Recommender Systems Research Articles

Role of Explainable AI in Crop Recommendation Technique of Smart Farming

Smart farming is undergoing a transformation with the integration of machine learning (ML) and artificial intelligence (AI) to improve crop recommendations. Despite the advancements, a critical gap exists in opaque ML models that need to explain their predictions, leading to a trust deficit among farmers. This research addresses the gap by implementing explainable AI (XAI) techniques, specifically focusing on the crop recommendation technique in smart farming. An experiment was conducted using a Crop recommendation dataset, applying XAI algorithms such as Local Interpretable Model-agnostic Explanations (LIME), Differentiable InterCounterfactual Explanations (dice_ml), and SHapley Additive exPlanations (SHAP). These algorithms were used to generate local and counterfactual explanations, enhancing model transparency in compliance with the General Data Protection Regulation (GDPR), which mandates the right to explanation. The results demonstrated the effectiveness of XAI in making ML models more interpretable and trustworthy. For instance, local explanations from LIME provided insights into individual predictions, while counterfactual scenarios from dice_ml offered alternative crop cultivation suggestions. Feature importance from SHAP gave a global perspective on the factors influencing the model's decisions. The study's statistical analysis revealed that the integration of XAI increased the farmers' understanding of the AI system's recommendations, potentially reducing food insufficiency by enabling the cultivation of alternative crops on the same land.

On Enhancing E-Commerce Shipping Policies with Blockchain and Recommender Systems

On Enhancing E-Commerce Shipping Policies with Blockchain and Recommender Systems

Smartphone Recommendations Based on Specifications Using Fuzzy Tahani

Technology has become an integral part of people's lives, especially smartphones. Smartphones are needed nowadays because of their very complete functions and features. Due to the large number of users, manufacturers compete to create smartphones with various features and prices. Often, the large number of cell phones available makes users confused about choosing a smartphone. So calculations and comparisons are needed from various sides so that users don't make the wrong choice. Therefore, this research proposes a method of calculating and comparing smartphones based on fuzzy logic with the resistance method through a system created by researchers. These calculations and recommendations rely on information from market demand through researchers who are also smartphone market players, so they can provide recommendations that are quite accurate and by conditions that often occur in the market. With this recommendation system, users can easily search for the cellphone they want, coupled with the fuzzy logic calculation method, which makes this system's calculations more accurate, thereby preventing user choice errors. With this, users also get a comparison of recommendations that will help them choose the smartphone they want.

Study on a User Preference Conversational Recommender Based on a Knowledge Graph

In the era of information explosion, as a form of personalized recommendation, dialogue recommendation systems provide users with personalized recommendation services through natural language interaction. However, in the face of complex user preferences, the traditional dialogue recommendation system has the problem of a poor recommendation effect. To solve these problems, this paper proposes a user preference dialogue recommendation algorithm (KGCR) based on a knowledge graph, which aims to enhance the understanding of user preferences through the semantic information of the knowledge graph and improve the relevance and accuracy of recommendations. This paper proposes a personalized conversation recommendation algorithm framework for user preference modeling. The framework uses a bilinear model attention mechanism and self-attention hierarchical coding structure to model user preferences to rank and recommend candidate items. By introducing rich user-related information, the recommendation results are not only more in line with users’ individual preferences but also have better diversity, effectively reducing the negative impact of information cocoons and other phenomena. At the same time, the experimental results on the open dataset prove the effectiveness and accuracy of the proposed model in the personalized conversation recommendation task.

