Application Of Recommender Systems Research Articles

Application of recommendation system in educational Field

The article is devoted to the issue of the application of recommender system technology in the educational sphere. It was determined that certain tasks of the educational field can be described in terms of recommendation systems: the user who is given a recommendation is the education applicant; the objects of his interest are disciplines from the catalog of optional disciplines, sources from the library of the educational institution, topics (or research area) of qualification papers, potential supervisors of qualification papers, external courses for the organization of self-education. A list of resources was created to determine the characteristics of the education applicants’ objects of interest and the education applicants themselves within the framework of formal education, and an analysis of their content and method of formation was carried out. The structure of the recommendation system has been developed; its feature is that each object of interest of the education applicant corresponds to a separate module of recommendations. At the same time, the recommendation modules use shared resources, including databases of the educational institution with direct information about the objects of interest and the education applicant, as well as survey databases consisting of general regular mandatory surveys for education applicants at the level of the educational institution and contextual surveys regarding objects of interest. A hybrid approach was chosen to form the recommendations. The structure of the system provides for the use of collaborative filtering for processing survey results, and data presented in the form of semi-structured or arbitrary texts in natural language is proposed to be processed using Natural Language Processing and Text Mining methods, which will allow taking into account semantically similar values of the characteristics of objects of interest and users and thus to improve the quality of the recommendation system.

Movie Recommendation Using Hybrid-Based Approach

The field of recommendation systems has been rapidly growing due to the increasing amount of data available on the internet. Movie recommendation systems are one of the most widely used applications of recommendation systems. In this paper, we propose a hybrid-based approach to movie recommendation systems. The proposed approach combines content-based filtering and collaborative filtering techniques to provide better recommendations. The content-based filtering technique uses movie features such as genre, director, actors, and plot to recommend similar movies to the users. The collaborative filtering technique uses the user's past behaviour and other users' behaviour to recommend movies to the user. We evaluated the proposed hybrid approach on the Cosine Similarity and SVD dataset to achieve better results compared to the individual content-based and collaborative filtering techniques.

Application of Top-N Rule-based Optimal Recommendation System for Language Education Content based on Parallel Computing

Application of Top-N Rule-based Optimal Recommendation System for Language Education Content based on Parallel Computing

An approach for ontology-based research and recommendation on systems engineering projects

Recommendation systems (RS) have dramatically evolved these past few years, generating more and more accurate results and developing innovative filtering methods. A huge breakthrough was the integration of ontologies into their recommendation process. It integrated the domain's knowledge into its reasoning process, thus overcoming the limitations of the conventional RS. The main purpose of this paper is to explore the application of ontology-based RS within critical infrastructure projects implementing the systems engineering or model-based engineering approach.

Pedestrian attribute recognition based on dual self-attention mechanism

Recognizing pedestrian attributes has recently obtained increasing attention due to its great potential in person re-identification, recommendation system, and other applications. Existing methods have achieved good results, but these methods do not fully utilize region information and the correlation between attributes. This paper aims at proposing a robust pedestrian attribute recognition framework. Specifically, we first propose an end-to-end framework for attribute recognition. Secondly, spatial and semantic self-attention mechanism is used for key points localization and bounding boxes generation. Finally, a hierarchical recognition strategy is proposed, the whole region is used for the global attribute recognition, and the relevant regions are used for the local attribute recognition. Experimental results on two pedestrian attribute datasets PETA and RAP show that the mean recognition accuracy reaches 84.63% and 82.70%. The heatmap analysis shows that our method can effectively improve the spatial and the semantic correlation between attributes. Compared with existing methods, it can achieve better recognition effect.

A machine learning based crop recommendation system and user-friendly android application for cultivation

A machine learning based crop recommendation system and user-friendly android application for cultivation

A machine learning based crop recommendation system and user-friendly android application for cultivation

A machine learning based crop recommendation system and user-friendly android application for cultivation

How do you solve a problem like Alexa?

Emotional Artificial Intelligence (EAI) is emerging as a mainstream technology. With the increasing use of EAI in different sectors, novel legal and ethical concerns are being raised. This paper focuses on an entertainment and creative content delivery recommendation system application, namely Amazon Alexa’s use of Neural-Text-to-Speech (NTTS) technology to capture and respond to users’ perceived emotions based on their voice. It also enables Alexa to play music based on, among other elements, its perception of users’ emotions. Given the recognised impact ‘music‘ has on emotions and Alexa‘s increasing involvement with big music sector actors, we are particularly concerned about how this domain can enable the manipulation of users. We use this example to highlight problems with the approach to AI regulation taken in the proposed EU Artificial Intelligence Act (AIA).

