Preference Amplification in Recommender Systems

Personalized recommendation benefits users in accessing contents of interests effectively. Current research on recommender systems mostly focuses on matching users with proper items based on user interests. However, significant efforts are missing to understand how the recommendations influence user preferences and behaviors, e.g., if and how recommendations result in echo chambers. Extensive efforts have been made in examining the phenomenon in online media and social network systems. Meanwhile, there are growing concerns that recommender systems might lead to the self-reinforcing of user's interests due to narrowed exposure of items, which may be the potential cause of echo chamber. In this paper, we aim to analyze the echo chamber phenomenon in Alibaba Taobao --- one of the largest e-commerce platforms in the world.

To improve the experience of consumers, all social media, commerce and entertainment sites deploy Recommendation Systems (RSs) that aim to help users locate interesting content. These RSs are black-boxes – the way a chunk of information is filtered out and served to a user from a large information base is mostly opaque. No one except the parent company generally has access to the entire information required for auditing these systems – neither the details of the algorithm nor the user-item interactions are ever made publicly available for third-party auditors. Hence auditing RSs remains an important challenge, especially with the recent concerns about how RSs are affecting the views of the society at large with new technical jargons like “echo chambers”, “confirmation biases”, “filter bubbles” etc. in place. Many prior works have evaluated different properties of RSs such as diversity, novelty, etc. However, most of these have focused on evaluating static snapshots of RSs. Today, auditors are not only interested in these static evaluations on a snapshot of the system, but also interested in how these systems are affecting the society in course of time. In this work, we propose a novel network-centric framework which is not only able to quantify various static properties of RSs, but also is able to quantify dynamic properties such as how likely RSs are to lead to polarization or segregation of information among their users. We apply the framework to several popular movie RSs to demonstrate its utility.

E-commerce Recommender Systems suggest useful and interesting products to customers in order to increase user satisfaction and online conversion rates. They typically exploit explicit or implicit user feedback such as ratings, buying records or clickstream data and apply statistical methods to derive recommendations. Collaborative filtering is one of the most widely used approaches in recommender systems. However, the traditional collaborative filtering methods compute users’ similarities in the dimension of products, and they do not take the influence of neighbor users into consideration when computing such similarities. This paper focuses on explicitly formulated user requirements as the sole type of user feedback. The new collaborative filtering method based on user interests’ transmission. This method computes customers’ similarities in the dimension of interests, and takes the interests transmission between different customers into reflection. This method not only can cope with cold start problem and data sparse problem, but also have prediction precision.

Causal graph, as an effective and powerful tool for causal modeling, is usually assumed as a Directed Acyclic Graph (DAG). However, recommender systems usually involve feedback loops, defined as the cyclic process of recommending items, incorporating user feedback in model updates, and repeating the procedure. As a result, it is important to incorporate loops into the causal graphs to accurately model the dynamic and iterative data generation process for recommender systems. However, feedback loops are not always beneficial since over time they may encourage more and more narrowed content exposure, which if left unattended, may results in echo chambers. As a result, it is important to understand when the recommendations will lead to echo chambers and how to mitigate echo chambers without hurting the recommendation performance. In this paper, we design a causal graph with loops to describe the dynamic process of recommendation. We then take Markov process to analyze the mathematical properties of echo chamber such as the conditions that lead to echo chambers. Inspired by the theoretical analysis, we propose a Dynamic Causal Collaborative Filtering ($\partial$CCF) model, which estimates users' post-intervention preference on items based on back-door adjustment and mitigates echo chamber with counterfactual reasoning. Multiple experiments are conducted on real-world datasets and results show that our framework can mitigate echo chambers better than other state-of-the-art frameworks while achieving comparable recommendation performance with the base recommendation models.

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.

Recommender systems play an important role in most modern e-commerce applications. They have allowed users to become aware of the myriad choices available to them. The ease of information and the abundance of options have helped users make educated decisions. A recommender system studies a user's preferences and continues learning the user's changing interests, so as to suggest items that incline with the user's interests. In cases where a user is new to the application, or the user prefers not to discourse preferences, the recommender system is unable to gather the user's preference on any item. This is called the cold start problem; wherein the system can make valid recommendations only once the user starts informing the system about his/her choices. In this paper, we discuss the challenges faced by the cold start problem and how this problem may be alleviated using social media. We suggest an approach where we collect public information from users' social media accounts and analyze this information to understand their preferences. In particular, we gather the new user's information using their Twitter profile; i.e., the user's interest and preferences are extracted from his/her Twitter profile by analyzing his/her tweets. These interests will help the system understand what kind of movies the user will be most interested in. We compare these preferences with the metadata about the individual items. Using this approach, we develop a movie recommendation system wherein we produce top-N movie recommendations for a user. We used the MovieTweetings dataset to model the application. Two sets of results have been produced. In the first, smaller set of 770 users, 72.67% of users have received 100% accurate movie recommendations while nearly 80% of users got more than 75% accuracy. For the second, larger set of more than 3,500 users, 53 % of users have received 100% accurate recommendations while 72% of users got more than 75% accuracy. These encouraging results have demonstrated that the approach is effectively in alleviating cold start problems in recommendation systems, and may be applicable to many other e-commerce applications.

