Prompt-based and weak-modality enhanced multimodal recommendation

Users of popular services like Twitter and Facebook are often simultaneously overwhelmed with the amount of information delivered via their social connections and miss out on much content that they might have liked to see, even though it was distributed outside of their social circle. Both issues serve as difficulties to the users and drawbacks to the services.Social media service providers can benefit from understanding user interests and how they interact with the service, potentially predicting their behaviors in the future. In this paper, we address the problem of simultaneously predicting user decisions and modeling users' interests in social media by analyzing rich information gathered from Twitter. The task differs from conventional recommender systems as the cold-start problem is ubiquitous, and rich features, including textual content, need to be considered. We build predictive models for user decisions in Twitter by proposing Co-Factorization Machines (CoFM), an extension of a state-of-the-art recommendation model, to handle multiple aspects of the dataset at the same time. Additionally, we discuss and compare ranking-based loss functions in the context of recommender systems, providing the first view of how they vary from each other and perform in real tasks. We explore an extensive set of features and conduct experiments on a real-world dataset, concluding that CoFM with ranking-based loss functions is superior to state-of-the-art methods and yields interpretable latent factors.

Evaluation Of Recommendation System On A Movie Dataset

Recommender systems have proven to be a valuable way for online users to cope with the issues of information overload. They have become one of the most powerful and popular tools in electronic commerce as illustrated by Amazon.com, YouTube, Netflix, Yahoo, and IMDb. While recommender systems have shown significant contribution, they still suffer from the long-standing problems related to cold-start users and data-sparsity. This is due to the fact that recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. On the other hand, sentiment ratings of items which can be derived from online news services, blogs, social media or even from the recommender systems themselves are seen capable of providing better recommendations to user as opposed to tags alone. Sentiment-based model has been exploited in recommender systems to overcome the data-sparsity problem that exists in conventional recommender systems. Hence, embedding sentiment in recommender systems may significantly enhance the recommendation quality of recommender systems. Among the aims of this research is to integrate sentiment analysis in recommender systems particular to those items with no associated rating that commonly contribute to the problem of data-sparsity.

With the boom of social media, it is a very popular trend for people to share what they are doing with friends across various social networking platforms. Nowadays, we have a vast amount of descriptions, comments, and ratings for local services. The information is valuable for new users to judge whether the services meet their requirements before partaking. In this paper, we propose a user-service rating prediction approach by exploring social users' rating behaviors. In order to predict user-service ratings, we focus on users' rating behaviors. In our opinion, the rating behavior in recommender system could be embodied in these aspects: 1) when user rated the item, 2) what the rating is, 3) what the item is, 4) what the user interest that we could dig from his/her rating records is, and 5) how the user's rating behavior diffuses among his/her social friends. Therefore, we propose a concept of the rating schedule to represent users' daily rating behaviors. In addition, we propose the factor of interpersonal rating behavior diffusion to deep understand users' rating behaviors. In the proposed user-service rating prediction approach, we fuse four factors-user personal interest (related to user and the item's topics), interpersonal interest similarity (related to user interest), interpersonal rating behavior similarity (related to users' rating behavior habits), and interpersonal rating behavior diffusion (related to users' behavior diffusions)-into a unified matrix-factorized framework. We conduct a series of experiments in the Yelp dataset and Douban Movie dataset. Experimental results show the effectiveness of our approach.

Over the past decade, internet usage has grown rapidly, creating opportunities for various online businesses to expand. One of the most significant areas of growth is e-commerce. As more people shop online, recommendation systems have become essential. These systems personalize the user experience, help customers find products quickly, and boost sales for businesses. However, building an effective recommendation system comes with challenges, especially when handling large amounts of data. A recommendation system suggests products to users based on their interests. It identifies the right items by analyzing past purchases, browsing history, and product details. Many recommendation systems generate long lists of suggested items, ranking them based on predicted user preferences. Recommendations can be based on factors like price, location, wish-listed items, cart history, search history, and past purchases. A well-designed recommendation system improves customer satisfaction, increases sales, and enhances user engagement. This research will develop to create a recommendation system for both new and existing users. It will use Neighborhood-Based Collaborative Filtering to suggest products based on user ratings and past purchases. Additionally, the system will remove duplicate ratings to provide more accurate and relevant recommendations based on user interests.

Learning instrumental variable representation for debiasing in recommender systems.

