/item latent factor. To address this issue, we propose a novel confidence-aware recommender model via review representation learning and historical rating behavior in this article. It is motived that ratings are consistent with reviews in terms of user preferences, and reviews often contain misleading comments (e.g., fake good reviews, fake bad reviews). To this end, the interaction latent factor of user and item in the framework is constructed by exploiting review information interactivity. Then, the confidence matrix, which measures the relationship between the rating outliers and misleading reviews, is employed to further improve the model accuracy and reduce the impact of misleading reviews on the model. Furthermore, the loss function is constructed by maximum a posteriori estimation theory. Finally, the mini-batch gradient descent algorithm is introduced to optimize the loss function. Experiments conducted on four real-world datasets empirically demonstrate that our proposed method outperforms the state-of-the-art methods. The proposed method also further promotes the application in learning resource adaptation. The source Python code will be available upon request.

A high-quality recommender system (RS) can effectively alleviate information overload by producing recommendations. The quality of the recommender system not only depends on the recommendation algorithm but also on the quality of collected data. Since users are often affected by environmental and accidental factors during the rating process, natural noise is probably brought into the data of RS by non-malicious users, which will lead to deviations in prediction results. In this paper, we propose a scheme based on fuzzy theory to manage the natural noise in RS. We first classify the ratings into three fuzzy categories with variable boundaries. Then, the fuzzy profiles of users and items are built to detect the natural noise in ratings. Finally, once the noisy ratings are detected, we replace them with the rating threshold values according to the Maximum membership principle. The proposed scheme is tested in two benchmark datasets and experimental results verify that the scheme can significantly improve the recommendation quality and has higher efficiency than the schemes based on re-predication.

As a method of information filtering, the Recommender System (RS) has gained considerable popularity because of its efficiency and provision of the most superior numbers of useful items. A recommender system is a proposed solution to the information overload problem in social media and algorithms. Collaborative Filtering (CF) is a practical approach to the recommendation; however, it is characterized by cold start and data sparsity, the most severe barriers against providing accurate recommendations. Rating matrices are finely represented by Nonnegative Matrix Factorization (NMF) models, fundamental models in CF-based RSs. However, most NMF methods do not provide reasonable accuracy due to the dispersion of the rating matrix. As a result of the sparsity of data and problems concerning the cold start, information on the trust network among users is further utilized to elevate RS performance. Therefore, this study suggests a novel trust-based matrix factorization technique referred to as CFMT, which uses the social network data in the recommendation process by modeling user’s roles as trustees and trusters, given the trust network’s structural information. The proposed method seeks to lower the sparsity of the data and the cold start problem by integrating information sources including ratings and trust statements into the recommendation model, an attempt by which significant superiority over state-of-the-art approaches is demonstrated an empirical examination of real-world datasets.

In recent years, online learning has become more and more popular. However, because of information overload, learners often find it difficult to retrieve suitable learning resources. Although many scholars have proposed excellent online learning resource recommendation algorithms, the accuracy of personalized recommendation results still needs to be improved. This study proposes an improved hybrid ontology-based approach for online learning resource recommendations, combining collaborative filtering algorithm and sequential pattern mining (SPM) techniques. Ontology can be used effectively for knowledge representation to avoid cold start and data sparsity problems. And the history of learners’ sequential access patterns helps in providing recommendations that are more consistent with the law of learning activities. Experimental results reveal that our improved hybrid approach for learning resource recommendations yields better performance and recommendation quality than other related algorithms. Compared with previous research outcomes, our collaborative filtering engine, with ontology domain knowledge, makes full use of the historical learning paths of similar learners. The ontology construction in this study has a more reliable theoretical basis and the selection of features is more representative. In addition, improvement of the SPM process further improves the efficiency of our recommended algorithm.

Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future., Comment: 35 pages, 5 figures

Web services are products in the era of service-oriented computing and cloud computing. Considering the information overload problem arising from the task of selecting web services, a recommendation system is by far the most effective solution for performing such selections. However, users calling a limited number of services will cause severe data sparseness and a weak correlation with services. In addition, fully mining the semantic features and knowledge features of the text description is also a major problem that needs to be solved urgently. This paper proposes a deep knowledge-aware approach which introduces knowledge graph and knowledge representation into web service recommendation for the first time. We solve the data sparse problem and optimize the user’s feature representation. In this approach, an attention module is introduced to model the impact of tags for the candidate services on different words of user queries, and a deep neural network is used to model the high-level features of user-service invocation behaviors. The results of experiments demonstrate that the proposed approach can achieve better recommendation performance than other state-of-the-art methods.

Information overload is a major problem for many internet users which occurs due to overwhelming amounts of data made available to a user. In order to deal with this problem filtering tool, like Recommender System is required for providing relevant information for the users which personalizes the search according to user preferences. The Collaborative Filtering Recommender System finds the nearest neighbour set of active user by using similarity measures on the rating matrix. This paper proposes different variations of K-nearest neighbors (KNN) algorithm with different similarity measures namely cosine, msd, pearson and pearson baseline for Movie Recommender System. These different variations of KNN algorithms have been implemented for real data from MovieLens dataset and compared on accuracy metrics like fraction of concordant Pairs, mean absolute error, mean squared error, root mean squared error, precision@k and recall@k for Movie Recommender System. For real life application, Movie Recommender System filtering tool may be used as plugin by customizing the web browser.

