Development Of Recommender Systems Research Articles

Promoting sustainable tourism by recommending sequences of attractions with deep reinforcement learning

Developing Recommender Systems (RSs) is particularly interesting in the tourist domain, where one or more attractions have to be suggested to users based on preferences, contextual dimensions, and several other constraints. RSs usually rely on the availability of a vast amount of historical information about users’ past activities. However, this is not usually the case in the tourist domain, where acquiring complete and accurate information about the user’s behavior is complex, and providing personalized suggestions is frequently practically impossible. Moreover, even though most available Touristic RSs (T-RSs) are user-focused, the touristic domain also requires the development of systems that can promote a more sustainable form of tourism. The concept of sustainable tourism covers many aspects, from economic, social, and environmental issues to the attention to improving tourists’ experience and the needs of host communities. In this regard, one of the most important aspects is the prevention of overcrowded situations in attractions or locations (over-tourism). For this reason, this paper proposes a different kind of T-RS, which focuses more on the tourists’ impact on the destinations, trying to improve their experiences by offering better visit conditions. Moreover, instead of suggesting the next Point of Interest (PoI) to visit in a given situation, it provides a suggestion about a complete sequence of PoIs (tourist itinerary) that covers an entire day or vacation period. The proposed technique is based on the application of Deep Reinforcement Learning, where the tourist’s reward depends on the specific spatial and temporal context in which the itinerary has to be performed. The solution has been evaluated with a real-world dataset regarding the visits conducted by tourists in Verona (Italy) from 2014 to 2023 and compared with three baselines.

Using Content-Based Filtering and Apriori for Recommendation Systems in a Smart Shopping System

This research is motivated by the increasing significance of online shopping platforms and the challenges faced by users in locating products that align with their preferences and requirements, which can significantly influence the sales performance of online retailers. Consequently, the primary objective of this study is to design and implement a recommendation system capable of identifying suitable products and forecasting the purchase frequency for various product combinations, while also integrating this recommendation system with a smart shopping platform. To achieve this objective, the research employs machine learning techniques, specifically content-based filtering and the Apriori algorithm. Content-based filtering is utilized to analyze user preferences and behavioral patterns related to visited products, while the Apriori algorithm is employed to evaluate support and confidence values for item set combinations, thereby generating frequency values for future transactions involving product combinations. Additionally, a smart shopping system is developed and integrated, enhancing the shopping experience through smartphone applications and streamlining the payment process to facilitate seamless product purchases. The research methodology involves data collection pertaining to products and user preferences, followed by several testing involving a sample group of user respondents. The results demonstrate that the developed recommendation system effectively delivers relevant product recommendations based on user preferences, achieving a confidence value up to 98%. Furthermore, the smart shopping system proves capable of independently assisting users throughout the transaction process, thereby enhancing overall user experience and convenience.

Exploring social networks through stochastic multilayer graph modeling

Several graph models are available today to model online social networks. These graph models are used to analyze the structural properties of the online social network, such as detecting communities, finding the influential spreader and predicting the behavior of the network. However, these models are based on deterministic single-layer graphs that may not be appropriate when online users use multiple social networks at the same time and social networks provide specific services. Moreover, because of the unknown and dynamic nature related to the behaviors and activities of online users, as well as structural and behavioral parameters, which may vary over time, stochastic multi-layer models could be applied to better capture and represent this phenomenon, as well as the dynamic nature of social networks. For example, in recommender systems, users' interests are unknown parameters and vary over time. Therefore, stochastic multilayer graph modeling can be used to develop recommender systems by considering different layers for different types of interests or preferences. In this paper, we propose a stochastic multilayer graph in which the edges are associated with random variables as a potential graph model for the analysis of online social networks. Therefore, after redefine some network measures related to stochastic multilayer graphs, we propose a Cellular Goore Game (CGG) based algorithm to computes the redefine network measures. A CGG-based algorithm computes defined network measures by learning automata from the edges of stochastic multilayer graphs. The experimental results show that the new CGG-based algorithm requires fewer samples from the edges of stochastic multilayer graphs than the standard sampling method in network measures calculation. Furthermore, the obtained results demonstrate that, from an evaluation perspective, the CGG-based algorithm provides superior results in terms of Kolmogorov-Smirnov (KS-test), Pearson Correlation Coefficient (PCC), Normalized Root Mean Square Error (NRMSE) and Kullback–Leibler divergence (KL-test).