Предметом вивчення в статті є процеси формування рекомендованого списку товарів та послуг в ситуації циклічного холодного старту рекомендаційної системи. Така ситуація характеризується циклічною зміною інтересів користувачів, що потребує уточнення вхідних даних для побудови рекомендацій. Метою є розробка методу доповнення вхідних даних для побудови рекомендацій непостійним користувачам, що змінюють свої вимоги, з використанням темпоральних обмежень типу «Next». Завдання: виділити базові особливості темпоральних залежностей в рекомендаційних системах; розробити концепцію коригування вхідних даних у ситуації циклічного холодного старту; розробити метод доповнення вхідних даних на основі темпоральних обмежень типу «Next». Отримані наступні результати. Виконано структуризацію темпоральних залежностей з урахуванням особливості їх застосування в рекомендаційних системах. Показано, що для опису поведінки користувача в таких системах можна використовувати залежності типу «Next» між послідовним у часі вибором одного й того ж об’єкту, а також залежності типу «Future» з проміжним вибором інших товарів або послуг. Запропоновано концептуальний підхід до уточнення вхідних даних на основі темпоральних залежностей. В рамках представленого концептуального підходу запропоновано метод доповнення вхідних даних рекомендаційної системи на основі формування темпоральних обмежень типу «Next». Висновки. Наукова новизна отриманих результатів полягає в наступному. Запропоновано метод доповнення вхідних даних рекомендаційної системи в ситуації циклічного холодного старту з використанням темпоральних обмежень типу «Next». Метод містить етапи узагальнення вхідних даних, формування темпоральних обмежень типу «Next», а також доповнення вхідних даних згідно отриманих обмежень. Запропонований метод дозволяє підвищити ефективність побудови рекомендацій для непостійних користувачів на основі формування обмежень, що відображають обов’язкові зміни інтересів відомих користувачів.

In this work, we present a proactive content based recommender system that employs web document clustering performed by using eye gaze data. Generally, recommender systems are used in commercial applications, where information about the user's habits and interests are of crucial importance in order to plan marketing strategies, or in information retrieval systems in order to suggest similar resources a user is interested in. Commonly, these systems use explicit relevance feedback techniques (e.g. mouse or keyboard) to improve their performance and to recommend products. In contrast, the proposed system permits to capture user's interest by using implicit relevance feedback, based on data acquired by an eye tracker Tobii T60. The purpose of the system is to collect eye gaze data during web navigation and, by employing clustering techniques, to suggest web documents similar to those that the user, implicitly, expressed greater interest. Performance evaluation was carried out on 30 users and the results show that the proposed system enhanced navigation experience in about 73% of the cases.

Click-through rate (CTR) prediction plays a critical role in recommender systems and other applications. Recently, modeling user behavior sequences attracts much attention and brings great improvements in the CTR field. Many existing works utilize attention mechanism or recurrent neural networks to exploit user interest from the sequence, but fail to recognize the simple truth that a user's real-time interests are inherently diverse and fluid. In this paper, we propose DisenCTR, a novel dynamic graph-based disentangled representation framework for CTR prediction. The key novelty of our method compared with existing approaches is to model evolving diverse interests of users. Specifically, we construct a time-evolving user-item interaction graph induced by historical interactions. And based on the rich dynamics supplied by the graph, we propose a disentangled graph representation module to extract diverse user interests. We further exploit the fluidity of user interests and model the temporal effect of historical behaviors using Mixture of Hawkes Process. Extensive experiments on three real-world datasets demonstrate the superior performance of our method comparing to state-of-the-art approaches.

The data sparsity problem significantly hinders the performance of recommender systems, as traditional models rely on limited historical interactions to learn user preferences and item properties. While incorporating multimodal information can explicitly represent these preferences and properties, existing works often use it only as side information, failing to fully leverage its potential. In this paper, we propose MDVT, a model-agnostic approach that constructs multimodal-driven virtual triplets to provide valuable supervision signals, effectively mitigating the data sparsity problem in multimodal recommendation systems. To ensure high-quality virtual triplets, we introduce three tailored warm-up threshold strategies: static, dynamic, and hybrid. The static warm-up threshold strategy exhaustively searches for the optimal number of warm-up epochs but is time-consuming and computationally intensive. The dynamic warm-up threshold strategy adjusts the warm-up period based on loss trends, improving efficiency but potentially missing optimal performance. The hybrid strategy combines both, using the dynamic strategy to find the approximate optimal number of warm-up epochs and then refining it with the static strategy in a narrow hyper-parameter space. Once the warm-up threshold is satisfied, the virtual triplets are used for joint model optimization by our enhanced pair-wise loss function without causing significant gradient skew. Extensive experiments on multiple real-world datasets demonstrate that integrating MDVT into advanced multimodal recommendation models effectively alleviates the data sparsity problem and improves recommendation performance, particularly in sparse data scenarios.