In recent years, Educational Recommender Systems (ERSs) have attracted great attention as a solution towards addressing the problem of information overload in e-learning environments and providing relevant recommendations to online learners. These systems play a key role in helping learners to find educational resources relevant and pertinent to their profiles and context. So, it is necessary to identify information that helps learner’s profile definition and in identifying requests and interests. In this context, we suggest to take advantage of the annotation activity used usually in the learning context for different purposes and which may reflect certain learner’s characteristics useful as input data for the recommendation process. Therefore, we propose an educational recommender system of web services based on learner’s annotative activity to assist him in his learning activity. This process of recommendation is founded on two preparatory phases: the phase of modelling learner’s personality profile through analysis of annotation digital traces in learning environment realized through a profile constructor module and the phase of discovery of web services which can meet the goals of annotations made by learner via the web service discovery module. The evaluation of the developed annotation based recommendation system through empirical studies realized on groups of learners based on the Student’s t-test showed significant results.

The Follower Link Prediction is an emerging application preferred by social networking sites to increase their user network. It helps in finding potential unseen individual and can be used for identifying relationship between nodes in social network. With the rapid growth of many users in social media, which users to follow leads to information overload problems. Previous works on link prediction problem are generally based on local and global features of a graph and limited to a smaller dataset. The number of users in social media is increasing in an extraordinary rate. Generating features for supervised learning from a large user network is challenging. In this paper, a supervised learning model (LPXGB) using XGBoost is proposed to consider the link prediction problem as a binary classification problem. Many hybrid graph feature techniques are used to represent the dataset suitable for machine learning. The efficiency of the LPXGB model is tested with three real world datasets Karate, Polblogs and Facebook. The proposed model is compared with various machine learning classifiers and also with traditional link prediction models. Experimental results are evident that the proposed model achieves higher classification accuracy and AUC value.

Falls are widespread among older adults causing serious injuries and threatening their quality of life. An approach to estimate fall risk, and to prevent falls, is the Timed-Up-and-Go (TUG) test. The TUG test has established validity and reliability. However, as a clinical test, it is not accessible for personal use. To enhance its reach, the authors developed a prototype called Fall Risk Evaluation and Feedback System (FREFS). The prototype is a Kinect-based depth sensor system with interfaces that support older adults in completing the TUG test and receiving personalized test results. The personalized feedback feature is novel that existing prototypes do not include. This study's goal was to gain knowledge of the user experience of FREFS. This research applied methods of observation, interviews, and collected responses on the System Usability Scale (SUS). Results show participants perceived the system as usable, with SUS score of 84.3, but also revealed issues. First, users were unsure how to deal with the TUG tests results when the results showed high fall risk. Second, clearer instructions and reduction of information overload specifically for these age groups were needed. Third, a communication approach embedded into the system would be required (i.e., a link to a chatbot feature or a button to connect to a real person). Overall, the study demonstrated that such a prototype cannot be fully automated; it needs a sociotechnical system solution that includes human communication.

The growth of e-commerce has resulted in massive product information and huge volumes of data. This results in data overload problems. In the case of e-commerce, consumers or users spend a lot of time choosing the goods they need. The urgent question to be answered at this time is how to provide solutions related to intelligent information restrictions so that the existing information is truly information that is by preferences and needs. This research performs information filtering by applying the singular value decomposition method and the Pearson similarity technique to the book recommendation system. The data used is the Book-Crossing Dataset which is the reference dataset for many research recommendation systems. The resulting recommendations are then compared with e-commerce recommendations such as amazom.com. Based on the results of the study obtained data that the results of the recommendations in this study are very good and accurate.

With the fast-developing domain of cyber-physical systems (CPS), constructing the CPS with high-quality services becomes an imperative task. As one of the effective solutions for information overload in CPS construction, quality of service (QoS)-aware service recommendation has drawn much attention in academia and industry. However, the lack of most QoS values limits the recommendation performance and it is time-consuming for users to get the QoS values by invoking all the services. Therefore, a powerful prediction model is required to predict the unobserved QoS values. Considering the fact that most existing QoS prediction models are unable to effectively address the data-sparsity problem, a novel two-stage framework called AgQ is proposed for QoS prediction. Specifically, a data augmentation strategy is designed in the first stage to enlarge the training set by drawing additional virtual instances. In the second stage, a prediction model is applied that considers both virtual and factual instances during the training procedure. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the our QoS prediction framework and verify that the data augmentation strategy can indeed alleviate the data-sparsity problem. In terms of mean absolute error, taking the Multilayer Perceptron model as an example, the maximum improvement achieves 5% under 5% sparsity.