A Robust Recommender System Against Adversarial and Shilling Attacks Using Diffusion Networks and Self-Adaptive Learning

Shilling and adversarial attacks are two main types of attacks against recommender systems (RSs). In modern RSs, existing defense methods are hindered by the following two challenges: (1) the diversity of RSs’ information sources beyond the interaction matrix, such as user comments, textual data, and visual information; and (2) most defense methods are robust only against specific types of adversarial attacks. Ensuring the robustness of RSs against new adversarial attacks across different data sources remains an open problem. To address this problem, we propose a novel method that unifies adversarial attack detection, purification, and fake user detection in RSs by utilizing a guided diffusion adversarial purification network and a self-adaptive training technique. Our approach aims to simultaneously handle both known and unknown adversarial attacks on RSs’ inputs and outputs. We conducted extensive experiments on three large-scale datasets to evaluate the effectiveness of the proposed method. The results confirm that our method can effectively eliminate adversarial perturbations on images and textual content within RSs, surpassing state-of-the-art methods by a significant margin. Moreover, it achieved the best results in three out of five evaluated shilling attack types. Finally, for attacks with realistic magnitudes, it can maintain baseline performance levels even when multiple attacks are applied simultaneously.

Whom do Explanations Serve? A Systematic Literature Survey of User Characteristics in Explainable Recommender Systems Evaluation

Adding explanations to recommender systems is said to have multiple benefits, such as increasing user trust or system transparency. Previous work from other application areas suggests that specific user characteristics impact the users’ perception of the explanation. However, we rarely find this type of evaluation for recommender systems explanations. This paper addresses this gap by surveying 124 papers in which recommender systems explanations were evaluated in user studies. We analyzed their participant descriptions and study results where the impact of user characteristics on the explanation effects was measured. Our findings suggest that the results from the surveyed studies predominantly cover specific users who do not necessarily represent the users of recommender systems in the evaluation domain. This may seriously hamper the generalizability of any insights we may gain from current studies on explanations in recommender systems. We further find inconsistencies in the data reporting, which impacts the reproducibility of the reported results. Hence, we recommend actions to move toward a more inclusive and reproducible evaluation.

Implementing Knowledge Graphs and Ontologies For AI-Powered Recommendation System

Implementing Knowledge Graphs and Ontologies For AI-Powered Recommendation System

A Context-Aware Content Recommendation Engine for Personalized Learning using Hybrid Reinforcement Learning Technique

In the evolving landscape of e-learning, delivering personalized content that aligns with learners' needs and preferences is crucial. This study proposes a Context-Aware Content Recommendation Engine (CACRE) that utilizes a Hybrid Reinforcement Learning (HRL) technique to optimize personalized learning experiences. The engine incorporates learners' contextual data, such as learning pace, preferences, and performance, to deliver tailored recommendations. The proposed HRL model combines Deep Q-Learning for dynamic content selection and Policy Gradient Methods to adapt to individual learning trajectories. Experimental results demonstrate significant improvements in learner engagement, content relevance, and knowledge retention. This approach underscores the potential of context-aware recommendation systems to revolutionize personalized education by fostering adaptive and interactive learning environments.

AI-Driven Real Estate Portals: Enhancing Property Discovery and Buyer Experience

The rapid digital transformation of the real estate sector has led to the development of online platforms that streamline property listings, transactions, and user interactions. This paper presents the design and implementation of a Real Estate Website that enhances property discovery, buyer-seller communication, and transaction transparency. The platform integrates responsive web design, advanced search filters, interactive property visualization, and automated recommendation systems to improve user experience and engagement. Additionally, the study explores key technological advancements, including artificial intelligence (AI) for predictive analytics, geographic information systems (GIS) for location-based insights, and blockchain for secure transactions. A comparative analysis is conducted to evaluate the efficiency of digital platforms over traditional real estate practices. The results indicate that web-based real estate solutions significantly enhance accessibility, reduce operational costs, and improve decision-making for buyers, sellers, and real estate agents. Future work aims to incorporate virtual reality (VR) for immersive property tours and AI-driven price estimation models to further refine the user experience. This paper contributes to the growing body of research on technology-driven real estate solutions and highlights potential innovations in the field

Personalizing Multimedia Content Recommendations for Intelligent Vehicles Through Text–Image Embedding Approaches

The ability to automate and personalize the recommendation of multimedia contents to consumers has been gaining significant attention recently. The burgeoning demand for digitization and automation of formerly analog communication processes has caught the attention of researchers and professionals alike. In light of the recent interest and anticipated transition to fully autonomous vehicles, this study proposes a text–image embedding method recommender system for the optimization of personalized multimedia content for in-vehicle infotainment. This study leverages existing pre-trained text embedding models and pre-trained image feature extraction methods. Previous research to date has focused mainly on textual-only or image-only analyses. By employing similarity measurements, this study demonstrates how recommendation of the most relevant multimedia content to consumers is enhanced through text–image embedding.

