Content-based Recommendation Research Articles

Hybrid Recommendation System for e-Pharmacy

In the ever-evolving field of recommendation systems, the importance of providing users with precise and personalized suggestions cannot be understated. This paper delves into the realm of medicine recommendation and explores the use of hybrid recommendation algorithms, combining content-based and collaborative filtering techniques. The study prioritizes content-based recommendation using cosine similarity and Singular Value Decomposition (SVD) while emphasizing their effectiveness in recommending medicines with similar formulae. The proposed hybrid approach leverages a rich dataset from Kaggle and integrates user-friendly features, linking to popular online pharmaceutical platforms. By analyzing the architecture and design, this paper demonstrates the superiority of hybrid filtering in the context of medicine recommendation

Sistema de Recomendación de Cursos en Línea basado en el Perfil de Competencias TIC del Docente

Digital transformation in education has created the need to train teachers and improve their digital competencies. However, training processes are often ineffective due to the lack of personalization in the proposals and the variety in teacher profiles. Given this, this article addresses the development of a web tool designed to diagnose teachers’ digital competencies and provide personalized recommendations for MOOCs to support the development of their skills. To achieve this, a system that uses Natural Language Processing (NLP) techniques and a content-based recommendation model is proposed. Course data is obtained through web scraping and processed with NLP techniques, using an advanced language model (BERT) to generate vector representations of the courses and competencies. The web system allows teachers to self-assess their competencies, visualize the results, and receive personalized recommendations for MOOCs. The implementation of this system has proven effective in identifying teachers’ areas for improvement and suggesting relevant courses for their professional development. The results suggest that the use of this system can be an effective solution for training teachers in digital competencies.

Integrated sentiment analysis with BERT for enhanced hybrid recommendation systems

Recommendation systems play a crucial role in assisting users by providing personalized suggestions based on their preferences. However, these systems often face challenges such as data sparsity, cold start user issues, and overlooking the critical aspect of user sentiment. To address these limitations, this study integrates sentiment analysis into recommendation systems using a dataset from Yelp, focusing on two domains: restaurants and hotels. We conduct preprocessing tasks to facilitate sentiment analysis and leverage the power of BERT, achieving an accuracy rate of 90% for the restaurant domain and 87% for the hotel domain. We then incorporate the sentiment analysis component into collaborative filtering, utilizing model-based deep matrix factorization, and significantly reduce the root mean square error (RMSE) to 0.1 for the restaurant domain and 0.1186 for the hotel domain. Additionally, we integrate sentiment analysis into content-based recommendation using clustering, resulting in improved recommendations with a higher silhouette score of 0.533 for the restaurant domain and 0.42 for the hotel domain. To further enhance system performance, we propose a novel approach that combines these sentiment-aware components using NMF with DecisionTreeRegressor, achieving an even lower RMSE of 0.02 for the restaurant domain and 0.01 for the hotel domain. This integration of sentiment analysis into the recommendation system demonstrates its effectiveness in improving accuracy and personalization, providing users with more meaningful and relevant recommendations based on their sentiments. However, challenges such as data sparsity, cold start problems for new users, and other limitations remain, warranting further research to mitigate these challenges for a more robust recommendation system.

The role of recommendation algorithms in driving the development of e-commerce platforms

Given the rapid development of e-commerce, recommendation algorithms play a crucial role in enhancing user experience and promoting platform growth. This paper delves into the application of recommendation algorithms within e-commerce platforms, scrutinizes the advantages and disadvantages of collaborative filtering, content-based recommendation, and hybrid recommendation models, and elucidates how these algorithms can enhance user stickiness, improve conversion rates, and promote the overall growth of platforms through personalized recommendations. Through empirical case studies, the author demonstrates how recommendation algorithms can optimize the user shopping experience and enable e-commerce platforms to differentiate themselves in a fiercely competitive market. This research not only aids e-commerce platforms in improving operational efficiency and market competitiveness but also provides valuable practical insights and theoretical support for the fields of data science and artificial intelligence.

