About
114
Publications
30,430
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,704
Citations
Introduction
Currently, my research is focused on Data Science, Personalization, Recommender Systems. View my website for more information: http://www.yongzheng.me
Additional affiliations
August 2018 - present
August 2016 - August 2018
September 2010 - June 2016
Publications
Publications (114)
Recommender system has been demonstrated as one of the most useful tools to assist users' decision makings. Several recommendation algorithms have been developed and implemented by both commercial and open-source recommendation libraries. Context-aware recommender system (CARS) emerged as a novel research direction during the past decade and many c...
Recommender systems have been demonstrated as a useful tool in assisting decision makings. Multi-criteria recommender systems take advantage user preferences in multiple criteria to produce better recommendations. In this paper, we propose a utility-based multi-criteria recommendation algorithm, in which we learn the user expectations by different...
Recommender systems have been widely applied to several domains and applications to assist decision making by recommending items tailored to user preferences. One of the popular recommendation algorithms is the model-based approach which optimizes a specific objective to improve the recommendation performance. These traditional recommendation model...
Recent advances in recommender systems has demonstrated the effectiveness of deep learning in the process of developing recommendation algorithms. There are several existing open-source libraries for recommendation research, but not in the area of context-aware recommendations. Therefore, we develop and release DeepCARSKit which is an open-source a...
Recommender systems have been served to assist decision making by recommending a list of items to the end users. Multi-criteria recommender system (MCRS) is a type of recommender systems which enhance recommendation performance by taking user preferences on multiple criteria. Traditional algorithms for MCRS usually predict user ratings on these cri...
The analysis of scholarly literature can serve as a conduit for insight dissemination, comprehension, and trend discovery. By distilling complex datasets of scientific literature into exploratory, biblio-metric and visual analysis, researchers can unveil patterns, trends, and correlations that might otherwise remain obscured, fostering interdiscipl...
Grant applications constitute a fundamental responsibility of research faculty within a university setting. Faculty members frequently encounter queries pertaining to grant applications and award management, e.g., procedural guidelines and post-award issues. While FAQs offer general responses to common questions, they often fall short in addressing...
Extensive research has probed the impacts of personality traits on student satisfaction, academic anxiety, and performance, with particular attention paid to their implications during the COVID-19 pandemic. Notably, a conspicuous gap is discernible in the existing literature concerning investigations that scrutinize the influence of personality on...
ChatGPT, an implementation and application of large language models, has gained significant popularity since its initial release. Researchers have been exploring ways to harness the practical benefits of ChatGPT in real-world scenarios. Educational researchers have investigated its potential in various subjects, e.g., programming, mathematics, fina...
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments. This document provides a user guide for MOPO-LSI version 1.0, including problem setup, workflow and the hyper-parameters in configurations.
Recommender systems (RecSys) have found widespread use in a variety of applications, including e-commerce platforms like Amazon.com and eBay, online streaming services such as YouTube, Netflix, and Spotify, and social media sites like Facebook and Twitter. The success of these applications in improving user experience and decision making by providi...
Multi-criteria recommender systems can improve the quality of recommendations by considering user preferences on multiple criteria. One promising approach proposed recently is multi-criteria ranking, which uses Pareto ranking to assign a ranking score based on the dominance relationship between predicted ratings across criteria. However, applying P...
The influence of personality traits on educational outcomes has been widely recognized and studied. Research has explored its effects on factors such as student satisfaction, academic anxiety, and dishonesty, particularly during the COVID-19 pandemic. However, there has been a lack of studies comparing the learning behaviors and performance of stud...
With the development of recommender systems (RS), several promising systems have emerged, such as context-aware RS, multi-criteria RS, and group RS. However, the education domain may not benefit from these developments due to missing information, such as contexts and multiple criteria, in educational data sets. In this paper, we announce and releas...
Context plays an important role in the process of decision making. A user’s preferences on the items may vary from contexts to contexts, e.g., a user may prefer to watch a different type of the movies, if he or she is going to enjoy the movie with partner rather than with children. Context-aware recommender systems, therefore, were developed to ada...
Recommender systems have been successfully applied to alleviate overloaded information and assist decision making in various domains and applications. Recently, several new research directions emerged and novel techniques were proposed to advance the development of recommender systems. In this special issue, we invited authors to submit the revised...
Recommender systems can assist with decision-making by delivering a list of item recommendations tailored to user preferences. Context-aware recommender systems additionally consider context information and adapt the recommendations to different situations. A process of context matching, therefore, enables the system to utilize rating profiles in t...