Self-learning AI in Educational Research and Other Fields

There are several areas where self-learning AI is actively used. Machine learning and deep learning allow you to identify patterns and improve performance. Algorithms such as neural networks can adapt and improve based on experience. Self-learning GPTs are used to dialogue with humans. Computer vision recognizes and classifies images. Recommender systems analyze user preferences and offer personalized solutions. Adaptive robotic industrial control systems can optimize processes by adapting to changing conditions and data. Self-learning intelligent systems help detect and respond to new threats and attacks by analyzing network traffic and user behavior. These technologies continue to evolve, opening up new research opportunities for students in the field of education. Self-learning AI helps programs learn, draw conclusions, and use them in the future. Programming languages do not consider algorithms as data. Programs do not have access to themselves. To learn, you need to change, and for this you need to have access to your own code. Then self-learning becomes possible. By generating the logic of self-learning algorithms, they can improve the program, it becomes different from its source code, and these changes must be saved. The interpreter of the algorithm improves the intelligence of the program, and it becomes the author of optimal solutions. The programming language of self-learning algorithms Author allows students to form the logic of self-learning algorithms to create intelligent systems that can help them in research activities. These systems are able to independently improve their skills and accuracy without explicit programming for each new type of task.

Technology-Enabled Learning for Green and Sustainable Entrepreneurship Education

(1) Background and objectives: Global crises such as climate change, pandemics, and resource depletion present unprecedented challenges that require coordinated and innovative responses. This study advocates for a bottom-up strategy by proposing and developing tools that empower individuals and organizations to embrace green and sustainable entrepreneurship, fostering localized solutions with global impact. In this context, the research explored the integration of technology-enabled entrepreneurship education (EE) into engineering curricula, with a focus on sustainable and green entrepreneurship. Leveraging insights from European projects, the research developed a cloud-based entrepreneurship educational system featuring three e-learning platforms. Particularly, one e-learning platform was specifically designed to support green and sustainable entrepreneurship education. (2) Methods: the study involved literature reviews, stakeholder surveys, interviews with green entrepreneurs, and iterative platform design. (3) Results: Key outcomes of the research include a methodology for designing pedagogical strategies and learning content for green and sustainable EE. Additionally, digital tools such as the green business innovation canvas, TRIZ-inspired matrices, and AI-driven recommendation systems were created to equip learners with the skills to develop sustainable business models. (4) Originality: The study’s novelty lies in its integration of advanced digital tools with original pedagogical strategies, providing a scalable framework for incorporating sustainability into entrepreneurship education. These findings have practical implications for educators and policymakers working to promote eco-friendly business practices. Future research should investigate the scalability of these tools across diverse educational contexts and evaluate their long-term impact on fostering sustainable entrepreneurial mindsets.

Book recommendation services in the bibliographic activities of libraries

Book recommendation services, promptly reflecting the development of readers demands, are an important means of updating library funds. This study is devoted to the prospects for using Internet resources of this profile in library and bibliographic activities and has been carried out based on an electronic thematic collection of popular scientific literature posted on the website of the State Public Scientific and Technical Library of the Siberian Branch of the Russian Academy of Sciences. The authors analyze Russian and foreign publications on recommendation systems, consider their species classification in connection with the library and information sphere; propose an original definition of the term book recommendation service. Based on the results of the survey undertaken at the State Public Scientific and Technical Library of the Siberian Branch of the Russian Academy of Sciences, conclusion has been made that readers, while choosing scientific and educational literature, are in need not only for extended bibliographic information, but also for recommendation services available online.