Advanced Deep Learning Model for Predicting the Academic Performances of Students in Educational Institutions

Educational institutions are increasingly focused on supporting students who may be facing academic challenges, aiming to enhance their educational outcomes through targeted interventions. Within this framework, leveraging advanced deep learning techniques to develop recommendation systems becomes essential. These systems are designed to identify students at risk of underperforming by analyzing patterns in their historical academic data, thereby facilitating personalized support strategies. This research introduces an innovative deep learning model tailored for pinpointing students in need of academic assistance. Utilizing a Gated Recurrent Neural Network (GRU) architecture, the model is rich with features such as a dense layer, max-pooling layer, and the ADAM optimization method used to optimize performance. The effectiveness of this model was tested using a comprehensive dataset containing 15,165 records of student assessments collected across several academic institutions. A comparative analysis with existing educational recommendation models, like Recurrent Neural Network (RNN), AdaBoost, and Artificial Immune Recognition System v2, highlights the superior accuracy of the proposed GRU model, which achieved an impressive overall accuracy of 99.70%. This breakthrough underscores the model’s potential in aiding educational institutions to proactively support students, thereby mitigating the risks of underachievement and dropout.

HYBRID RECOMMENDER FOR VIRTUAL ART COMPOSITIONS WITH VIDEO SENTIMENTS ANALYSIS

Topicality. Recent studies confirm the growing trend to implement emotional feedback and sentiment analysis to improve the performance of recommender systems. In this way, a deeper personalization and current emotional relevance of the user experience is ensured. The subject of study in the article is a hybrid recommender system with a component of video sentiment analysis. The purpose of the article is to investigate the possibilities of improving the effectiveness of the results of the hybrid recommender system of virtual art compositions by implementing a component of video sentiment analysis. Used methods: matrix factorization methods, collaborative filtering method, content-based method, knowledge-based method, video sentiment analysis method. The following results were obtained. A new model has been created that combines a hybrid recommender system and a video sentiment analysis component. The average absolute error of the system has been significantly reduced. Added system reaction to emotional feedback in the context of user interaction with virtual art compositions. Conclusion. Thus, the system can not only select the most suitable virtual art compositions, but also create adaptive and dynamic content, which will increase user satisfaction and improve the immersive aspects of the system. A promising direction of further research may be the addition of a subsystem with a generative neural network, which will create new virtual art compositions based on the conclusions of the developed recommendation system.

Selecting the Best K Features for Predicting Student Participation in Generic Competency Development Activities in Higher Education

Generic competency (GC) is an essential but often overlooked aspect of developing students in higher education. While there is much research about using technologies to develop discipline- specific skills for students, the use of technologies in GC development is insufficient. In particular, more research is needed on using technologies to predict student participation in GC development activities (GCDAs). Machine learning (ML) can use student characteristics, known as features, to predict their involvement in GCDAs. However, too many features will slow down the prediction process and reduce the ability to pinpoint the best features for prediction. This study explored an effective way to identify the minimal number of features essential for predicting student participation in GCDAs. The findings help educators develop recommendation systems to help students select the most beneficial GCDA for their holistic development. We collected 98 features from 9570 students from a community college. Then, we applied the Principal Component Analysis and SelectKBest algorithms to reduce the number of features from 98 to 8. Finally, we compared the accuracy of predictions using KNN and ANN based on the all-feature dataset with those based on the reduced-feature dataset. The results showed that the reduced-feature dataset maintained good prediction accuracy and enabled the educator to recommend the GCDAs to students. The findings could drive further research and development in applying machine learning technologies to enhance the recommendations for GCDAs for higher-education students.

Data augmentation and refinement for recommender system: A semi-supervised approach using maximum margin matrix factorization

Collaborative filtering (CF) has become a popular method for developing recommender systems (RSs) where ratings of a user for new items are predicted based on her past preferences and available preference information of other users. Despite the popularity of CF-based methods, their performance is often greatly limited by the sparsity of observed entries. In this study, we explore the data augmentation and refinement aspects of Maximum Margin Matrix Factorization (MMMF), a widely accepted CF technique for rating predictions, which has not been investigated before. We exploit the inherent characteristics of MMMF to assess the confidence level of algorithm’s prediction of individual rating and propose a semi-supervised approach for rating augmentation based on self-training. We hypothesize that any CF algorithm’s predictions with low confidence are due to some deficiency in the training data and hence, the performance of the algorithm can be improved by adopting a systematic data augmentation strategy. We iteratively use some of the ratings predicted with high confidence to augment the training data and remove low-confidence entries through a refinement process. By repeating this process, the system learns to improve prediction accuracy. Our method is experimentally evaluated on several state-of-the-art CF algorithms and leads to informative rating augmentation, improving the performance of the baseline approaches.