Automatic text summarization is considered as an important task in various fields in natural language processing such as information retrieval. It is a process of automatically generating a text representation. Text summarization can be a solution to the problem of information overload. Hence, with the large amount of information available on the Internet, the presentation of a document by a summary helps to get the most relevant result of a search. We propose in this paper a new free Arabic structured corpus in the standard XML TREC format. ANT corpus v2.1 is collected using RSS feeds from different news sources. This corpus is useful for multiple text mining purposes such as generic text summarization, clustering or classification. We test this corpus for an unsupervised single-document extractive summarization using statistical and graph-based language-independent summarizers such as LexRank, TextRank, Luhn and LSA. We investigate the sensitivity of the summarization process to the stemming and stop words removal steps. We evaluate these summarizers performance by comparing the extracted texts fragments to the abstracts existing in ANT corpus v2.1 using ROUGE and BLEU metrics. Experimental results show that LexRank summarizer has achieved the best scores for the ROUGE metric using the stop words removal scenario.

Recommender system (RS) are a type of suggestion to the information overload problem suffered by user of websites that allow the rating of particular item. The movie RS are one of the most efficient, useful, and widespread applications for individual to watch movie with minimum decision time. Many attempts made by the researchers to solve these issues like watching movie, purchasing book etc., through RS, whereas most of the study fails to address cold start problem, data sparsity and malicious attacks. This study address these problems, we propose trust matrix measure in this paper, which combines user similarity with weighted trust propagation. Non cold user passed through different models with trust filter and a cold user generated an optimal score with their preferences for recommendation. Four different recommendation models such as Backpropagation (BPNN) model, SVD (Singular Value Decomposition) model, DNN (Deep Neural Network model) and DNN with Trust were compared to recommend the suitable movie to the user. Results imply that DNN with trust model proved to be the best model with high accuracy of 83% with 0.74 MSE value and can be used for best movie recommendation.

Recommendation system has drawn growing attention in the academia and industry because it can solve the problem of information overload. Among a variety of methods, the click-through rate prediction model plays an important role in predicting user’s attention to a specific item. To predict click-through rate, high-dimensional and sparse features are usually adopted, and the accuracy of the prediction result depends on the combination of high-order features to a great extent. Therefore, many methods have been proposed to find the low-dimensional representation from sparse high-dimensional original features, and the meaningful way of feature combination has also been mined to improve the accuracy of the model. However, the click-through rate prediction models generally have two problems. One is that they can’t extract the feature interaction of non-Euclidean features very well. Another one is that it is hard to explain the inward meaning of feature interaction. In this paper, a GCN-int model based on the interaction of Graph Convolutional Network is proposed to solve the above problems. The proposed model simplifies the complex interaction among multiple features, gets a better representation of the interaction between high-order features, and improves the interpretability of feature interaction. The experimental results on the public movie recommendation dataset and our own IPTV movie recommendation dataset show that the proposed GCN-int model gets higher accuracy and efficiency compared with the state-of-the-art models.

Today, lots of personalization can be done in applications or even websites. It is possible to change the look and feel, to group often used functionalities or to filter relevant information. To get the same behavior for security monitoring in large scaled enterprise companies, one aspect of the research project IUNO-iSOC is to develop a dashboard system where every user can create his own custom overview of all needed information. A second part IUNO-iSOC aims to handle the information overload a security analyst is faced by analyzing alerts of different types of security management systems. This paper adresses the mentioned problem and describes the way from collecting security data from different sources to the concept of supporting the users creating their own view to the data currently needed as well as dealing with lots of incoming security alerts.

Concerning the information overload of online reviews, this paper models a new review selection problem called the Informative Review Subset Selection problem (namely, IRSS) and demonstrates that it is NP-hard to solve and approximate. Furthermore, a novel heuristic method (namely, Combined Search-ComS) is proposed for seeking the solution to the problem and selecting a subset of reviews, which is consistent with the original review corpus in light of mutual information entropy. The proposed method is then comprehensively examined via extensive data experiments and a user study on Amazon data. Experimental results reveal the overall superiority of the proposed method in comparison with other extant methods of concern, showing that it is an effective way to select an informative subset of online reviews. The proposed method is deemed desirable and useful for online consumers and service providers.

