Wenjun Zhou

University of Tennessee | UTK

Recent years have witnessed increased attention on peer-to-peer (P2P) lending, which provides an alternative way of financing without the involvement of traditional financial institutions. A key challenge for personal investors in P2P lending marketplaces is the effective allocation of their money across different loans by accurately assessing the...

Given a set of data objects, the problem of correlation computing is concerned with efficient identification of strongly-related ones. Existing studies have been mainly focused on static data. However, as observed in many real-world scenarios, input data are often dynamic and analytical results have to be continually updated. Therefore, there is th...

Discovering communities from social media and collaboration systems has been of great interest in recent years. Existing work show prospects of modeling contents and social links, aiming at discovering social communities, whose definition varies by application. We believe that a community depends not only on the group of people who actively partici...

The blockchain, a decentralized ledger system, has been considered a revolutionary technology to transform businesses, including the financial markets. As peer-to-peer (P2P) lending is also known for decentralization in the sense that individuals borrow from and lend to each other directly, bypassing traditional banks, we explore the possibility an...

Forecasting the analyst rating quality (ARQ), defined as whether a stock rating provided by an analyst can correctly foretell the stock movement, is crucial to fully leveraging the value of this information resource. This study develops a two-phase method to identify key predictors for ARQ forecasting. In the first stage, we conduct a thorough lite...

Previous research has demonstrated that referential communication tasks (RCTs) can be used to detect language deficits in people with Alzheimer’s Disease (AD). This study carried out a multi-modal vision-and-language analysis on data produced during RCT. Using the CLIP model, we calculated the association between the transcripts of image descriptio...

BACKGROUND Referential communication refers to one’s capacity to successfully describe a target object or an idea to a conversational partner. Previous research has demonstrated that referential communication tasks (RCTs) combined with natural language processing techniques can achieve superior performance of detecting communication deficits in peo...

Methods research has been a core part of the marketing discipline for over 50 years. Methods researchers provide tools both for academic researchers to explore marketing phenomenon and for marketing practitioners to better analyze commercial data. There are several reasons for the continuing relevance of methods research in marketing. First, in bot...

We propose NECA, a deep representation learning method for categorical data. Built upon the foundations of network embedding and deep unsupervised representation learning, NECA deeply embeds the intrinsic relationship among attribute values and explicitly expresses data objects with numeric vector representations. Designed specifically for categori...

As COVID-19 swept over the world, people discussed facts, expressed opinions, and shared sentiments about the pandemic on social media. Since policies such as travel restriction and lockdown in reaction to COVID-19 were made at different levels of the society (e.g., schools and employers) and the government, we build a large geo-tagged Twitter data...

Background: People with Alzheimer's disease (AD) often demonstrate difficulties in discourse production. Referential communication tasks (RCTs) are used to examine a speaker's capability to select and verbally code the characteristics of an object in interactive conversation. Objective: In this study, we used contextualized word representations...

This study aimed to develop a food systems knowledge and attitudes survey for college students. Sixty-eight initial items were generated. Items were removed after content and face validity, item analysis, and exploratory factor analysis. During confirmatory factor analysis, a 22-item, 2-factor structure was the best fit for the data (comparative fi...

Most loan evaluation methods in peer-to-peer (P2P) lending mainly exploit the borrowers’ credit information. However, the present study presents the maturity-based lender composition score, which exploits the investment capability of a group of lenders who fund the same loan, to enhance the P2P loan evaluation. More specifically, we extract lenders...

The loan evaluation is a fundamental task in peer-to-peer (P2P) lending. Effective loan evaluation can help lenders make informed investment decisions. Existing methods do not consider the return of loans in the core learning stage and thus fail to explore the relationship between the return of loans and their final loan payoff outcomes. In this st...

Unlike traditional loan scoring methods that rely solely on the borrower’s credit information, this paper presents a new indicator for loan scoring in peer-to-peer (P2P) lending. Our indicator exploits the investment capability of a group of lenders who fund the same loan, namely lender composition. More specifically, we extract lenders’ profiles i...