Enhancing neural collaborative filtering using hybrid feature selection for recommendation.

The past decade has seen substantial growth in online transactions. Accordingly, many professionals and researchers utilize deep learning models to design and develop recommender systems to suit the needs of online personal services. These systems can model the interactions between users and items. However, existing approaches focus on either modeling global or local item correlation and rarely consider both cases, thus failing to represent user-item correlation very well. Therefore, this article proposes a deep collaborative recommendation system based on a convolutional neural network with an outer product matrix and a hybrid feature selection module to capture local and global higher-order interaction between users and items. Moreover, we incorporated the weights of generalized matrix factorization to optimize the overall network performance and prevent overfitting. Finally, we conducted extensive experiments on two real-world datasets with different sparsity to confirm that our proposed approach outperforms the baseline methods we have used in the experiment.

Job Recommendation System Using NLP

Abstract: Recommender systems is one of the most successful machine learning applications. We are exposed to the products/information recommended by these systems everywhere in our daily life. This project will introduce several recommender systems in NLP, specifically in the domain of online recruitment. I will explain the important ideas behind the recommender systems in our web application, it might be also similar with those in recruiting platforms like LinkedIn, Xing. One of my main jobs is to design and develop recommender systems on the skill-based matching app. Before getting into this specific topic, I would like to go over the general concepts and methods of current recommender system in different domains. We have provided a brief overview of the approaches, techniques, and applications of recommendation systems in this paper. One significant application of recommendation systems is in the field of job recruitment, where candidates are chosen using online job recruitment portals based on their profiles, employment histories, and behavioral tendencies. According to a recent survey, this field has not been thoroughly investigated up to this point, and the current job recommender system has many flaws. They analyze resumes, profiles, and job descriptions, but because of the "cold start" problem, new job postings and candidate profiles are not properlymatched. In some cases, potential candidates lose their jobs as a result of inadequate job descriptions and education information in the ontology.

Comprehensive Readability Assessment of Scientific Learning Resources

Readability is the measure of how easier a piece of text is. Readability assessment plays a crucial role in facilitating content writers and proofreaders to receive guidance about how easy or difficult a piece of text is. In literature, classical readability, lexical measures, and deep learning based model have been proposed to assess the text readability. However, readability assessment using machine and deep learning is a data-intensive task, which requires a reasonable-sized dataset for accurate assessment. While several datasets, readability indices (RI) and assessment models have been proposed for military agencies manuals, health documents, and early educational materials, studies related to the readability assessment of computer science literature are limited. To address this gap, we have contributed Computer science (CS) literature dataset <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AGREE</b> , comprising 42,850 learning resources(LR). We assessed the readability of learning objects(LOs) pertaining to domains of Computer Science (CS), machine learning (ML), software engineering (SE), and natural language processing (NLP). LOs consists of research papers, lecture notes and Wikipedia content of topics list of learning repositories for CS, NLP, SE and ML in English Language. From the statistically significant sample of LOs two annotators manually annotated LO’s text difficulty and established gold standard. Text readability was computed using 14 readability Indices (RI) and 12 lexical measures (LM). RI were ensembled, and readability measures were used to train the model for readability assessment. The results indicate that the extra tree classifier performs well on the AGREE dataset, exhibiting high accuracy, F1 score, and efficiency. We observed that there is no consensus among readability measures for shorter texts, but as the length of the text increases, the accuracy improves. The AGREE and SELRD datasets, along with the associated readability measures, provide a novel contribution to the field. They can be used to train deep learning models for readability assessment, develop recommender systems, and assist in curriculum planning within the domain of Computer Science. In the future, we plan to scale AGREE by adding more LOs and adding multimedia LOs. In addition, we would explore the use of deep learning methods for improved readability assessment.

Sistem Rekomendasi Content-based Filtering Menggunakan TF-IDF Vector Similarity Untuk Rekomendasi Artikel Berita

The population of active students in the Informatics Bachelor Program, Universitas Amikom Yogyakarta, in the odd semester of 2021 is 3,870. Efforts to track interest in the three concentration options were carried out early on through article literacy recommendations. Various articles are produced continuously and provided on an ongoing basis to students. However, the many articles offered daily make students overwhelmed and tend to choose articles that do not match what they want. To help solve this problem, recommender system is developed. A recommender system helps to estimate the prediction value or relevancy of an article and create a ranking according to user's taste. Content-based Filtering technique is used in this research. Using the dataset from Kabar Informatika news portal of University of Amikom Yogyakarta, the developed Content-based Filtering Recommendation System is able to produce Recall@5 score at around 73% and Recall@10 at around 80%.