Usability is a big challenge for medical software, on one side because data are of large size and complex and on the other because the context of use is critical. We know that clinicians call for the right amount and to this regard, adaptive user interfaces can help not only identifying these information needs but also alleviating the data overload. However, before implementing user interface adaptations, these particular information demands have to be identified and prioritised. Eye-trackers can help accomplishing such tasks, since they can gather the visual behaviour of users, which depict interest, but using them in a deployed system requires a complex infraestructure. In this contribution, we analyse whether visual behaviour of users on a medication safety dashboard can be inferred from their interaction data. The results show that the use of the mouse interaction and visual behaviour (cognitive load) are some-how connected, measured in terms of the following features respectively: dwell time and mouse hovers between two consecutive clicks, and duration of gaze fixations. The article discusses the significance of this statement for the design of adaptations in medical dashboards.; Osasun-arlorako softwarean, beste esparru askotan bezala, erabilgarritasuna erronka handia da; batetik, datuak ugariak eta konplexuak direlako eta, bestetik, erabilera-testuingurua kritikoa delako. Jakina da langile klinikoek informazio kopuru egokia eskatzen dutela beren zereginak aurrera eramateko, eta, zentzu horretan, erabiltzaile- interfaze moldagarriak oso baliagarriak izan daitezke informazio-behar horiek asetzeko nahiz informaziogainkargaren arazoari heltzeko. Erabiltzaile-interfazerako egokitzapenak inplementatu aurretik, baina, aldakorrak diren informazio-behar horiek identifikatu eta lehenetsi egin behar dira. Begi-arakatzaileak lagungarriak izan daitezke zeregin hauek erdiesteko, erabiltzaileen portaera bisuala antzeman baitezakete, zeina interesaren adierazle den. Zoritxarrez, arakatzaile horiek sistema hedatu batean erabiltzeak azpiegitura konplexuegia eskatzen du. Ekarpen honetan aztertu dugu ea erabiltzaileen portaera bisuala inferi ote daitekeen erabiltzaile horiek botiken segurtasunari lotutako arbel batean izandako elkarrekintzaren datuetatik abiatuz. Emaitzek aditzera emandute alderdiak, hots, saguaren bidezko elkarrekintza eta portaera bisuala (karga kognitiboa), lotuta daudela; ezaugarri hauen arabera neurtuak, hurrenez hurren: saguaren ondoz ondoko bi kliken arteko denbora-tarteak eta sagu-pausatzeak, batetik, eta, bestetik, begiradaren finkapenaren iraupenak. Lanak eztabaidatzen du zer eragin izan dezakeen aurkikuntza horrek arbel medikoen egokitzapenen diseinuan.

Nowadays, recommender systems are used widely in various fields to solve the problem of information overload. Collaborative filtering and content-based models are representative solutions in recommender systems; however, the content-based model has some shortcomings, such as single kind of recommendation results and lack of effective perception of user preferences, while for the collaborative filtering model, there is a cold start problem, and such a model is greatly affected by its adopted clustering algorithm. To address these issues, a hybrid recommendation scheme is proposed in this paper, which is based on both collaborative filtering and content-based. In this scheme, we propose the concept of time impact factor, and a time-aware user preference model is built based on it. Also, user feedback on recommendation items is utilized to improve the accuracy of our proposed recommendation model. Finally, the proposed hybrid model combines the results of content recommendation and collaborative filtering based on the logistic regression algorithm.

In its traditional form, medical education begins with learning basic science disciplines, with subsequent transition to clinical training. The basic sciences are taught as a series of separate academic courses, with no coordination applied at the inter-disciplinary level. During past decades, the integrated curriculum has become increasingly popular as a novel instructional strategy that promotes contextual learning in medical practice. The curriculum breaks down the barriers between basic and clinical sciences (vertical integration), interconnects teaching of various basic science disciplines (horizontal integration) and facilitates the acquisition of critical thinking, problem-solving and team-working skills through collaborative learning. The vertical integration is encouraged with training in clinical and communication skills starting in the first semester, teaching basic sciences at the interface with medical problems and involving clinicians in giving lectures on applied anatomy and clinical physiology. In order to facilitate the horizontal integration, basic science disciplines are taught concurrently within interdisciplinary units aligned around the body organ systems. This contributes to a better understanding of complex interrelations between structure and function and stimulates wider insights into mechanisms of the disease. The integrated curriculum supports conceptual learning rather than simple memorisation of fragmented factual knowledge. As such, it relieves the information overload imposed on students due to a rapid growth of medical knowledge in the contemporary world. With the integrated curriculum, the main emphasis is placed on problem-oriented learning guided by an experienced tutor in a small group of students. In this setting, a realistic medical case is used as a trigger for discussion aimed at linking basic science concepts with the clinical problem. Through collaborative problem-solving, students develop a clinical reasoning and team-working skills. Overall, problem-based learning puts forward a student-centred approach in a sense that students themselves are primarily responsible for identifying relevant learning objectives and self-guided acquisition of medical knowledge. This raises their motivation in learning basic sciences and markedly improves the perception of learning environment. In summary, the integrated curriculum offers a number of benefits to medical students and appears to provide an effective instrument in developing professional competencies required in clinical work.

The reliance on machine learning in cognitive systems is further justified as it is not always possible to equip an intelligent agent with prior knowledge. In the modern times, the field of machine learning has been dominated by deep learning based on artificial neural networks. This chapter introduces deep learning for visual cognition. It starts with a brief introduction to deep neural networks (DNN) and some basic reusable configurations to realize various learning algorithms. The chapter discusses various modes of learning realized through DNN in some illustrative computer vision tasks. It presents a broad overview of the architecture of the networks and the principles involved. The chapter focuses on DNN‐based implementations of visual attention models, which is crucial for alleviating information overload in cognitive systems. It presents some research on synthesizing Bayesian reasoning with DNNs, aimed at improving the robustness of inferences. Finally, the chapter concludes with some salient observations on the topic.