Enhancing user experience: a content-based recommendation approach for addressing cold start in music recommendation

Enhancing user experience: a content-based recommendation approach for addressing cold start in music recommendation

Analysis on recommendation systems based on ML and DL approaches

The explosive growth of the Internet has led to an unprecedented increase in available information, creating a major challenge in identifying content that aligns with user interests. Recommendation systems (RS) address this challenge by providing personalized content recommendations based on user behavior and preferences. This article systematically reviews the evolution of recommendation systems with a focus on the methodologies of machine learning (ML) and deep learning (DL). It highlights core technologies in ML-based RS, such as content-based recommendation, collaborative filtering (CF), and hybrid filtering (HF). The article evaluates the effectiveness of various DL models, including autoencoders (AE), convolutional neural networks (CNN), and recurrent neural networks (RNN). The review also addresses key challenges faced by RS, such as cold start issues and the need for improved model transparency and interpretability. DL methods are shown to significantly enhance recommendation accuracy by leveraging complex patterns in large-scale data, to improve the user experience. Future research directions include refining data preprocessing, enhancing feature engineering, compressing and accelerating DL models, and improving interpretability through advanced mechanisms. This study provides valuable insights and references for researchers aiming to advance recommendation system design and performance optimization.

Research on movie recommendation algorithms based on machine learning

In recent years, the number of movies released worldwide has grown exponentially. Due to the large number of movies, it is difficult for users to find movies that match their preferences. Therefore, with the development of Internet technology, it has become an important research direction how to filter out the movies that users are interested in from the massive movie data. This paper mainly focuses on the film recommendation algorithms based on machine learning, including the traditional collaborative filtering algorithm, rating-based sorting recommendation algorithm and content-based recommendation algorithm. By conducting a detailed analysis of the principles, advantages and disadvantages, as well as application scenarios of these recommendation algorithms, this paper aims to identify methods that best fit current movie recommendation systems. The objective is to improve the real-time and personalized recommendation, while providing users with better film recommendation services.

Marvel Movie Recommendation System Using Hybrid Item-Based and Content-Based Filtering Methods

Currently, there are so many movie genres available to the general public, making it difficult for viewers to choose a movie. One of the most popular movies is the “Marvel Movies” or MCU (Marvel Cinematic Universe), which has become the highest grossing franchise of all time with 90 movies released. The large number of movie titles makes it difficult for people to choose which movie to watch. Therefore, a Marvel movie recommendation system is needed using a hybrid item-based and content-based filtering method. The content-based method calculates the similarity between movies by identifying similar Marvel movies based on content such as genre, actor, director, and synopsis. Meanwhile, item-based completes content-based recommendations by considering user preferences. The reason for using the hybrid item-based and content-based filtering method is to be able to produce more accurate recommendations than a single method. The types and sources of data used are secondary data from journals and the internet (Imdb and Movielens), as well as datasets about Marvel movies. From the results of testing the hybrid model, the precision value is 0.8 or 80% which indicates that the model is accurate. In item-based filtering testing, the similarity result of 0.68 shows good item similarity. In the content-based filtering test, the highest similarity is 0.14 and the lowest similarity is 0.10 which shows that the similarity between the searched content and the generated content is relevant.

A cutting-edge artificial intelligence paradigm for entertainment-infused music recommendations

Personalized and fascinating music recommendations are becoming increasingly in demand as the advent of technology continues to change the way that people consume music. Traditional music recommendation systems primarily rely on user listening history and preferences, often neglecting the emotional and experiential dimensions that make music a deeply personal and entertaining endeavour. This research introduces a music recommendation system after classifying the tracks using a novel Gravitational Search Optimized Recursive Neural Networks (GS-RNN) approach. GS-RNN addressed this gap by integrating the Gravitational Search Algorithm (GSA) with Recursive Neural Networks (RNN) to create a content-based recommendation system that assesses audio signal similarity. Evaluation metrics, including accuracy (80%), logarithmic loss (0.85), precision (84%), recall (83%), and F1-score (88%), demonstrate GS-RNN’s superiority over existing techniques. Genre-specific accuracy analysis further underscores the model’s capability to suggest songs within the same genre. Overall, GS-RNN presents a novel and effective paradigm for music recommendations.