A Study of Health Recommender Systems: Analyzing the Advancement of Sustainable Health Recommender Systems Using NLP Techniques

Over the years, the amount of healthcare data has immensely increased due to technological development. Although it has provided the user with ease to data access, large amounts of data can be challenging to the user due to information overload. In the case of the healthcare domain, any misinterpreted information may cause a severe situation. Recommender systems are proving to be beneficial due to their use in extracting the required information quickly. In this paper, we conducted an analysis of the existing health recommender systems using NLP techniques. We reviewed the existing solutions for health recommender systems, described and compared them based on their features and algorithms employed, and presented future research directions. Our findings indicate that the popular applications of the health recommender systems developed are in patient-doctor match, recommending drugs, cancer predictions, chronic disease diagnosis, and recommender systems for patients with heart problems. Further, given the knowledge of sustainable products, a recommender system can suggest products with these characteristics.

Algorithmic modeling of public recommender systems: insights from selected cities

PurposeIn the context of digital public governance of the 21st century, recommender systems serve as a digital tool to support decision-making and shift toward proactive public services delivery. This paper aims to synthesize an algorithm for public recommender systems deployment coherent with the digital transformation of public services in three Russian regions: the City of Moscow, Moscow region and Astrakhan region.Design/methodology/approachThe studied regions serve as an adequate representation of the country’s population coverage carrying, at the same time, diversity of public governance structures in qualitative and quantitative terms. Thus, the authors were able to retrieve both commonalities and particularities in locally applied policies to create an algorithm model for governance high-tech decision support systems (DSS) deployment in management terms. Therefore, the authors use structural and functional analysis to derive the matters for further induction into our algorithmic model.FindingsThe proposed algorithmic model is developed under the framework of automated verification of current public service delivery mechanisms. The practical application of recommendation systems as a special case of DSS is shown in the example of public service delivery. It is assumed that following the developed algorithm leads to the “digital maturity” of a particular sector of public governance.Originality/valueThe paper holds a novel look at public services digital transformation through the application of recommender systems, which is evidenced by the algorithmic model approbation on the theoretical level.

Adversarial examples for extreme multilabel text classification

Extreme Multilabel Text Classification (XMTC) is a text classification problem in which, (i) the output space is extremely large, (ii) each data point may have multiple positive labels, and (iii) the data follows a strongly imbalanced distribution. With applications in recommendation systems and automatic tagging of web-scale documents, the research on XMTC has been focused on improving prediction accuracy and dealing with imbalanced data. However, the robustness of deep learning based XMTC models against adversarial examples has been largely underexplored. In this paper, we investigate the behaviour of XMTC models under adversarial attacks. To this end, first, we define adversarial attacks in multilabel text classification problems. We categorize attacking multilabel text classifiers as (a) positive-to-negative, where the target positive label should fall out of top-k predicted labels, and (b) negative-to-positive, where the target negative label should be among the top-k predicted labels. Then, by experiments on APLC-XLNet and AttentionXML, we show that XMTC models are highly vulnerable to positive-to-negative attacks but more robust to negative-to-positive ones. Furthermore, our experiments show that the success rate of positive-to-negative adversarial attacks has an imbalanced distribution. More precisely, tail classes are highly vulnerable to adversarial attacks for which an attacker can generate adversarial samples with high similarity to the actual data-points. To overcome this problem, we explore the effect of rebalanced loss functions in XMTC where not only do they increase accuracy on tail classes, but they also improve the robustness of these classes against adversarial attacks. The code for our experiments is available at https://github.com/xmc-aalto/adv-xmtc.

Research directions in recommender systems for health and well-being

Recommender systems have been put to use in the entertainment and e-commerce domains for decades, and in these decades, recommender systems have grown and matured into reliable and ubiquitous systems in today’s digital landscape. Relying on this maturity, the application of recommender systems for health and well-being has seen a rise in recent years, paving the way for tailored and personalized systems that support caretakers, caregivers, and other users in the health domain. In this introduction, we give a brief overview of the stakes, the requirements, and the possibilities that recommender systems for health and well-being bring.