Objective This study aims to: (1) examine gender differences for weight conscious drinking among college students accounting for the broader phenomenon (e.g. including the Alcohol Effects dimension); and (2) longitudinally examine the effect of weight conscious drinking behaviors on body mass index (BMI). Participants: United States freshmen studen...

Classification problems, where the objective is to identify the class labels of given data points, are most often the subject of open contests, in which solvers compete for awards offered by solution seekers. Extant literature in open contests has studied both the winner‐takes‐all and top‐K award schemes, in which the award is granted to the best o...

Sellers of crop seeds need to plan for the variety and quantity of seeds to stock at least a year in advance. There are a large number of seed varieties of one crop, and each can perform best under different growing conditions. Given the unpredictability of weather, farmers need to make decisions that balance high yield and low risk. A seed vendor...

Because diet quality (DQ) is associated with risk of chronic disease and is a common construct assessed in health-related research, validated tools to assess DQ are needed that have low respondent and researcher burden. Thus, content experts develop the Short Healthy Eating Index (sHEI) tool and an associated scoring system. The sHEI scoring system...

Self-reported measures for body mass index (BMI) are considered a limitation in research design, especially when they are a primary outcome. Studies have found some populations to be quite accurate when self-reporting BMI; however, there is mixed research on the accuracy of self-reported measurements in adolescents. The aim of this study is to exam...

Background: Food insecurity affects millions of Americans and college students are especially vulnerable. Little is known about the relation of food insecurity with weight status and dietary intake during this critical phase of emerging adulthood. Objectives: We aimed to examine the sex-specific associations of food insecurity with obesity and d...

We enhance the mobile sequential recommendation (MSR) model and address some critical issues in existing formulations by proposing three new forms of the MSR from a multi-user perspective. The multi-user MSR (MMSR) model searches optimal routes for multiple drivers at different locations while disallowing overlapping routes to be recommended. To en...

Objective To describe process evaluation findings for a pilot sustainable food systems course. Use of Theory or Research The Value-Belief-Norm Theory, a pro-environmental behavior theory used to describe socially responsible behavior, was used. Process evaluation ensured theory-based learning outcomes were properly implemented and participants wer...

As the COVID-19 pandemic swept over the world, people discussed facts, expressed opinions, and shared sentiments on social media. Since the reaction to COVID-19 in different locations may be tied to local cases, government regulations, healthcare resources and socioeconomic factors, we curated a large geo-tagged Twitter dataset and performed explor...

Objectives This study aimed to assess the association between food insecurity and obesity and to examine whether it varies by sex. Methods A cross-sectional study was conducted in spring 2017 among college students from eight U.S. institutions. Participants (n = 683) completed the USDA Adult Food Security Survey and had their weight and height mea...

The KDD Cup has been a data science competition affiliated with the ACM SIGKDD conference with more than 20 years' tradition. In 2019, we organized the KDD Cup by hosting 3 parallel tracks, each with tremendous innovation. The regular machine learning (ML) track was a context-aware travel mode recommendation problem, sponsored by Baidu.com. The aut...

As emojis become prevalent in personal communications, people are always looking for new, interesting emojis to express emotions, show attitudes, or simply visualize texts. In this study, we collected more than 30 million tweets mentioning the word emoji in a 1-year period to study emoji requests on Twitter. First, we filtered out bot-generated twe...

Communicating scientific results with community partners is often lacking in intervention programs, thus eB4CAST was developed to facilitate impact sharing. This article investigated using the eB4CAST dissemination tool to communicate impact from a campus-based obesity prevention program. Data from Get Fruved RCT university sites collected at basel...

Objective: To examine health behavior and environmental perception differences among vegetarian and nonvegetarian students. Participants: First-year university students (n = 1078) from eight United States universities. Methods: Data were obtained from base 2015 and followup 2016 assessments. Vegetarians and nonvegetarians were compared for anthropo...

With the popularity of social networking services, big social data analytics emerged in various applications, such as discovering trending topics, monitoring public sentiment, and identifying human mobility patterns. In this paper, we take the opportunity of The 2017 Great American Eclipse, a once-in-a-lifetime event, to look into its potential soc...