Beyond the Hype : Building a Personalized Movie Experience with Content-Based Recommendation

This review paper provides a detailed analysis of how a movie recommendation system based on content was planned, executed and evaluated using Streamlit framework. The exponential expansion of digital content has led to the need for efficient recommendation systems, particularly in the realm of movies. In this respect, the proposed recommender system utilizes cosine similarity computations and content-based filtering methods to offer personalized film suggestions relying upon various features such as genres, keywords, castings as well as crews. The author further illustrates rigorous data preparation methods which encompass feature engineering, data collection and cleaning techniques. Furthermore, various other data sources such as TMDb API have been integrated to obtain detailed information about movies. The system, after a thorough study, shows that it has the ability of offering personalized movie recommendations that improve user engagement and experience. This paper examines broader implications of recommendation algorithms and argues their importance for improving happiness and content discovery in digital entertainment platforms. It also raises some common issues encountered during system development and advocates further research work aimed at enhancing recommendation algorithms and making them more flexible and scalable. In this way, it advances our understanding on how personalized content delivery can be applied to shape the landscape of digital entertainment through unmasking the complexities of recommendation systems.

A review of challenges, algorithms and evaluation methods in news recommendation

News reading is an important social activity and to help readers quickly find news articles of their interest, news content providers and aggregators use recommender systems. Such systems are designed to address a variety of challenges. Inspiration for algorithmic design is taken from various domains which has resulted in the creation of an enormous body of literature. Also, different methods are used for evaluation of the recommendation algorithms. In this study, we review these developments and present three major components in news recommendation research. First, we list and categorise the challenges faced while designing news recommender systems. We especially list the different algorithmic designs used for generating personalised and non-personalised recommendations. We discuss the major neural network architectures that are being increasingly used for both collaborative and content-based recommender systems. Next, we list the two major evaluation methods and also list some popular datasets used in evaluation. Finally, we identify the emerging trends in news recommender research. We find that the issues related to fake news, trust and use of personal data for news recommendation are gaining wider attention, and deep learning methods are being increasingly used to address these issues.

Enhanced Content-Based Recommendation Using Topic Modelling and Knowledge Graph

Content-based (CB) recommendation algorithms recommend items to a user based on items the user liked in the past. CB methodologies have gained attention due to their higher accuracy and transparency and the emergence of new technologies, such as knowledge graphs (KGs), advances in natural language processing (NLP), and sentiment analysis. While most previous studies have mainly focussed on the use of term frequency-inverse document frequency (TF-IDF) and other related enhancements, little work can be found on using KGs in CB recommendations. This paper presents an enhancement of the conventional CB recommendation by incorporating KGs for a movie domain. The graph is constructed using the MovieLens data set, which is augmented with additional features such as actors, directors, and genres. Furthermore, the graph is expanded by incorporating topics derived from latent dirichlet allocation (LDA) extraction. Using the KGs, the proposed approach enhances user profiles by leveraging the interconnected user-movie relationship within a graph structure. The results of the experiments showed that the proposed approach exceeded the tested baselines in terms of precision, recall, and F-score metrics.

Comprehensive Travel Companion: A Hybrid Recommendation and Route Planning System for Globetrotting

This paper presents a comprehensive AI-powered travel companion system designed to enhance the travel experience for globetrotters. Leveraging cutting-edge artificial intelligence (AI) techniques, the system combines image recognition, recommendation algorithms, and route planning functionality to provide personalized travel recommendations and seamless navigation. The integration of collaborative filtering, content-based recommendation, and real-time route optimization algorithms ensures that users receive tailored suggestions and efficient travel routes based on their preferences, interests, and current context. The architecture, implementation details, and evaluation of the proposed system are discussed, highlighting its effectiveness in facilitating immersive and enjoyable travel experiences. Keywords: Travel Companion, Recommendation Systems, Route Planning, Image Recognition, Collaborative Filtering, Content-Based Recommendation, Dijkstra's Algorithm.