The article presents selected aspects of the process of cognitive functioning of the users of contemporary technologies and the Internet, with special consideration of the negative effects of being immersed in the digital culture. The introduction synthetically characterizes the digital world, focusing on the most active users of the virtual space. In the body of the text, the author analyzes the negative effects of an individual’s functioning in the Internet space, especially those related to the change in the way of information acquisition and processing. The conclusions refer to implementing educational postulates connected with helping students develop the culture of behavior in the virtual space, involving as major elements the ability to distance oneself from digital media, to engage in deep reflection, and to organize and sort the acquired information. These skills are treated as crucial, ensuring the rational use of digital technologies. Focusing educational activities on the formation of youths’ media competence offers them an opportunity of fuller intellectual development, the sense of security in the context of expansion of the media, and active participation in the information society by structuring the available information and the knowledge constructed on its basis.

In autonomous multiagent or multirobotic systems, the ability to quickly and accurately respond to threats and uncertainties is important for both mission outcomes and survivability. Such systems are never truly autonomous, often operating as part of a human-agent team. Artificial intelligent agents (IAs) have been proposed as tools to help manage such teams; e.g., proposing potential courses of action to human operators. However, they are often underutilized due to a lack of trust . Designing transparent agents, who can convey at least some information regarding their internal reasoning processes, is considered an effective method of increasing trust. How people interact with such transparency information to gain situation awareness while avoiding information overload is currently an unexplored topic. In this article, we go part way to answering this question, by investigating two forms of transparency: sequential transparency , which requires people to step through the IA's explanation in a fixed order; and demand-driven transparency , which allows people to request information as needed. In an experiment using a multivehicle simulation, our results show that demand-driven interaction improves the operators’ trust in the system while maintaining, and at times improving, performance http://www.ieee.org/documents/taxonomy_v101.pdf ."?> and usability.

Increasing volumes of offline/online data has thrown diverse challenges. Availability of the data has made the researchers to urge for new paradigms to analyze data to gain useful insights from it. Such analysis can be helpful for predictions in various domains such as medical informatics, cyber security, fraud detection etc. Further, problem of overloaded information is that it leads to over-choice, especially for users in web applications. Machine learning algorithms construct models that can learn from the data without being explicitly programmed, to perform predictions/decisions. However, the limitations of machine learning have paved a way to deep learning. Unlike the task specific algorithms of machine learning, deep learning learns feature representations from data itself. These traits enabled deep learning to achieve futuristic results for exceptionally complex tasks of various domains. Particularly in health care, natural language processing, information retrieval, computer vision etc. Area of research in this work focused on processing sequential data in the domains of ambient air quality management and recommender systems. Air quality data analysis is one of the domains where deep learning models have outperformed the traditional machine learning models. Hence, this research aims to build a model to predict ambient air quality using Amplified Recurrent Neural Networks for a particular geographical area. Recommender Systems (RS) have become a part of all the web applications these days. The main objective of RS is to asist users by avoiding information overload through generating personalized suggestions. Deep learning-based RS models have gained more prominence these days. Consequently, this research aims to develop deep learning-based recommenders/personal assistance/advisory systems to exploit the information systems and to capture its user’s preferences. The primary goals of the objectives were successfully accomplished with promising results.

Recommender Systems (RSs) provide users with item choices based on their preferences reflected in past interactions and become important tools to alleviate the information overload problem for users. However, in real-world scenarios, the user–item interaction matrix is generally sparse, leading to the poor performance of recommendation methods. To cope with this problem, social information is introduced into these methods in several ways, such as regularization, ensemble, and sampling. However, these strategies to use social information have their limitations. The regularization and ensemble strategies may suffer from the over-smoothing problem, while the sampling-based strategy may be affected by the overfitting problem. To overcome the limitations of the previous efforts, a novel social recommendation model, namely, Social Collaborative Mutual Learning (SCML), is proposed in this article. SCML combines the item-based CF model with the social CF model by two well-designed mutual regularization strategies. The embedding-level mutual regularization forces the user representations in two models to be close, and the output-level mutual regularization matches the distributions of the predictions in two models. Extensive experiments on three public datasets show that SCML significantly outperforms the baseline methods and the proposed mutual regularization strategies can embrace the advantages of the item-based CF model and the social CF model to improve the recommendation performance.

Recommender systems have been an efficient strategy to deal with information overload by producing personalized predictions. Recommendation systems based on deep learning have accomplished magnificent results, but most of these systems are traditional recommender systems that use a single rating. In this work, we introduce a multi-criteria collaborative filtering recommender by combining deep neural network and matrix factorization. Our model consists of two parts: the first part uses a fused model of deep neural network and matrix factorization to predict the criteria ratings and the second one employs a deep neural network to predict the overall rating. The experimental results on two datasets, including a real-world dataset, show that the proposed model outperformed several state-of-the-art methods across different datasets and performance evaluation metrics.

Information overload and limited laboratory time usually result in students focusing mostly on procedural tasks to get the results, rather than being engaged with what they are doing. Moreover, tra...

The Internet has been identified in human enhancement scholarship as a powerful cognitive enhancement technology. It offers instant access to almost any type of information, along with the ability to share that information with others. The aim of this paper is to critically assess the enhancement potential of the Internet. We argue that unconditional access to information does not lead to cognitive enhancement. The Internet is not a simple, uniform technology, either in its composition, or in its use. We will look into why the Internet as an informational resource currently fails to enhance cognition. We analyze some of the phenomena that emerge from vast, continual fluxes of information–information overload, misinformation and persuasive design—and show how they could negatively impact users’ cognition. Methods for mitigating these negative impacts are then advanced: individual empowerment, better collaborative systems for sorting and categorizing information, and the use of artificial intelligence assistants that could guide users through the informational space of today’s Internet.