Gardening has been positively associated with fruit and vegetable (FV) consumption based on short-term studies among children, but long-term data among adolescents and young adults are lacking. This investigation sought to elucidate the association between gardening experience and FV intake among college students over a two-year period. Students (N...

Objective: To examine the effect of weight-conscious drinking and compensatory behavior temporality on binge drinking frequency of college freshmen. Participants: Freshmen (n = 1149) from eight US universities, Fall 2015. Methods: Participants completed the Compensatory Eating Behaviors in Response to Alcohol Consumption Scale and Alcohol Use Diso...

The objective was to determine if cooking skills and meal planning behaviors are associated with greater fruit and vegetable intake and lower body mass index (BMI) in first-year college students who are at risk for excessive weight gain. A cross-sectional analysis was conducted using baseline data from a multi-state research project aimed at preven...

Background Self-reported measures for body mass index (BMI) are considered a limitation in research design, especially when they are a primary outcome. Studies have found some populations to be quite accurate when self-reporting BMI; however, there is limited research on the accuracy of self-reported measurements in adolescents. Objective The purp...

Background Food insecurity is a growing concern among US higher education institutions. Research is needed to understand the impact of food insecurity on food choice priorities when designing interventions for college students. Objective To examine the factors that influence decisions about food between food secure (FS) and food insecure (FI) coll...

Objective To describe the current outcomes of the Get Fruved project. Description Get Fruved is a social marketing and environmental change intervention seeking to prevent unwanted weight gain among high school and college students. The intervention, a non-diet approach focusing on increasing healthy diet choices, physical activity, and stress man...

Abstract Background College students may be vulnerable to food insecurity due to limited financial resources, decreased buying power of federal aid, and rising costs of tuition, housing, and food. This study assessed the prevalence of food insecurity and its sociodemographic, health, academic, and food pantry correlates among first-year college stu...

In real-time bidding (RTB) systems for display advertising, a demand-side platform (DSP) serves as an agent for advertisers and plays an important role in competing for online advertising spaces by placing proper bidding prices. A critical function of a DSP is formulating proper bidding strategies to maximize key performance indicators, such as num...

As emojis become prevalent in personal communications, people are always looking for new, interesting emojis to express emotions, show attitudes, or simply visualize texts. In this study, we collected more than thirty million tweets mentioning the word “emoji” in a one-year period to study emoji requests on Twitter. First, we filtered out bot-gener...

Objective: This study used a multi-phase, multiple-method design to gather both quantitative and qualitative data from participants regarding the product, pricing, and promotional strategies associated with a potential intervention for a healthful vending snack product. Methods: Cognitive interviews were conducted in two phases – Phase 1 (explorato...

Background: Workplace or campus wellness/obesity-prevention policies and initiatives can improve health. Research tools to assess worksite or campus policies/initiatives are scarce. Thus, the aim of this research is to develop and validate the policies, opportunities, initiatives, and notable topics (POINTS) audit. Methods: POINTS was developed and...

Discovering hidden patterns under unexpected market shocks is a significant and challenging problem, which continually attracts attention from research communities of mathematics, economics, and data science. Classic financial pricing models present unsatisfactory prediction accuracy when applied to real-world data due to limited capacity in depict...

Understanding citywide transit patterns is important for transportation management, including city planning and route optimization. The wide deployment of automated fare collection (AFC) systems in public transit vehicles has enabled us to collect massive amounts of transit records, which capture passengers’ traveling activities. Based on such tran...

Within lifestyle behavior research, the sex of populations causes differences in behaviors and outcomes of studies. This cross-sectional study investigated lifestyle behavior patterns in college students, examining sex differences in four areas: Nutrition, physical activity, sleep, and stress. Data from over 1100 college freshmen across 8 United St...

The purpose of this convergent, multiphase, mixed methods study was to better understand the perceptions of adolescents’ food environments and related food behaviors using grounded visualization and story mapping. Adolescents from one high school (13–16 years) in the southeastern United States were evaluated via data from health behavior surveys (n...

Self-reported height and weight, if accurate, provide a simple and economical method to track changes in body weight over time. Literature suggests adults tend to under-report their own weight and that the gap between self-reported weight and actual weight increases with obesity. This study investigates the extent of discrepancy in self-reported he...