Aspect-based currency of customer reviews: A novel probability-based metric to pave the way for data quality-aware decision-making

Customer reviews from digital platforms are a vital data resource for recommender and other decision support systems. The performance of these systems is highly dependent on the quality of the underlying data—particularly its currency. Existing metrics for assessing the currency of customer reviews are often based solely on data age. They do not consider that customer reviews can be outdated with respect to one aspect (e.g., guest room after renovation) while still being up-to-date with respect to others (e.g., location). Moreover, they disregard that customer reviews can only become outdated due to state changes of the corresponding item (e.g., renovation), which are associated with uncertainty. We propose a probability-based metric for the aspect-based currency of customer reviews. The values of the metric represent the probability that information in a set of customer reviews is still up-to-date. Our evaluation on a large TripAdvisor dataset shows that the values of the metric are reliable and discriminate well between up-to-date and outdated data, paving the way for data quality-aware decision-making based on customer reviews.

Towards Streamlining the Choice of Crossing Combinations in Plant Breeding by Integrating Model-Based Recommendations and Plant Breeder’s Preferences

Selecting crossing combinations crucial for successfully developing new improved crop varieties and genomic data from DNA markers have become invaluable for guiding plant breeders in evaluating and choosing promising crosses between potential parents. However, navigating the vast array of thousands of possible parental combinations, even with extensive genomic information, can be challenging, even for experienced breeders with deep knowledge of their crop’s gene pool. This case study aimed to evaluate the effectiveness of a recommender system to support plant breeders in this complex decision-making process. It took a retrospective approach, analyzing selection decisions made by an experienced breeder across several thousand potential crossing combinations over six years. The results indicated that a recommender system could significantly reduce the time and effort needed to identify promising crosses aligned with the breeder’s preferences. However, active feedback from the breeder to the recommender system appeared to be essential for achieving a satisfactory prediction. Integrating model-based recommendations and plant breeder’s preferences in a recommender system featuring such a reciprocal fine-tuning scheme, where the breeder actively provides feedback to the machine in the style of hybrid human–artificial intelligence, represents one step towards streamlining the choice of crossing combinations in plant breeding programs.

CTRL: Connect Collaborative and Language Model for CTR Prediction

Traditional click-through rate (CTR) prediction models convert the tabular data into one-hot vectors and leverage the collaborative relations among features for inferring the user’s preference over items. This modeling paradigm discards essential semantic information. Though some works like P5 and KAR have explored the potential of using Pre-trained Language Models (PLMs) to extract semantic signals for CTR prediction, they are computationally expensive and suffer from low efficiency. Besides, the beneficial collaborative relations are not considered, hindering the recommendation performance. To solve these problems, in this paper, we propose a novel framework CTRL , which is industrial-friendly and model-agnostic with superior inference efficiency. Specifically, the original tabular data is first converted into textual data. Both tabular data and converted textual data are regarded as two different modalities and are separately fed into the collaborative CTR model and pre-trained language model. A cross-modal knowledge alignment procedure is performed to fine-grained align and integrate the collaborative and semantic signals, and the lightweight collaborative model can be deployed online for efficient serving after fine-tuned with supervised signals. Experimental results on three public datasets show that CTRL outperforms the state-of-the-art (SOTA) CTR models significantly. Moreover, we further verify its effectiveness on a large-scale industrial recommender system.

A Blockchain-based Landslide Mitigation Recommendation System for Decision-Making

Landslides are catastrophic natural disasters that could threaten the structural integrity of a building, imposing hazards to engineering and human life. This study proposes a TOPSIS landslide disaster mitigation recommendation system integrated with blockchain. New approaches to data provenance, transparency, and informed decision-making are explored in the context of geospatial blockchain. The decision-making process is carried out using the multicriteria evaluation method, which considers soil stability, rainfall, vegetation density, proximity to rivers, and slope. The results yielded promising precision, recall, accuracy, and F1 scores (91%, 93%, 95%, and 95%, respectively), suggesting that the model could make accurate and impartial prioritization predictions. Blockchain ensures data transparency, immutability, and security, and TOPSIS ranks mitigation strategies from worst to best to determine the better solution. The proposed approach is essential to predict regions that are prone to landslides and enables the appropriate management of relaxation measures. This application of blockchain technology can provide trust, reliability, and speed in decision-making while reducing landslides.