Information diffusion is one of the most important issues in social network analysis. Unlike most existing works, which either rely on network topology or node profiles, this study focuses on the diffusion itself, i.e., the recorded propagation histories. These histories are the evidence of diffusion and can be used to explain to users what happened in their networks. However, these histories can quickly grow in size and complexity, limiting their capacity to be intuitively understood. To reduce this information overload, in this paper we present the problem of propagation history ranking. The goal is to rank participant edges/nodes by their contribution to the diffusion. We first discuss and adapt a causal measure, Difference of Causal Effects (DCE), as the ranking criterion. Then, to avoid the complex calculation of DCE, we propose two integrated ranking strategies by adopting two indicators. One is responsibility, which captures the necessity aspect of causal effects. We further give an approximate algorithm, which could guarantee a feasible solution, for this indicator. The other is capability, which captures the sufficiency aspect of causal effects. Finally, promising experimental results are presented to verify the feasibility of the proposed ranking strategies.

With the increase in the number of live TV channels, audiences must spend increasing amounts of time and energy deciding which shows to watch; this problem is called information overload, and recommender systems (RSs) are effective methods for addressing such problems. Due to the high update rates and low replay rates of TV programs, the item cold-start problem is prominent, and this problem seriously affects the effectiveness of the recommender and limits the application of recommendation algorithms for live TV. To solve this problem better, RSs must consider information in addition to the time slot strategy, which relies on experience. At present, no methods make good use of viewing behavior records. Therefore, in this paper, we proposed a viewing environment model called DeepTV that considers viewing behavior records and electronic program guides and includes a feature generation process and a model construction process. In the feature generation process, we defined seven key features by clustering viewing time, distinguishing positive and negative feedback, capturing continuous viewing preference and introducing the remaining time proportion of candidate programs. We normalize the continuous features and add powers of them. In the model construction process, we regard the live TV recommendation task as a classification problem and fuse the above features by using a neural network. Finally, experiments on industrial datasets show that the proposed model significantly outperforms baseline algorithms.

Notes to the financial statements are an important source of economic and accounting information. The tendency to information overload of notes causes a rethinking of their role and content, as well as a revision of regulations governing the process of submitting financial statements at the legislative level. There is an urgent need to improve the disclosure process for disclosure requirements to prevent duplication of information in the financial statements as a whole and to eliminate irrelevant disclosures. This contributes to the fact that the information in the notes is clear, consistent, can be compared both in the dynamics of the enterprise and with the enterprises of the industry. The article examines the scientific approaches of domestic scientists on the architecture of notes to financial statements, which takes into account the relationship between the level of objectivity risk and the level of information risk. Starting in 2019, companies that are required to report under International Financial Reporting Standards are required to file taxonomic financial statements in a single electronic XBRL format. The main legislative acts regulating the use of this format are analyzed. The article considers the key principles of using the HBRL format. Based on the study of information resources, the elements of taxonomy are described in detail with an explanation of their functions. Describes the purpose and identifies the main benefits of reporting in XBRL format. The article clearly considers the submission of reports in XBRL-format on the example of reporting of agricultural enterprises, the feature of which is the application of IAS 41 "Agriculture". Namely, the main components of this format that need to be used are studied, as well as the sources of information for filling in the main blocks of notes according to this standard, taking into account industry specifics. It is determined that an important stage of reporting in XBRL-format is validation, which involves checking the compliance of the completed data. The article describes free resources for reading this format, as well as free software for the formation and validation of financial statements in XBRL-format. The need for training and retraining of specialists responsible for the process of preparing financial statements is emphasized.

The present study analyzes the phenomenon of information security and the ways of its potential achievement. Information security is interpreted as an important condition for the sustainable development in the global world. It’s noted in the study that globalization has a significant impact on the information sphere and its functioning. This has both positive and negative consequences for the information security of the humans, states and societies. The problems of information availability and overloading the Network, of digital dividing, hacking and meddling, of cybercrimes, cyber-terrorism and infogenic disasters are also the subjects of consideration. It’s concluded that in the global era the threats of the information security sphere are more numerous than the real results of their technical overcoming. To prevent such an imbalance the international cooperation in the field of the information security must be previously developed.

Programming tutorials are often created to demonstrate programming tasks with code examples. However, our study of Stack Overflow questions reveals the low utilization of high-quality programming tutorials, which is caused task description mismatch and code information overload. Document search can find relevant tutorial documents, but they often cannot find specific programming actions and code solutions relevant to the developers' task needs. The recently proposed activity-centric search over knowledge graph supports direct search of programming actions, but it has limitations in action coverage, natural language based task search, and coarse-grained code example recommendation. In this work, we enhance action coverage in knowledge graph with actions extracted from comments in code examples and more forms of activity sentences. To overcome the task description mismatch problem, we develop a code matching based task search method to find relevant programming actions and code examples to the code under development. We integrate our knowledge graph and task search method in the IDE, and develop an observe-push based tool to prompt developers with task-oriented API usage examples. To alleviate the code information overload problem, our tool highlights programming action and API information in the prompted tutorial task excerpts and code examples based on the underlying knowledge graph. Our evaluation confirms the high quality of the constructed knowledge graph, and show that our code matching based task search can recommend effective code solutions to programming issues asked on Stack Overflow. A small-scale user study demonstrates that our tool is useful for assisting developers in finding and using relevant programming tutorials in their programming tasks.