This study assessed food choice priorities (FCP) and associations with consumption of fruits and vegetables (FV), fiber, added sugars from non-beverage sources, and sugar-sweetened beverages (SSB) among college students. Freshmen from eight U.S. universities (N = 1149) completed the Food Choice Priorities Survey, designed for college students to pr...

The classic mobile sequential recommendation (MSR) problem aims to provide the optimal route to taxi drivers for minimizing the potential travel distance before they meet next passengers. However, the problem is designed from the view of a single user and may lead to overlapped recommendations and cause traffic problems. Existing approaches usually...

Cars of the future have been predicted as shared and electric. There has been a rapid growth in electric vehicle (EV) sharing services worldwide in recent years. For EV-sharing platforms to excel, it is essential for them to offer private charging infrastructure for exclusive use that meets the charging demand of their clients. Particularly, they n...

The objective of this study was to determine the relationship between neck circumference (NC) and other anthropometric measures and examine cut-off points for males and females according to existing waist circumference cut-off levels in this age group. Across 8 universities, 1562 students underwent a physical assessment. Spearman rho correlations (...

Massive data collected by automated fare collection (AFC) systems provide opportunities for studying both personal traveling behaviors and collective mobility patterns in urban areas. Existing studies on AFC data have primarily focused on identifying passengers' movement patterns. However, we creatively leveraged such data for identifying pickpocke...

Objective/Introduction Lengthy surveys have the potential to burden users and can lead to inaccuracies. Conducting analyses to shorten existing validated surveys is beneficial. The objective, therefore, was to shorten the Pittsburgh Quality Sleep Index (PSQI) for young adults. Methods PSQI data from 1246 college students were used. An exploratory...

Given a large transactional database, correlation computing/association analysis aims at efficiently finding strongly correlated items. For traditional association analysis, relationships among variables are usually measured at a global level. In this study, we investigate confounding factors that can help to capture abnormal correlation behaviors...

With the rapid growth in smartphone usage, it has been more and more important to understand the patterns of mobile data consumption by users. In this paper, we present an empirical study of the correlation between user mobility and app usage patterns. In particular, we focus on users' moving speed as the key mobility metric, and try to answer the...

Understanding factors that influence food choice may help improve diet quality. Factors that commonly affect adults’ food choices have been described, but measures that identify and assess food choice factors specific to college students are lacking. This study developed and tested the Food Choice Priorities Survey (FCPS) among college students. Th...

Background Gardening interventions have been shown to increase fruit and vegetable (F/V) intake among school-aged children. It is unknown whether these effects persist into later adolescence or adulthood, and little is known about whether gardening in later adolescence is related to F/V intake. Objective To identify the relationship between both c...

Objective: We developed and tested a College Environmental Perceptions Survey (CEPS) to assess college students' perceptions of the healthfulness of their campus. Methods: CEPS was developed in 3 stages: questionnaire development, validity testing, and reliability testing. Questionnaire development was based on an extensive literature review and...

The prevalence of mobile apps has greatly changed people's lives, generating myriads of data and creating new research opportunities. By exploiting mobile apps’ data, existing studies have primarily investigated app users’ usage patterns. Few studies have focused on profiling the geospatial distributions of individual apps’ usage patterns on a larg...

With advances in vehicle-to-vehicle communication, future vehicles will have access to a communication channel through which messages can be sent and received when two get close to each other. This enabling technology makes it possible for authenticated users to send queries to those vehicles of interest, such as those that are located within a geo...

IoT (Internet of Things) deployments have been used in many diverse applications in increasingly large numbers, usually composed of embedded sensors, computational units, and actuators. One central problem with IoT applications is that we frequently need to query the number of nodes according to certain requirements, or filters. For example, a user...

Sparse representation has been a powerful technique for modeling high-dimensional data. As an unsupervised technique to extract sparse representations, sparse coding encodes the original data into a new sparse code space and simultaneously learns a dictionary representing high-level semantics. Existing methods have considered local manifold within...

Objective: The study purpose was to identify clusters of weight-related behaviors by sex in a college student populations. Methods: We conducted secondary data analysis from online surveys and physical assessments collected in Project Young Adults Eating and Active for Health (YEAH) with a convenience sample of students on 13 college campuses in...