Enhancing Recommendation Systems with Skew Deviation Bias for Shilling Attack Detection

Introduction: Recommender systems serve as a powerful tool to address the challenges of information overload by delivering personalized recommendations. However, their susceptibility to profile injection or shilling attacks poses a significant threat. Malicious entities can introduce fabricated profiles into the database of users to manipulate the popularity of specific items, subsequently influencing prediction outcomes Method: Detecting and mitigating the impact of such attacks is critical for preserving recommendation accuracy and user trust. The primary objective of this study is to develop an integrated framework for robust shilling attack detection and data sparsity mitigation in recommendation systems. This approach aims to make the system more resistant to manipulative attacks and improve recommendation quality, especially when dealing with limited data. In this paper, Skew Deviation Bias (SDB), is a novel metric that gauges the skewness within rating distributions, enabling the identification of both fabricated shilling profiles and the anomalous rating behaviors exhibited by attackers. Building upon this foundation, SDB is integrated with other statistical metrics like Rating deviation from the mean agreement (RDMA), Weighted deviation from the mean agreement (WDMA), Weighted degree of agreement (WDA), and length variance. This research investigates the impact of incorporating SDB alongside existing attributes in countering various attack scenarios, including random, average, and bandwagon attacks. Result: Extensive experiments are conducted to compare the effectiveness of SDB when integrated with existing attributes against scenarios employing only existing attributes. These experiments cover a range of attack sizes while maintaining a fixed 50% filler size. The results of thorough comparative analyses demonstrate the consistent superiority of the SDB-integrated approach, resulting in higher accuracy across all attack types compared to scenarios using only existing attributes. Notably, the random attack scenario shows the most significant accuracy improvement among the evaluated scenarios. Conclusion: The approach achieves a detection accuracy of 97.08% for random shilling attacks, affirming its robustness. Furthermore, in the context of data sparsity, the approach notably enhances recommendation quality.

ConvSeq-MF: Convo-Sequential Matrix Factorization for recommender system

In the domain of recommendation, the fusion of user historical preferences and item features has emerged as a promising field to enhance recommendation accuracy and mitigate the sparsity problem. This research presents a novel approach to recommendation systems by integrating both user and item content auxilary information. By harnessing the rich contextual data associated with users and items, our hybrid aproach ConvSeq-MF endeavors to provide more personalized and accurate recommendations. As the name indivates, it is based on a matrix factorization approach driven by joint venture of semantic and contextual information of both user’s and item’s. Series of experimentation on three real-world datasets shows the suggested methodology’s practicality and efficacy over otther baselines. To the best of our knowledge, the data demonstrate that the suggested model works better than other state of the art frameworks.

Gamispotify: a gamified social music recommendation system based on users’ personal values

Abstract In this article, we have introduced Gamispotify. For the first time, in a social network-based environment, and by benefiting from gamification and crowdsourcing, Gamispotify recommends music to the users based on their personal values. The proposed method has been compared to another published article by conducting two experiments and surveys on 32 application participants. Experimental results indicate that user engagement has significantly increased using the proposed method. Spending time on the application increased by 299.48%, the music play count increased by 150%, and receiving music recommendations increased by 244.41%. Statistical analysis using the Wilcoxon Signed-Rank Test confirmed these improvements were significant (p < 0.05). Moreover, survey results support these findings and show a notable increase in user satisfaction with the proposed music recommendation system compared with the previous work (p = 0.019). It also indicates that the proposed method successfully motivated users to discover new songs (p = 0.043). We have also found that social networking features, recommendations based on personal values, and gamification have positively impacted the users’ motivation to use the music streaming application.