The design of recommender systems (RSs) to support software development encompasses the fulfillment of different steps, including data preprocessing, choice of the most appropriate algorithms, item delivery. Though RSs can alleviate the curse of information overload, existing approaches resemble black-box systems, in which the end-user is not expected to fine-tune or personalize the overall process. In this work, we propose LEV4REC, a low-code environment to assist developers in designing, configuring, and delivering recommender systems. The first step supported by the proposed tool includes defining an initial model that allows for the configuration of the crucial components of the wanted RS. Then, a subsequent phase is performed to finalize the RS design, e.g., to specify configuration parameters. LEV4REC is eventually capable of generating source code for the desired RS. To evaluate the capabilities of the approach, we used LEV4REC to specify two existing RSs built on top of two different recommendation algorithms, i.e., collaborative filtering and supervised machine learning.

The emergence of big data platforms has alleviated the restrictions of space and time on people's enjoyment of music information services. The need to improve user experience has become very urgent. One of the effective solutions to information overload is the recommendation system, which can help people discover interesting content from complex information. Therefore, the purpose of this article is to study a personalized film and television recommendation system based on a big data platform. This article first introduces the core technology of big data through an overview of the basic theory of big data. And combined with the traditional film and television recommendation method, analyze the existing problems and shortcomings, and analyze and discuss it with the core technology of big data. This article systematically expounds the overall process, system composition design and algorithm analysis of the personalized film and television recommendation system based on the big data platform. Experimental research shows that the algorithm proposed in this paper is better than the traditional User-basedCF strategy and Item-basedCF strategy under the same number of movies recommended by Hit-rate.

The COVID-19 pandemic has had a significant impact on society, both because of the serious health effects of COVID-19 and because of public health measures implemented to slow its spread. Many of these difficulties are fundamentally information needs; attempts to address these needs have caused an information overload for both researchers and the public. Natural language processing (NLP), the branch of artificial intelligence that interprets human language, can be applied to address many of the information needs made urgent by the COVID-19 pandemic. This review surveys approximately 150 NLP studies and more than 50 systems and datasets addressing the COVID-19 pandemic. We detail work on four core NLP tasks: information retrieval, named entity recognition, literature-based discovery, and question answering. We also describe work that directly addresses aspects of the pandemic through four additional tasks: topic modeling, sentiment and emotion analysis, caseload forecasting, and misinformation detection. We conclude by discussing observable trends and remaining challenges., Comment: 51 pages, 3 figures and 2 tables; published at the Annual Review of Biomedical Data Science

Recently, the worldwide COVID-19 pandemic has led to an increasing demand for online education platforms. However, it is challenging to correctly choose course content from among many online education resources due to the differences in users’ knowledge structures. Therefore, a course recommender system has the essential role of improving the learning efficiency of users. At present, many online education platforms have built diverse recommender systems that utilize traditional data mining methods, such as Collaborative Filtering (CF). Despite the development and contributions of many recommender systems based on CF, diverse deep learning models for personalized recommendation are being studied because of problems such as sparsity and scalability. Therefore, to solve traditional recommendation problems, this study proposes a novel deep learning-based course recommender system (DECOR), which elaborately captures high-level user behaviors and course attribute features. The DECOR model can reduce information overload, solve high-dimensional data sparsity problems, and achieve high feature information extraction performance. We perform several experiments utilizing real-world datasets to evaluate the DECOR model’s performance compared with that of traditional recommendation approaches. The experimental results indicate that the DECOR model offers better and more robust recommendation performance than the traditional methods.

Recommender systems (RSs) have gained immense popularity and achieved great success as intelligent information system that helps to deal with information overload problem. Recommender systems (RSs) have been very long evaluated for accuracy. Nowadays, along with the accuracy of the presented recommendation, other factors like novelty, diversity and serendipity have become an important aspect of recommendation systems. In this paper, we propose Explanation-based Serendipitous Recommender System (EBSRS) to generate explanation for the serendipitous recommendations presented to the user. Hereby, the approach integrates the concept of serendipity in recommendations, ensuring the relevance of recommendations while generating serendipitous recommendation. The approach generates the explanation for the serendipitous recommendations to provide a justification for the recommended list. The proposed approach is evaluated using accuracy and relevancy measures. Precision, recall and f-measure are used as the accuracy measure, whereas explanation coverage and unexpectedness is used to get the relevancy measure.