Expert assessments with pre-defined numerical or language terms can limit the scope of decision-making models. We propose that decision-making models can incorporate expert judgments expressed in natural language through sentiment analysis. To help make more informed choices, we present the Sentiment Analysis in Recommender Systems with Multi-person, Multi-criteria Decision Making (SAR-MCMD) method. This method compiles the opinions of several experts by analyzing their written reviews and, if applicable, their star ratings. The growth of online applications and the sheer amount of available information have made it difficult for users to decide which information or products to select from the Internet. Intelligent decision-support technologies, known as recommender systems, leverage users’ preferences to suggest what they might find interesting. Recommender systems are one of the many approaches to dealing with information overload issues. These systems have traditionally relied on single-grading algorithms to predict and communicate users’ opinions for observed items. To boost their predictive and recommendation abilities, multi-criteria recommender systems assign numerous ratings to various qualities of products. We created, manually annotated, and released the technique in a case study of restaurant selection using ‘TripAdvisor reviews’, ‘TMDB 5000 movies’, and an ‘Amazon dataset’. In various areas, cutting-edge deep learning approaches have led to breakthrough progress. Recently, researchers have begun to focus on applying these methods to recommendation systems, and different deep learning-based recommendation models have been suggested. Due to its proficiency with sparse data in large data systems and its ability to construct complex models that characterize user performance for the recommended procedure, deep learning is a formidable tool. In this article, we introduce a model for a multi-criteria recommender system that combines the best of both deep learning and multi-criteria decision-making. According to our findings, the suggested system may give customers very accurate suggestions with a sentiment analysis accuracy of 98%. Additionally, the metrics, accuracy, precision, recall, and F1 score are where the system truly shines, much above what has been achieved in the past.

In an era of information explosion, recommender systems are vital tools to deliver personalized recommendations for users. The key of recommender systems is to forecast users' future behaviors based on previous user-item interactions. Due to their strong expressive power of capturing high-order connectivities in user-item interaction data, recent years have witnessed a rising interest in leveraging Graph Neural Networks (GNNs) to boost the prediction performance of recommender systems. Nonetheless, classic Matrix Factorization (MF) and Deep Neural Network (DNN) approaches still play an important role in real-world large-scale recommender systems due to their scalability advantages. Despite the existence of GNN-acceleration solutions, it remains an open question whether GNN-based recommender systems can scale as efficiently as classic MF and DNN methods. In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy. Extensive experiments and ablation studies are presented to validate the effectiveness and scalability of the proposed algorithm. Our implementation based on PyTorch is available.

Social trust model for rating prediction in recommender systems: Effects of similarity, centrality, and social ties

Nowadays, virtual learning environments have become widespread to avoid time and space constraints and share high-quality learning resources. As a result of human–computer interaction, student behaviors are recorded instantly. This work aims to design an educational recommendation system according to the individual's interests in educational resources. This system is evaluated based on clicking or downloading the source with the help of the user so that the appropriate resources can be suggested to users. In online tutorials, in addition to the problem of choosing the right source, we face the challenge of being aware of diversity in users' preferences and tastes, especially their short-term interests in the near future, at the beginning of a session. We assume that the user's interests consist of two parts: (1) the user's long-term interests, which include the user's constant interests based on the history of the user's dynamic activities, and (2) the user's short-term interests, which indicate the user's current interests. Due to the use of Bilstm networks and their gradual learning feature, the proposed model supports learners' behavioral changes. An average accuracy of 0.9978 and a Loss of 0.0051 offer more appropriate recommendations than similar works.

Recent studies reveal that recommender systems are vulnerable to data poisoning attack due to their openness nature. In data poisoning attack, the attacker typically recruits a group of controlled users to inject well-crafted user-item interaction data into the recommendation model's training set to modify the model parameters as desired. Thus, existing attack approaches usually require full access to the training data to infer items' characteristics and craft the fake interactions for controlled users. However, such attack approaches may not be feasible in practice due to the attacker's limited data collection capability and the restricted access to the training data, which sometimes are even perturbed by the privacy preserving mechanism of the service providers. Such design-reality gap may cause failure of attacks. In this paper, we fill the gap by proposing two novel adversarial attack approaches to handle the incompleteness and perturbations in user-item interaction data. First, we propose a bi-level optimization framework that incorporates a probabilistic generative model to find the users and items whose interaction data is sufficient and has not been significantly perturbed, and leverage these users and items' data to craft fake user-item interactions. Moreover, we reverse the learning process of recommendation models and develop a simple yet effective approach that can incorporate context-specific heuristic rules to handle data incompleteness and perturbations. Extensive experiments on two datasets against three representative recommendation models show that the proposed approaches can achieve better attack performance than existing approaches.