Recommender systems (RecSys) have been well developed to assist user decision making. Traditional RecSys usually optimize a single objective (e.g., rating prediction errors or ranking quality) in the model. There is an emerging demand in multi-objective optimization recently in RecSys, especially in the area of multi-stakeholder and multi-task reco...
Recommender systems have been successfully applied to alleviate the problem of information overload and assist users’ decision makings. Multi-stakeholder recommender systems produce the item recommendations to the end user by considering the perspective of multiple stakeholders. Existing research on multi-stakeholder recommendations relies on the o...
Recommender systems have been successfully applied to assist decision making in multiple domains and applications. Multi-criteria recommender systems try to take the user preferences on multiple criteria into consideration, in order to further improve the quality of the recommendations. Most recently, the utility-based multi-criteria recommendation...
Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast amount of music available. However, many are not reliable as they may not take into account contextual aspects...
Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast amount of music available. However, many are not reliable as they may not take into account contextual aspects...
Personality traits have been demonstrated as one of the effective human factors in the process of decision making. Personality-aware recommendation models have been built for different applications. However, the models and research for educations are still under investigation. In this paper, we utilize the educational learning as a case study, expl...
Smartphones have become a popular target for cyberattacks. Malware can be embedded into the mobile applications. Several techniques have been proposed to alleviate these problems. However, these solutions may perform experiments by using simulated data, or may require root system privileges, or did not take advantage of the discovered patterns to b...
Abstract Recommender systems (RS) have been applied in the area of educations to recommend formal and informal learning materials, after-school programs or online courses. In the traditional RS, the receiver of the recommendations is the only stakeholder, but other stakeholders may be involved in the environment. Take educations for example, not on...
Recommender systems are able to produce a list of recommended items tailored to user preferences, while the end user is the only stakeholder in these traditional system. However, there could be multiple stakeholders in several applications domains (e.g., e-commerce, movies, music). Recommendations are necessary to be produced by balancing the needs...
As one of the most popular shared-economy industries, the bikesharing system allows the users to rent a bike from one location and return it to any other locations in their network. In this paper, we perform the statistical and predictive analysis on the bikesharing data in Washington, D.C. Our results discover different usage patterns by the regis...
Data analytics techniques are useful in understanding data, discovering patterns and building predictive models. Several curricula related to data analytics have been developed in worldwide Universities. As a practical curriculum, it is important to teach necessary tools or software for students to better learn data analytics. However, there could...
Artificial intelligence (AI) and data science have become one of the most popular curricula in the computing educations. Plenty of theories, optimizations and math are involved in these courses, which results in a higher degree of difficulty for students to learn, not to mention the students without specializations in computer science or informatio...
Taxi ride is still one of the most common and popular transportation methods, even if there are a lot of different options provided in a large city. In this paper, we utilize the taxi ride data in the city of Chicago, and analyze the factors that are influential in determining the fare of the taxi ride. We analyze the data and discover some interes...
Recommender systems are able to produce a list of recommended items tailored to user preferences, while the end user is the only stakeholder in the system. However, there could be multiple stakeholders in several applications or domains, e.g., e-commerce, advertising, educations, dating, job seeking, and so forth. Recommendations are necessary to b...
Recommender systems (RS) have served as an effective technology-enhanced learning technique in the learning area. Traditional RS only consider the preferences of the end user who is the receiver the recommendations. Multi-stakeholder recommender systems (MSRS) are recently proposed to balance the needs of multiple stakeholders in the recommender sy...
Recommender systems (RS) have been introduced to educations as an effective technology-enhanced learning technique. Traditional RS produce recommendations by considering the preferences of the end users only. Multi-stakeholder recommender systems (MSRS) claim that it is necessary to consider the utility of the items from the perspective of other st...
Recommender system is a well-known information system which can capture user tastes and produce item recommendations to the end users. Context-aware recommender systems (CARS) additionally take contexts (e.g., location, time, weather, etc) into consideration , and multi-criteria recommender systems (MCRS) utilize user preferences in multiple criter...
Recommender systems have been widely applied to produce recommendations tailored by user preferences. Context-aware recom-mender systems additionally take context information (such as time, location, weather, companion, etc) into consideration to generate better recommendations, due to the fact that user tastes may vary from contexts to contexts. I...
In the recommender systems, the receiver of the recommendations may not be the only stakeholder in the system, while others may come into play. For example, job positions cannot be simply recommended to a user according to his or her tastes only without considering the expectations of the recruiters. In this paper, we propose a utility-based recomm...