User-centered Design Strategies to Develop Mobile Application for Selection of Digital Forensics Tool

There are several types of digital forensics tool. Therefore, to help investigators to choose suitable tools, a recommendation system is needed. This research type is development of mobile application recommendation system. The development using User Centered Design (UCD) method. The evaluation system uses the Blackbox method and the User Acceptance Test (UAT) method. From the results, it is concluded that the application is useful, easy to use, and easy to learn by users. As for usability testing, it was found that the users found it very helpful to operate, which was 28 students with a margin of error of 5%.

ИНТЕЛЛЕКТУАЛЬНАЯ РЕКОМЕНДАТЕЛЬНАЯ СИСТЕМА ДЛЯ ПРОСТРАНСТВЕННОГО АНАЛИЗА

The work is devoted to the analysis of mechanisms of formation of recommendations andevaluation of the user's reaction to them in the interactive mode of work with the geoinformationsystem. One of the important areas of application of recommender systems is the search and decision-making in spatial situations. A peculiarity of this class of problems is the uncertainty of taskdefinition and ambiguity of decision evaluation. Users are often faced with problems that do nothave a clear formulation. To try to solve them, it is necessary not only to designate the direction ofsolution search, but also to find an adequate sequence of tasks with clearly formulated input andoutput data. Recommendations in such cases are designed in a dialogue with the user-analyst todevelop a strategy for finding solutions. In this paper we study a smart recommendation systemusing the experience of dialog interaction. We propose a model of adaptation to the mental imageof the problem, which builds the user, taking into account the levels of situational awareness andcognitive load. The peculiarity of the model is the use of visual cartographic objects, which areindicators of the state of the mental image. A recommendation is represented by a set of objectsthat are introduced into the field of cartographic analysis. This implicitly induces a certain semanticdirection of increasing situational awareness. A criterion of satisfaction with the recommendationis suggested. A diagram of recommender system states, which describes the selection of context,adequate to the problem being solved, is given. The context is understood as an informationobject, capable of providing program functions and data for solving problems of a limited class.A sequence of contexts in an analysis session is considered as a precedent of experience. Indicatorsof trend, tendency and rhythm are proposed for possible chains of contexts. The degree ofsemantic proximity of precedents to the current course of search for a solution is estimated bythese indicators. Their use will increase the speed of adaptation.

Recommendation Systems: A Systematic Review

This article presents a comprehensive and objective systematic review of existing research on recommendation systems with regards to core theory, latest studies, various applications, current attitudes, and potential future applications. The research is mainly based on exploring professional peer-reviewed studies and articles and using their abstracts to create a comprehensive and unbiased review of existing research. The following search terms were used to identify articles and studies for the research: recommendation systems; recommender systems; core theory of recommender systems; current attitudes towards recommendation systems; latest studies on recommendation systems; applications of recommendation systems; potential studies on recommendation systems; and future potential applications of recommendation systems. The research also used the advanced search filter to locate recent studies for comparison by limiting the search by year to find studies published from 2021 onwards. Most literature on this area highlights the importance of recommendation systems in almost all aspects of modern life. Specifically, recommendation systems have become critical components in business, health care, education, marketing, and social networking domains. Additionally, most studies identified reinforcement of learning and deep learning techniques as significant developments in the field. These techniques form the backbone of most modern recommendation systems. The primary concern that could hinder further evolution systems is their consequent filter bubble effects which many studies showed to be problematic. Healthcare is a central area that shows tremendous potential for these systems. Although recommender systems have been implemented in this domain, there remains a lot of untapped potential that, if unleashed, could revolutionize medicine and healthcare. But the problems facing these systems have to be tackled first to establish trust. Keywords: Recommendation systems, Recommender systems, Deep learning, Reinforcement learning DOI: 10.7176/CEIS/13-4-04 Publication date: August 31 st 2022

Smartphone Selection Recommendation System

Smartphone is a telecommunications tool that has the same capabilities as conventional telephones, where smartphones are much more practical and easy to carry anywhere. The brands smartphone offered have many models and specifications such as ram, rom, camera, processor and others. To make it easier for users to choose the type of smartphone, it takes a smartphone selection recommendation system to assist users in making a decision. In this study resulted in a smartphone selection recommendation system application that is designed to assist users in making decisions in choosing a smartphone. This system is designed with reference to the calculation results of the Simple Additive Weighting (SAW) method by considering several criteria used to search smartphones. From the results of calculations using the SAW method, the preference values ​​of V1 to V3 are determined where according to alternative data, V1 for alternative A1 with a value of 0.76, V2 for alternative A2 with a value of 0.77, and V3 for alternative A3 with a value of 0.85. So that the largest ranking value is obtained, namely V3 with a value of 0.85. So alternative V3 is the alternative that was chosen as the best alternative.