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

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.

In today's information-rich environment, recommendation systems play a pivotal role in helping users efficiently navigate vast amounts of data, with applications spanning online platforms, e-commerce, streaming services, and digital advertising. Among various algorithms, Thompson Sampling (TS) stands out for its ability to balance exploring new options with leveraging known preferences, thereby preventing recommendation stagnation and adapting to shifts in user interests. This paper investigates TS within the context of advertising and movie recommendations, exploring its Bayesian probabilistic foundation, uncertainty modeling, practical integration within recommendation architectures, handling of large-scale data streams, and real-time feedback mechanisms. Performance is evaluated through metrics including accuracy, user engagement, click-through rates, and conversion rates, with comparisons against ETC and UCB algorithms. Results demonstrate that TS enhances recommendation accuracy, user satisfaction, and system revenue, establishing its position as a valuable and versatile tool for improving modern recommendation systems. Furthermore, the study provides insights into practical deployment strategies for real-world applications.

Recommender systems (RSs) have become pillars of personalization in contemporary retail that is improving customer experience and business value. With the help of sophisticated algorithms, retailers will be able to offer personalized product recommendations taking into account the personal preferences of consumers and thus minimizing the information overload and making decisions more easily. Most recommender systems are based on two major approaches, which are Collaborative Filtering (CF) and Content-Based Filtering (CBF). Unlike CBF which pays attention to item attributes and individual interactions of a user to create an item, CF examines user behaviors and preferences of a population to determine the relevant items. The hybrid models unify these two methods in an attempt to ease their disadvantages, which include cold-start, sparsity, and lack of diversity. In addition to the development of algorithms, combination of deep learning and diversification methods has also contributed to the relevance, novelty, and adaptability of recommendations. This review explores the application of recommender system in retail with an overview of the principles of CF and CBF, their contribution to customer engagement, and the latest trends in hybrid and AI-driven recommendation systems. This paper synthesizes the main body of research to show the potential transformational nature of personalized recommendations in maximizing customer satisfaction, loyalty, and revenue generation and outlining the challenges and future research opportunities to further enhance the use of personalized recommendations in retail.

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.

In order to identify a user's personal preference in navigating the Web or to recommend collected Web information, it is very useful to analyze the user's Web-browsing behavior. However, it is difficult to determine which Web-browsing behaviors are influential on predicting a user's interest because each individual has his/her own habit and personal manner in surfing the Web and locating documents of interest. In this study, we propose an adaptive personalized recommender system based on a preference-thesaurus constructed by learning a user's Web-browsing behavior. The major components of the proposed recommender system are the Web-browsing behavior monitor, preference-thesaurus constructor, relevant document recommender, and user feedback learner. The adaptive nature of the proposed system allows the personalization of recommendation and the identification of the ever-changing influential Web-browsing behaviors. A proof-of-concept system is implemented and experiments are performed to verify the system's capability to personalize recommendation and to learn through user's feedbacks.

Traveling to other locations for pleasure, business, or other reasons is called tourism. In every sort of recommender system, there are a certain amount of users and items. Creating a recommendation systems is made more difficult by the abundance of information available online and the high volume of website visits. A recommender system pulls the user's preferences or interests from relevant data sets to reduce information overload. This calls for the development of a new recommended system that will deliver higher-quality recommendations for massive data sets. To solve these kinds of problems, we have found several approaches for making recommendations, including three different types: content-based filtering, collaborative filtering, and hybrid filtering. With each type of recommender system, this research also analyses several algorithms. The main aim of this paper is to review several trends and techniques currently being used in tourist recommender systems.

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.

This study aims to explore an artificial intelligence (AI) based red culture content production and recommendation system, and analyze how the system can effectively improve users’ contact frequency, cognitive depth, satisfaction and participation in red culture content, as well as promote users’ positive emotional responses. Through regression analysis and correlation analysis of 759 valid questionnaires, this study verified four core research hypotheses: AI recommendation system can significantly increase users’ exposure to red cultural content; enhance the depth of users’ cognition of red culture; increase user satisfaction and engagement; and eliciting positive emotional responses from users. The results show that personalized recommendation mechanisms play a key role in improving user experience, while strengthening the emotional resonance of content can significantly improve user engagement and communication willingness. In addition, this study also puts forward suggestions such as optimizing the algorithm of the recommendation system, multi-channel operation, and establishing a continuous monitoring and evaluation mechanism, so as to further improve the intelligent communication effect of red cultural content. This study provides theoretical and empirical support for the intelligent dissemination of red culture, and has important practical significance and academic value for the use of AI technology to promote red culture.