Drug Recommendation from Diagnosis Codes: Classification vs. Collaborative Filtering Approaches.

Over time, large amounts of clinical data have accumulated in electronic health records (EHRs), making it difficult for healthcare professionals to navigate and make patient-centered decisions. This underscores the need for healthcare recommendation systems that help medical professionals make faster and more accurate decisions. This study addresses drug recommendation systems that generate an appropriate list of drugs that match patients' diagnoses. Currently, recommendations are manually prepared by physicians, but this is difficult for patients with multiple comorbidities. We explored approaches to drug recommendations based on elderly patients with diabetes, hypertension, and cardiovascular disease who visited primary-care clinics and often had multiple conditions. We examined both collaborative filtering approaches and traditional machine-learning classifiers. The hybrid model between the two yielded a recall at 5 of 76.61%, a precision at 5 of 46.20%, a macro-averaged area under the curve of 74.52%, and an average physician agreement of 47.50%. Although collaborative filtering is widely used in recommendation systems, our results showed that it consistently underperformed traditional classification. Collaborative filtering was sensitive to class imbalances and favored the more popular classes. This study highlighted challenges that need to be addressed when developing recommendation systems in EHRs.

A Learning Automata-Based Approach to Improve the Scalability of Clustering-Based Recommender Systems

One of the common techniques to reduce the scalability problem in collaborative filtering (CF)-based recommender systems is the clustering technique, which accelerates finding the nearest neighbor users in the recommendation process. Different clustering algorithms lead to improved accuracy and diversity in recommender systems. It is challenging to develop recommender systems based on clustering with decreasing scalability and simultaneously increasing accuracy. This article proposes a new clustering-based recommender system that takes into account the theoretical properties of the Learning Automata (LA) technique. The presented clustering novelty lies in the fact that employing LA technique for the user clustering in a CF-based recommender system has not been set forth so far in a way that addresses the scalability while improving accuracy. In addition, a novel similarity metric is embedded in the proposed algorithm to measure the similarity value between users. This metric is developed as like/dislike (LD) which can significantly improve the accuracy by reducing the computational cost. Extensive simulations have been performed on real-world datasets such as MovieLens and FilmTrust, which confirm the effectiveness of the proposed algorithm. In this regard, the proposed algorithm has improved the precision between 5 and 16% on average compared to the existing state-of-the-art methods such as GA-GELS, NUSCCF, NNMF, and KL-KM.

Real-Time Learning from an Expert in Deep Recommendation Systems with Application to mHealth for Physical Exercises.

Recommendation systems play an important role in today’s digital world. They have found applications in various areas such as music platforms, e.g., Spotify, and movie streaming services, e.g., Netflix. Less research effort has been devoted to physical exercise recommendation systems. Sedentary lifestyles have become the major driver of several diseases as well as healthcare costs. In this paper, we develop a recommendation system to recommend daily exercise activities to users based on their history, profiles and similar users. The developed recommendation system uses a deep recurrent neural network with user-profile attention and temporal attention mechanisms. Moreover, exercise recommendation systems are significantly different from streaming recommendation systems in that we are not able to collect click feedback from the participants in exercise recommendation systems. Thus, we propose a real-time, expert-in-the-loop active learning procedure. The active learner calculates the uncertainty of the recommendation system at each time step for each user and asks an expert for recommendation when the certainty is low. In this paper, we derive the probability distribution function of marginal distance, and use it to determine when to ask experts for feedback. Our experimental results on a mHealth and MovieLens datasets show improved accuracy after incorporating the real-time active learner with the recommendation system.

Movie Recommendation System Using Content-Based Filtering with Heroku Deployment

Abstract: Now days peoples watching movies to make their busy life calm , watching movie is not that easy as it takes a lot of time to select a movie due to large data set of movies exist in the world and it is very difficult and time consuming process to people to select a movie due to large data set but we can achieve this with the help of movie recommendation system using content based filtering ,where this recommendation system recommend a movie to the user based on the content he/she is watching. In this paper I am building a recommendation system using content- based filtering with Heroku deployment. Generally, recommendation systems are build using content -based filtering approach or collaborative filtering approach here in this paper I developed recommendation system using content-based filtering approach with Heroku Deployment. Heroku Deployment enables easy deployment of application.