Two-Stage Voice Application Recommender System for Unhandled Utterances in Intelligent Personal Assistant.

Intelligent personal assistants (IPA) enable voice applications that facilitate people's daily tasks. However, due to the complexity and ambiguity of voice requests, some requests may not be handled properly by the standard natural language understanding (NLU) component. In such cases, a simple reply like “Sorry, I don't know” hurts the user's experience and limits the functionality of IPA. In this paper, we propose a two-stage shortlister-reranker recommender system to match third-party voice applications (skills) to unhandled utterances. In this approach, a skill shortlister is proposed to retrieve candidate skills from the skill catalog by calculating both lexical and semantic similarity between skills and user requests. We also illustrate how to build a new system by using observed data collected from a baseline rule-based system, and how the exposure biases can generate discrepancy between offline and human metrics. Lastly, we present two relabeling methods that can handle the incomplete ground truth, and mitigate exposure bias. We demonstrate the effectiveness of our proposed system through extensive offline experiments. Furthermore, we present online A/B testing results that show a significant boost on user experience satisfaction.

DiPS: Differentiable Policy for Sketching in Recommender Systems

In sequential recommender system applications, it is important to develop models that can capture users' evolving interest over time to successfully recommend future items that they are likely to interact with. For users with long histories, typical models based on recurrent neural networks tend to forget important items in the distant past. Recent works have shown that storing a small sketch of past items can improve sequential recommendation tasks. However, these works all rely on static sketching policies, i.e., heuristics to select items to keep in the sketch, which are not necessarily optimal and cannot improve over time with more training data. In this paper, we propose a differentiable policy for sketching (DiPS), a framework that learns a data-driven sketching policy in an end-to-end manner together with the recommender system model to explicitly maximize recommendation quality in the future. We also propose an approximate estimator of the gradient for optimizing the sketching algorithm parameters that is computationally efficient. We verify the effectiveness of DiPS on real-world datasets under various practical settings and show that it requires up to 50% fewer sketch items to reach the same predictive quality than existing sketching policies.

Knowledge Discovery in a Recommender System: The Matrix Factorization Approach

Two famous matrix factorization techniques, the Singular Value Decomposition (SVD) and the Nonnegative Matrix Factorization (NMF), are popularly used by recommender system applications. Recommender system data matrices have many missing entries, and to make them suitable for factorization, the missing entries need to be filled. For matrix completion, we use mean, median and mode as three different cases of imputation. The natural clusters produced after factorization are used to formulate simple out-of-sample extension algorithms and methods to generate recommendation for a new user. Two cluster evaluation measures, Normalized Mutual Information (NMI) and Purity are used to evaluate the quality of clusters.

Exploring post-hoc agnostic models for explainable cooking recipe recommendations

The need of increasing trustworthiness and transparency in artificial intelligence (AI)-based systems that adhere ethical principles of respect for human autonomy, prevention of harm, fairness, and explainability; has boosting the development of systems that incorporate such issues as a key component. Recommender systems (RSs) are included in such AI-based systems, because they use intelligent algorithms for providing the most suitable items to active users according to other users’ preferences. The RSs success is based on how much customers trust on the system, therefore recommendation explainability has become a crucial dimension for RSs adoption in real-world scenarios. Among the different successful applications of RS, it is remarkable the recent and exponential importance of recommendations for health and wellness areas. Hence, this paper aims at exploring, adapting and applying explanations for nutrition/recipes recommendations, that not only explain why the recommendation is enjoyable but also, it is aware of how healthy is the recommendation. Among the different methodologies to explain recommendations, this paper is focused on post-hoc explainability approaches and its adaptation, application and evaluation for nutrition/recipes recommendation. Eventually, it is included a comprehensive experimental study for characterizing the strengths and weaknesses of such explainability approaches in the recipe recommendation context.