Paper Recommendation Method based on Attention Mechanism and Graph Neural Network

At present, most recommendation technologies only consider text or citation information, which suffers from data sparseness and cold start problems. Therefore, an academic paper recommendation method based on attention mechanism and heterogeneous graph CAH is proposed. This method considers textual information and heterogeneous graph structure information to obtain a richer and more complete feature representation. Finally, cosine similarity is calculated to generate recommendations. The results show that compared with the content-based recommendation method, the accuracy rate, recall rate and f value of CAH method are increased by nearly 5.6%, 5.8% and 8.7%, respectively, which are significantly improved compared with the basic method. This method is expected to promote the in-depth application of recommendation systems in the field of artificial intelligence.

Personalized multi-attribute recommendation method based on partial order set

With the rapid development of big data and continuous optimization of online shopping platforms, personalized recommendation has become a standard feature of recommendation methods. In order to effectively provide personalized recommendations to customers, improve recommendation accuracy, and customer satisfaction, it is necessary to consider customers’ preferences for multiple product attributes when making product recommendations. However, existing recommendation methods require precise calculation of product attribute weights, which is computationally expensive, complex, and often results in unstable weight values. This paper proposes a multi-attribute recommendation method based on consumer decision preference information that overcomes the need for weights and reflects personalized customer preferences. Based on the acquisition of customer product attribute preference sequences, a partial order relation for recommended products is constructed using partial order set theory. Finally, the recommended products are determined through the partial order Hasse diagram, where the top layer elements of the Hasse diagram represent the recommended product set. This method addresses challenges that traditional content-based recommendations cannot overcome. The experiment in this paper uses a dataset of 30,000 records from Beeradvocate beer reviews. The experimental results show that, compared to traditional multi-attribute recommendation methods, this method only requires decision-maker preference information to complete product recommendations, requiring less information and having lower computational costs, resulting in more robust results.

Research on the Recommendation System of Music e-learning Resources with Blockchain based on Hybrid Deep Learning Model

Learners are confronted with an ever-growing array of diverse and complex educational resources as music education increasingly moves to online platforms. Traditional resource curation methods, which rely heavily on educators, fall short of meeting the dynamic needs of modern students. To address this issue, we present a novel recommendation system for music e-learning resources that combines the power of blockchain technology with a hybrid deep learning model. Our model combines blockchain's robust security and transparency features with advanced deep learning algorithms, enhancing the personalization and efficiency of resource recommendations. A backpropagation neural network with K nearest neighbor classification, traditional collaborative filtering (CF), and an improved CF algorithm are used in the hybrid approach. For the back propagation neural network algorithm, K nearest neighbor classification algorithm, traditional collaborative filtering (CF) and improved CF algorithm, the accuracy rate of improved CF algorithm is higher, reaching 95%. Comparing the proposed model with the association rule-based recommendation model and the content-based recommendation model, the model constructed in this study received high evaluation from experts, with an average score of 98, and more than 97% of them gave a high score of 95 or more, and the evaluation of experts tended to be consistent. Overall, the model proposed in this study can make better recommendations for music education learning resources and bring users a good learning experience, so this study has some practical application value. This research demonstrates a highly effective, blockchain-enhanced recommendation system for music e-learning resources. Our model has significant practical value and potential for adoption in online music education platforms because it provides tailored educational content and an enhanced learning experience.