Objectives. This research addresses the questions: what does online content reveal that should be analyzed when trying to explore co-creation of value?; How could that content be analyzed?; Why should these conversations be analyzed to enhance the overall value produced by the ecosystem containing consumers and brands? Methodology. We look at cas...

With the development of sensor technology and embedded systems, building large-scale, low-cost sensor networks, which is a critical step to facilitating the application of pervasive sensing in the future, becomes possible. One of the major challenges in developing sensor network applications is to improve the execution efficiency of programs runnin...

Background Neck circumference is a novel method for estimating upper‐body subcutaneous adipose tissue distribution. Studies have concluded that neck circumference is a potentially useful, simple, non‐invasive, cost‐effective initial screening tool for overweight/obesity and the metabolic syndrome. Objective The objective of this study was to deter...

BACKGROUND Social media may be a useful tool in modifying health‐related behaviors; however, there is limited research on college students' use of health‐related social media and whether those behaviors vary by gender. METHODS Incoming first year students at eight universities were invited to complete screening surveys to determine if they were el...

Objective To determine baseline wellness characteristics of students participating in a community‐based participatory research intervention to reduce obesity among college students. Methods An online‐based survey was offered during the first four weeks of the Fall 2016 semester. The survey was available to all students, however freshmen received a...

The study objectives were to determine if there was an association between intention to breastfeed and accuracy of body size estimation (BSE) among a sample of nulliparous undergraduate females, and to explore other potential explanatory factors, should such a relationship be detected. Female figure drawings from Gardner and Jappe's Body Image Asse...

Introduction Obesity is recognized as a worldwide public health concern. It is most commonly assessed and classified using Body Mass Index (BMI). Historical data says that adults tend to under‐report their own weight and that the gap between self‐reported weight and actual weight increases with obesity. Few studies have examined how well young adul...

Background College students often do not consume the recommended amounts of beans and legumes. To develop interventions aimed at improving the intake of beans and legumes in the college population, more information is needed on the behaviors, environment, attitudes, and nutrition knowledge (B.E.A.N.) of college students regarding beans. Validated t...

Constructing a graph to represent the structure among data objects plays a fundamental role in various data mining tasks with graph-based learning. Since traditional pairwise distance-based graph construction is sensitive to noise and outliers, sparse representation based graphs (e.g., ℓ1-graphs) have been proposed in the literature. Although ℓ1-gr...

The purpose of this study was to assess the prevalence of food insecurity among college freshmen and its association with health and academic outcomes. A cross-sectional research design was used to analyze the food security status of college freshmen (n = 859) at the end of their first academic year (April–May 2015). Freshmen from 8 colleges in the...

Eliminating or reducing skill gaps in the job market is critical to putting people back to work, reducing the unemployment rate, and increasing the labor market participation rate. A key element in closing the skills gap is accurately identifying the mismatch between the skills expected by employers and those possessed by job seekers. In this study...

In this paper, we analyze a variety of influence factors for the spreading pattern of forest fires. Rules of these crucial factors are expressed with cellular automata (CA), which has powerful simulation capacity. Specifically, we analyze the influence of combustible materials, wind, temperature, and terrain. We implement a CA Forest Fire Forecast...

Massive data collected by automated fare collection (AFC) systems provide opportunities for studying both personal traveling behaviors and collective mobility patterns in the urban area. Existing studies on the AFC data have primarily focused on identifying passengers' movement patterns. In this paper, however, we creatively leveraged such data for...

Sparse representation has been a powerful technique for modeling image data and thus enhance the performance of image clustering. Sparse coding, as an unsupervised way to extract sparse representation, learns a dictionary that represents high-level semantics and the new representations on the dictionary. Though existing sparse coding schemes are co...

The objective of this study was to examine sleep hours (SH) and perceived stress (PS) levels in college students. Freshmen, sophomore, junior and senior college students (n=280) from four land‐grant, public universities (Florida, South Dakota, Tennessee and West Virginia) where enrolled in the “Get Fruved” research study and trained via two multi‐u...