Having data from multiple sources, cross-domain and context-aware recommender systems, with the help of transfer learning approaches, aim to integrate such data to improve recommendation quality and alleviate issues such as cold-start problem. With the advantages of these techniques, we host the second international workshop on intelligent recommen...
Malicious activities in mobile applications may affect the mobile usages and even leave security concerns in the mobile applications. For example, they may drain the batteries, use up CPU or memories, increase bandwidth utilization, and even steal our information. In this paper, we analyze the Sherlock data to explore the patterns in mobile usage b...
Social media has been popular and powerful in the real-world applications. Facebook was even involved in the lawsuit in 2018 due to that social media data on Facebook was used to affect the presidential elections. In this work, we show case of how social tagging data is useful to predict the political trends by using the time-series analytical mode...
Personality, as one of the human factors, has been demonstrated as an influential factor in decision making. Particularly, personality traits can be utilized to identify decision leaders and followers in the context of group decision making. In this paper, we propose an approach to learn user roles (i.e., decision leaders and followers) to improve...
Traditional recommender systems suggest items by learning from user preferences, but ignore other stakeholders in the whole system. Actually, not only the receiver of the recommendations, but also other stakeholders may come into play, such as the producers of items or those of the system owners. Reciprocal recommender system in dating or job recom...
Recommender system has been demonstrated as a successful solution to assist decision makings. Context-awareness becomes necessity in recommendations, especially in mobile computing, since a user's decision may vary from contexts to contexts. Context-aware recommender systems, therefore, emerged to adapt the personalizations to different contextu-al...
Personality, as one of the human factors, has been demonstrated as an influential element in decision makings. Its impact in educational learning is still under investigation and there are very few of available data sets in this area. In this paper, we introduce one data that is collected from user studies, describe our exploratory analysis and dis...
Recommender Systems have been successfully applied to alleviate the information overload problem and assist the process of decision making. Collaborative ltering, as one of the most popular recommendation algorithms, has been fully explored and developed in the past two decades. However, one of the challenges in collaborative ltering, the problem o...
Collaborative filtering, as one of the most popular recommendation algorithms , has been well developed in the area of recommender systems. However , one of the classical challenges in collaborative filtering, the problem of " Grey Sheep " user, is still under investigation. " Grey Sheep " users is a group of the users who may neither agree nor dis...
Recommender systems have been widely applied to assist user's decision making by providing a list of personalized item recommendations. Context-aware recommender systems (CARS) additionally take context information into considering in the recommendation process, since user's tastes on the items may vary from contexts to contexts. Several context-aw...
The global climate change has been one of the serious problems in the 21 st century. In this paper, we analyze the correlations or patterns associated with the global temperature data, carbon-dioxide emission and the location information based on the latitude or longitude. We do nd some interesting patterns, especially the ones based on latitude or...
Cross-domain recommender systems and transfer learning approaches are useful to help integrate knowledge from different places, so that we alleviate some existing problems (such as the cold-start problem), or improve the quality of recommender systems. With the advantages of these techniques, we host the first international workshop on intelligent...
Recommender systems have been successfully applied to alleviate the information overload and assist user's decision makings. Emotional states have been demonstrated as eeective factors in recommender systems. However, how to collect or predict a user's emotional state becomes one of the challenges to build aaective rec-ommender systems. In this pap...
Recommender System has been successfully applied to assist user's decision making by providing a list of recommended items. Context-aware recommender system additionally incorporates contexts (such as time and location) into the system to improve the recommendation performance. The development of context-aware recommender systems brings a new oppor...
Recommender systems have been successfully applied to assist decision making by producing a list of item recommendations tailored to user preferences. Traditional recommender systems only focus on optimizing the utility of the end users who are the receiver of the recommendations. By contrast, multi-stakeholder recommendation attempts to generate r...
Context suggestion refers to the task of recommending appropriate contexts to the users to improve the user experience. The suggested contexts could be time, location, companion, category, and so forth. In this paper, we particularly focus on the task of suggesting appropriate contexts to a user on a specific item. We evaluate the indirect context...
Recommender systems (RSs) have been successfully applied to alleviate the problem of information overload and assist users' decision makings. Multi-criteria recommender systems is one of the RSs which utilizes users' multiple ratings on different aspects of the items (i.e., multi-criteria ratings) to predict user preferences. Traditional approaches...
Recommender systems (RSs) have been successfully applied to alleviate the problem of information overload and assist users' decision makings. Multi-criteria recommender systems is one of the RSs which utilizes users' multiple ratings on different aspects of the items (i.e., multi-criteria ratings) to predict user preferences. Traditional approaches...