Knowledge-Aware Explainable Reciprocal Recommendation

Reciprocal recommender systems (RRS) have been widely used in online platforms such as online dating and recruitment. They can simultaneously fulfill the needs of both parties involved in the recommendation process. Due to the inherent nature of the task, interaction data is relatively sparse compared to other recommendation tasks. Existing works mainly address this issue through content-based recommendation methods. However, these methods often implicitly model textual information from a unified perspective, making it challenging to capture the distinct intentions held by each party, which further leads to limited performance and the lack of interpretability. In this paper, we propose a Knowledge-Aware Explainable Reciprocal Recommender System (KAERR), which models metapaths between two parties independently, considering their respective perspectives and requirements. Various metapaths are fused using an attention-based mechanism, where the attention weights unveil dual-perspective preferences and provide recommendation explanations for both parties. Extensive experiments on two real-world datasets from diverse scenarios demonstrate that the proposed model outperforms state-of-the-art baselines, while also delivering compelling reasons for recommendations to both parties.

Attributes Relevance in Content-Based Music Recommendation System

The possibility of recommendations of musical songs is becoming increasingly required because of the millions of users and songs included in online databases. Therefore, effective methods that automatically solve this issue need to be created. In this paper, the mentioned task is solved using three basic factors based on genre classification made by neural network, Mel-frequency cepstral coefficients (MFCCs), and the tempo of the song. The recommendation system is built using a probability function based on these three factors. The authors’ contribution to the development of an automatic content-based recommendation system are methods built with the use of the mentioned three factors. Using different combinations of them, four strategies were created. All four strategies were evaluated based on the feedback score of 37 users, who created a total of 300 surveys. The proposed recommendation methods show a definite improvement in comparison with a random method. The obtained results indicate that the MFCC parameters have the greatest impact on the quality of recommendations.

Research on the Design of Intelligent Recommendation System for Civic and Political Education Content and the Effectiveness Assessment of Students’ Acceptance

Abstract The article improves the traditional collaborative filtering algorithm, integrates it with the content-based recommendation algorithm, proposes the recommendation algorithm based on the mixture of collaborative filtering and content, and serves as the operation logic for designing the intelligent recommendation system of educational content for Civics class. Model variables are determined using structural equation modeling and relevant hypotheses are presented to construct a model of factors that influence student acceptance of the Civics Intelligent Recommendation System, followed by empirical analysis. The mean values of expectation performance, effort performance, social influence, convenience conditions, self-efficacy, perceived pleasantness, and willingness to use are 3.48, 2.70, 3.61, 2.36, 3.77, 3.84, and 3.73, respectively. Students’ use of the Civic Intelligent Recommendation System is greatly influenced by their perception of pleasantness and self-efficacy. The questionnaire has good reliability and validity in general. The initial model has valid hypotheses H1, H2, H6, H7, H8, H9, H10, and H11. In the analysis of variance, there were significant differences between genders only in performance expectations (0.000) and perceived pleasantness (0.016). Significant differences existed across grades in terms of performance expectations (0.018) and social influence (0.000). The measurement dimension of willingness to use had a moderating effect across majors. Hypotheses H12 and H13 are partially valid, but H14 is valid.

Exploring the Communication Path of Civic Education in Cyberspace Using Data Mining Technology

Abstract A recommendation algorithm is a specific application of data mining technology, which is an important means to expand the dissemination of Civics education in cyberspace. The elbow method is employed in this paper to determine the best number of clusters to cluster the Civics course evaluation dataset and finish preprocessing large-scale data. Aiming at the problem of different importance of rating bias between items, the traditional Slope One algorithm is optimized by comprehensively considering the relationship between the number of common ratings and the similarity between items and the prediction results. The optimized Slope One algorithm is used to perform one round of prediction and fill the scoring matrix to solve the data sparsity problem and improve prediction accuracy and stability. The optimized algorithm reduces by 8.56% compared to the user-based collaborative filtering algorithm, 5.83% compared to the item-based collaborative filtering algorithm, and 5.25% compared to the content-based recommendation algorithm, with a significant improvement in accuracy, recall, and F1 value. The four hypothesis validations indicate that the diversity, personalization, and accuracy of resource recommendations all have positive effects on the dissemination effect of civic education. The recommendation algorithm’s dissemination effect score in this paper is 3.781, which is significantly superior to the dissemination effect of Civic Education.