The amount of Internet data is increasing day by day with the rapid development of information technology. To process massive amounts of data and solve information overload, researchers proposed recommender systems. Traditional recommendation methods are mainly based on collaborative filtering algorithms, which have data sparsity problems. At present, most model-based collaborative filtering recommendation algorithms can only capture first-order semantic information and cannot process high-order semantic information. To solve the above issues, in this paper, we propose a hybrid graph neural network model based on heterogeneous graphs with high-order semantic information extraction, which models users and items respectively by learning low-dimensional representations for them. We introduced an attention mechanism to allow the model to understand the corresponding edge weights adaptively. Simultaneously, the model also integrates social information in the data to learn more abundant information. We performed some experiments on related datasets. Our method achieved better results than some current advanced models, which verified the proposed model’s effectiveness.

As an important means to solve information overload, recommender systems have been widely applied in many fields, such as e-commerce and advertising. However, recent studies have shown that recommender systems are vulnerable to poisoning attacks; that is, injecting a group of carefully designed user profiles into the recommender system can severely affect recommendation quality. Despite the development from shilling attacks to optimization-based attacks, the imperceptibility and harmfulness of the generated data in most attacks are arduous to balance. To this end, we propose a triple adversarial learning for influence based poisoning attack (TrialAttack), a flexible end-to-end poisoning framework to generate non-notable and harmful user profiles. Specifically, given the input noise, TrialAttack directly generates malicious users through triple adversarial learning of the generator, discriminator, and influence module. Besides, to provide reliable influence for TrialAttack training, we explore a new approximation approach for estimating each fake user's influence. Through theoretical analysis, we prove that the distribution characterized by TrialAttack approximates to the rating distribution of real users under the premise of performing an efficient attack. This property allows the injected users to attack in an unremarkable way. Experiments on three real-world datasets show that TrialAttack's attack performance outperforms state-of-the-art attacks, and the generated fake profiles are more difficult to detect compared to baselines.

In response to the problems that the new crown pneumonia epidemic may bring to doctors in schools of Chinese medicine, such as information overload, traumatic stress, changes in mentality, crisis of trust, safety when going abroad, and employment choices, explain from the perspective of medical teachers in Chinese medicine schools. The understanding of the epidemic and the major events during the epidemic, combined with the experience of the psychological impact of the past epidemic on the doctors in the school, to highlight the outstanding contributions of medical staff in the fight against the epidemic, and to emphasize the strong leadership of the party and the unity of the people during the fight against the epidemic. The huge role played by Chinese medicine in the fight against the epidemic is the principle. In recent years, cloud computing technology has been continuously developed and improved. Traditional infrastructure as a service has been unable to meet users' needs for cloud computing delivery capabilities. They hope that more and more traditional IT software will be delivered in the form of cloud services. This paper mainly studies the utility optimization and stable matching strategy of UDRN based on EH and limited character input, divides the nodes into multiple clusters, and implements the utility optimization strategy within the clusters. Model users and relays as energy buyers and energy sellers. First, when users choose relays as their candidates, the golden section method is used to obtain the best relay power to maximize user utility. Secondly, based on the principle of maximizing the utility of matching, a mutual preference matrix between users and relays is established. Finally, based on the mutual preference matrix, an improved UDRN stable matching algorithm is proposed through the less complex GS algorithm. This algorithm will play a great role in the psychological reconstruction of doctors after the epidemic.

Recommender system is the core to solve the problem of information overload. Meanwhile, non-IID (non-Independently Identically Distribution) recommender system shows its potential in improving recommendation quality and solving the problems such as sparsity and cold start. With the development of deep learning, recommendation has become a hot topic and a large number of studies have proved the effectiveness of deep learning in recommender system. In this work, we contribute a new multi-layer neural network framework, EACoupledCF (Enhanced Attention-based Coupled Collaborative Filtering), to perform collaborative filtering. The idea of EACoupledCF is to use an outer product to explicitly model the pairwise correlations between the dimensions of the embedding space, utilize the convolutional neural network and introduce spatial attention mechanism to learn high-order features between embedded dimensions. At the same time, it also proposes a novel model called DCCF (Deep Combination Collaborative Filtering) for implicit feedback learning in order to capture the interactive information better. In contrast to the existing neural recommendation models, the experimental results obtained on two real-word large datasets show the effectiveness of our proposed model.

The development of democratic systems is a crucial task as confirmed by its selection as one of the Millennium Sustainable Development Goals by the United Nations. In this article, we report on the progress of a project that aims to address barriers, one of which is information overload, to achieving effective direct citizen participation in democratic decision-making processes. The main objectives are to explore if the application of Natural Language Processing (NLP) and machine learning can improve citizens' experience of digital citizen participation platforms. Taking as a case study the "Decide Madrid" Consul platform, which enables citizens to post proposals for policies they would like to see adopted by the city council, we used NLP and machine learning to provide new ways to (a) suggest to citizens proposals they might wish to support; (b) group citizens by interests so that they can more easily interact with each other; (c) summarise comments posted in response to proposals; (d) assist citizens in aggregating and developing proposals. Evaluation of the results confirms that NLP and machine learning have a role to play in addressing some of the barriers users of platforms such as Consul currently experience., Comment: 19 pages, 5 figures, 4 tables, to appear in Digital Government: Research and Practice (DGOV)