Context-aware recommender systems (CARS) have been developed to adapt to users' preferences in different contextual situations. Users' emotions have been demonstrated as one of effective context information in recommender systems. However, there are no work exploring the effect of emotional reactions (or expressions) in the recommendation process....
Recommender systems are decision aids that offer users personalized suggestions for products and other items. Context-aware recommender systems are an important subclass of recommender systems that take into account the context in which an item will be consumed or experienced. In context-aware recommendation research, a number of contextual feature...
Recommender systems have been used in many domains to assist users' decision making by providing item recommendations and thereby reducing information overload. Context-aware recommender systems go further, incorporating the variability of users' preferences across contexts, and suggesting items that are appropriate in different contexts. In this p...
The problem of information overload can be summarized as the difficulty for users to make decisions (e.g., retrieve a document or purchase an item) which is actually caused by the presence of too much information, especially the Web information. Information retrieval and recommender systems have successfully alleviated this problem by either explor...
Context-aware recommender systems extend traditional recommenders by adapting
their suggestions to users' contextual situations. CARSKit is a Java-based
open-source library specifically designed for the context-aware recommendation,
where the state-of-the-art context-aware recommendation algorithms have been
implemented. This report provides the ba...
Recommender systems (RS) have been popular for decades and many novel types of RS have been proposed and developed, such as context-aware recommender systems (CARS) which additionally take contexts (e.g., time, location, occasion, etc) into consideration to further assist users' decision makings. Meantime, the emergence of CARS also brings new reco...
Context-aware recommender systems (CARS) take context into consideration when modeling user preferences. There are two general ways to integrate context with recommendation: contextual filtering and contextual mod-eling. Currently, the most effective context-aware recommendation algorithms are based on a contextual modeling approach that estimate d...
Context-aware recommender systems (CARS) go beyond traditional recommender systems, that only consider users' profiles, by adapting their recommendations also to users' contextual situations. Several contextual recommendation algorithms have been developed by incorporating context into recommendation algorithms in different ways. The most effective...
Context-aware recommender systems extend traditional rec-ommender systems by adapting their output to users' specific con-textual situations. Most of the existing approaches to context-aware recommendation involve directly incorporating context into standard recommendation algorithms (e.g., collaborative filtering, matrix fac-torization). In this p...
In contrast to traditional recommender systems, context-aware recommender systems (CARS) additionally take context into consideration and try to adapt their recommendations to users' different contextual situations. Several contextual recommendation algorithms have been developed by incorporating context into recommenders in different ways. Most of...
Context-aware recommender systems (CARS) emerged during recent years in order to adapt to users' preferences in different contextual situations. For example, users may choose different movies if they are going to see movies with their partners rather than with kids. The motivation behind is that users' preferences on items are always changing from...
In contrast to traditional recommender systems (RS), context-aware recommender systems (CARS) emerged to adapt to users' preferences in various contextual situations. During those years, different context-aware recommendation algorithms have been developed and they are able to demonstrate the effectiveness of CARS. However, this field has yet to ag...
Context-aware recommender systems (CARS) help improve the ef-fectiveness of recommendations by adapting to users' preferences in different contextual situations. One approach to CARS that has been shown to be particularly effective is Context-Aware Matrix Factorization (CAMF). CAMF incorporates contextual dependen-cies into the standard matrix fact...
Context-aware recommender systems (CARS) take contextual con-ditions into account when providing item recommendations. In recent years, context-aware matrix factorization (CAMF) has e-merged as an extension of the matrix factorization technique that also incorporates contextual conditions. In this paper, we intro-duce another matrix factorization a...
Context-aware recommender systems (CARS) have been demon-strated to be able to enhance recommendations by adapting users' preferences to different contextual situations. In recent years, sev-eral CARS algorithms have been developed to incorporated into the recommender systems. For example, differential context modeling (DCM) was modified based on t...
User and item splitting are well-known approaches to context-aware recommendation. To perform item splitting, multiple copies of an item are created based on the contexts in which it has been rated. User splitting performs a similar treatment with respect to user-s. The combination of user and item splitting: UI splitting, splits both users and ite...
Context-aware recommender systems (CARS) additionally take contexts into consideration and try to adapt users' preferences according to their contextual situations. In the traditional recommender systems (RS), latent factor models, such as matrix factorization and latent dirichlet allocation, have demonstrated their efficiencies. Apparently, contex...
Context-aware recommender systems try to adapt to users' pref-erences across different contexts and have been proven to provide better predictive performance in a number of domains. Emotion is one of the most popular contextual variables, but few researcher-s have explored how emotions take effect in recommendations – especially the usage of the em...