THE PARTICIPATION OF UX DESIGNERS IN ARTIFICIAL INTELLIGENCE PROJECTS: RECOMMENDER SYSTEMS

With technological advances, artificial intelligence has gained prominence and we increasingly find innovative products on the market, bringing it as a differential. One example is machine learning-based recommender systems, which filter content in a personalized way for each user, saving the user's time and cognitive effort. Like any novelty, the professional market is still maturing, and users are learning to interact with interfaces. The performance of a UX designer becomes relevant to ensure a good user experience. Therefore, it is important to investigate the market to map the participation of the UX designer in the development of products that use a recommendation system. For this purpose, this research involved market professionals in interviews to understand the UX Designer's participation in developing recommendation systems based on machine learning and identified several relevant issues that point to the need to focus on human factors. It also indicates the training of professionals, the generation of content on the theme of AI/ML aimed at designers and working on the culture of companies.

New recommender system evaluation approaches based on user selections factor

Currently, due to the increasing importance of recommender systems (RSs), especially in the fields of social networking and e-commerce, these systems represent one of the most interesting subjects in computer programming. Although many research reports have previously been published in this subject area, because of lack of clarity regarding their algorithms or limited comparisons with the literature, most of them are difficult to extend for similar applications in the future. Therefore, in the present study, we have attempted to improve two novel RS evaluation measures (variety and newness) developed from previous evaluator rules (namely, diversity and novelty) based on human behavior so as to be more reliable and compatible with various developments in RSs. The new rules provide higher weighting for suggestions and respect for users' behavior and can be used in place of diversity and novelty rules with better precision and centralization, by 22.54% for variety and by 14.84% for newness. In addition, we aim to use the developed measures to improve new RSs and support better comparative analyses in this field in the future. This contribution is expected to facilitate better RS research and competition, especially in the social networking domain.

Rec-CFSVD++: Implementing Recommendation System Using Collaborative Filtering and Singular Value Decomposition (SVD)++

In recommender systems, Collaborative Filtering (CF) plays an essential role in promoting recommendation services. The conventional CF approach has limitations, namely data sparsity and cold-start. The matrix decomposition approach is demonstrated to be one of the effective approaches used in developing recommendation systems. This paper presents a new approach that uses CF and Singular Value Decomposition (SVD)[Formula: see text] for implementing a recommendation system. Therefore, this work is an attempt to extend the existing recommendation systems by (i) finding similarity between user and item from rating matrices using cosine similarity; (ii) predicting missing ratings using a matrix decomposition approach, and (iii) recommending top-N user-preferred items. The recommender system’s performance is evaluated considering Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Performance evaluation is accomplished by comparing the systems developed using CF in combination with six different algorithms, namely SVD, SVD[Formula: see text], Co-Clustering, KNNBasic, KNNBaseline, and KNNWithMeans. We have experimented using MovieLens 100[Formula: see text]K, MovieLens 1[Formula: see text]M, and BookCrossing datasets. The results prove that the proposed approach gives a lesser error rate when cross-validation ([Formula: see text]) is performed. The experimental results show that the lowest error rate is achieved with MovieLens 100[Formula: see text]K dataset ([Formula: see text], [Formula: see text]). The proposed approach also alleviates the sparsity and cold-start problems and recommends the relevant items.

Data-Driven Online Recommender Systems with Costly Information Acquisition

In numerous recommender systems, collecting useful information from users is costly, implying that the recommender system has to make active choices by simultaneously learning the observations of the features' states to make useful recommendations to users among available products and services. This paper integrates information acquisition decisions into recommender system. To solve the aforementioned dual learning problem, we propose two different algorithms, namely Sim-OOS and Seq-OOS, where observations are made simultaneously and sequentially, respectively. We prove that both algorithms guarantee a sub linear regret. The developed recommender system can be applied to a variety of real-world applications, including medical informatics, smart transportation, finance, and cyber-security where collecting information before making decisions results in an excessive cost. We validate and evaluate our proposed policies in a medical decision-support system that recommends tests and treatments for breast cancer patients.

СИСТЕМА ПРОЕКТИРОВАНИЯ ИНДИВИДУАЛЬНОЙ ОБРАЗОВАТЕЛЬНОЙ ТРАЕКТОРИИ СТУДЕНТА

The increasing rate of change of modern technologies generates not only significant transformations in existing professions, but also the emergence of new professions. A modern specialist, within the framework of solving his current tasks, should not only follow the trends in the development of his and related professional fields, but also improve his qualifications. The functionality of the developed recommendation system will allow forming an individual educational trajectory of a specialist (student) in accordance with his professional needs, interests and perception features.