Xuan Lu

Xuan Lu

Auto-generated profile, based on publicly available information

Xuan Lu

The University of Arizona, Tucson, AZ, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 January 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
XLXuan Lu
Xuan Lu
WAWei Ai
Wei Ai
ZCZhenpeng Chen
Zhenpeng Chen
YCYanbin Cao
Yanbin Cao
QMQiaozhu Mei
Qiaozhu Mei
Emotions at work have long been identified as critical signals of work motivations, status, and attitudes, and as predictors of various work-related outcomes. When more and more employees work remotely, these emotional signals of workers become harder to observe through daily, face-to-face communications. The use of online platforms to communicate and collaborate at work provides an alternative channel to monitor the emotions of workers. This paper studies how emojis, as non-verbal cues in online communications, can be used for such purposes and how the emotional signals in emoji usage can be used to predict future behavior of workers. In particular, we present how the developers on GitHub use emojis in their work-related activities. We show that developers have diverse patterns of emoji usage, which can be related to their working status including activity levels, types of work, types of communications, time management, and other behavioral patterns. Developers who use emojis in their posts are significantly less likely to dropout from the online work platform. Surprisingly, solely using emoji usage as features, standard machine learning models can predict future dropouts of developers at a satisfactory accuracy. Features related to the general use and the emotions of emojis appear to be important factors, while they do not rule out paths through other purposes of emoji use.

1 January 2022 in Journal of Functional Foods
Verified
Journal Article
Open access
Yiping TangYiping Tang
Yiping Tang
YYYuanyuan Yang
Yuanyuan Yang
XLXuan Lu
Xuan Lu
QLQiuchen Liu
Qiuchen Liu
QLQiaohong Li
Qiaohong Li
YWYefu Wang
Yefu Wang

14 November 2023 in ACM Transactions on the Web
Verified
Journal Article
Open access
FLFuqi Lin
Fuqi Lin
XLXuan Lu
Xuan Lu
WAWei Ai
Wei Ai
HLHuoran Li
Huoran Li
YMYun Ma
Yun Ma
XLXuanzhe Liu
Xuanzhe Liu
Modern technology innovations feature a successive and even recurrent procedure. Intervals between old and new generations of technology are shrinking, and the Internet and Web services have facilitated the fast adoption of an innovation even before the convergence of its predecessor. While the adoption and diffusion of innovations have been studied for decades, most theories and analyses focus on single and one-time innovations. Meanwhile, limited work has investigated successive innovations while lacking user-level analysis, possibly due to the unavailability of fine-grained adoption behavior data. In this study, we present the first large-scale analysis of the adoption of recurrent innovations in the context of mobile app updates, investigating how millions of users consume various versions of thousands of apps on their mobile devices. Our analysis reveals novel patterns of crowd and individual adoption behaviors, which suggest the need for new categories of adopters to be added on top of the Rogers model of innovation diffusion. We show that standard machine learning models are able to pick up various sources of signals to predict whether users in these different categories will adopt a new version of an app and how soon they will adopt it.

29 July 2016 in EURASIP Journal on Advances in Signal Processing
Verified
Journal Article
Open access
PDF file
XLXuan Lu
Xuan Lu
DWDingwen Wang
Dingwen Wang
WSWenxuan Shi
Wenxuan Shi
DDDexiang Deng
Dexiang Deng
Recently, sparse representation has been successfully used in single image super-resolution reconstruction. Unlike the traditional single image super-resolution methods such as image interpolation, the super-resolution with sparse representation reconstructs image with one or several constant dictionaries learned from external databases. However, the contents can vary significantly across different patches in a single image, and the fixed dictionaries cannot suit for every patch. This paper presents a novel approach for single image super-resolution based on sparse representation, which uses group as the basic unit, and trains dictionary with external database and the input low-resolution image itself for each group to ensure that the dictionary is suitable for the patches in the group. Simultaneous sparse coding algorithm is used to accelerate the processing and improve the result. Extensive experiments on natural images show that our method achieves better results than some state-of-the-art algorithms in terms of both objective and human visual evaluations.

4 November 2025 in The Gerontologist
Verified
Journal Article
Closed access
XXXiaoling Xiang
Xiaoling Xiang
XLXuan Lu
Xuan Lu
XGXiwen Guan
Xiwen Guan
Background and Objectives: This study predicted psychological resilience among older adults during the COVID-19 pandemic based on a comprehensive, theory-informed set of factors at the individual, interpersonal, and community levels. Research Design and Methods: The study sample consisted of 3,364 individuals who completed the 2016 and 2020 Leave-Behind Questionnaire from the Health and Retirement Study. A longitudinal design was used, with pre-pandemic predictors measured in 2016 and resilience measured in 2020. Three machine learning algorithms (LASSO, Ridge, and Random Forest) were trained with five-fold cross-validation. SHAP values were used to interpret feature importance. Results: LASSO had the best model fit (RMSE = 0.873; R2 = 0.195). Twenty-four features emerged as important predictors. Psychological dispositions and resources, including four Big Five personality traits, optimism, purpose in life, life satisfaction, and religiosity, were strong predictors of resilience. Pre-pandemic social participation, social support, and neighborhood cohesion were also positively associated with resilience. Several indicators of technology adaptation, particularly learning a new device, and socio-behavioral adaptation during the pandemic were additional positive predictors of resilience. In contrast, older subjective age was linked to lower resilience. Several non-linear and interaction effects were identified. Discussion and Implications: Study findings underscore the complex, multifactorial nature of resilience and demonstrate the value of theory-informed data science approach in advancing our understanding of resilience. Addressing digital inequities and fostering supportive social relationships and community participation are potential targets for population-based strategies as we face increasing threats from disasters.

20 March 2026
Verified
Journal Article
Open access
PDF file
YKYoung Soo Ko
Young Soo Ko
XLXuan Lu
Xuan Lu
Introduction. The advancement of large language models (LLMs) has led to a rapidly expanding body of research, making systematic mapping of the research landscape critical for informed policy and resource allocation. We present an LLM-powered framework constructing hierarchical topics to reveal how research emerges and reorganizes. Method. We gather Web of Science (WoS) titles/abstracts, extract topics via GPTopic, and prompt an LLM to form a hierarchy. We integrate quantitative and qualitative analyses, building a bipartite network linking domains and methods. Analysis. The hierarchical topics provide an overview of the LLM research landscape. Trends are derived from monthly aggregations of publications, offering insights into how research topics evolve and shift in the future. Results. AI/ML led overall output, peaking in August 2024, with multimodal learning, systems efficiency, and cybersecurity emerging as key growth engines. Medical LLM research evolved from exploration (2023) to workflow integration (2024), reaching specialized deployment focused on fairness and guidelines by 2025 across medical imaging topics. We successfully forecast two research directions that account for 83.75% of publications in a specific area over the next three months. Conclusion. The framework can effectively generate hierarchical topics for LLM-related research for downstream analysis and can be generalized to other domains.