Juan Shi

Dr. Juan Shi

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
4 April 2018 in Internet Research
Verified
Journal Article
Closed access
JSJuan Shi
Juan Shi
PHPing Hu
Ping Hu
KLKin Keung Lai
Kin Keung Lai
GCGang Chen
Gang Chen
Purpose: As a new communication paradigm, social networking sites (SNS) have boosted information diffusion and viral marketing. Prior researchers have identified various factors affecting information dissemination on SNS. However, they often focus on limited factors and there is a lack of an integrated theoretical framework that explains aspects of relevant factors. Besides, the research on the impacts of relationships on individual retweeting behavior is still controversial. The purpose of this paper is to propose a theoretical framework to systematically investigate the determinants of individual dissemination behavior on SNS based on the elaboration likelihood model (ELM). Moreover, the authors also examine the relative importance of those relevant factors.Design/methodology/approach: The authors randomly selected 1,250 members of Twitter and crawled posts published by each member since he/she created the Twitter account using Twitter API. The authors processed the data to create panel data and tested hypotheses with the panel logit model.Findings: Factors both on the central route and on the peripheral route of ELM have positive impacts on individual dissemination behavior. Among them, information receiver-related factor and relationships-related factors are the most influential. Contrastingly, source-related factors are the least influential. Furthermore, the authors find that social tie strength mediates almost 50 percent of the effect of value homophily on individual dissemination behavior.Originality/value: The authors are the first to directly apply ELM to examine individual dissemination behavior on SNS. By integrating factors into the two information processing routes, They incorporate relevant factors into the model and systematically analyze their impacts on individual retweeting behavior on SNS. The research offers at least one explanation for the contradictory findings about the effect of homophily on individual sharing behavior in previous research. The authors propose new variables that gauge topical relevance and interpersonal value homophily on SNS.

22 May 2025 in Frontiers in Pharmacology
Verified
Journal Article
Open access
PDF file
PZPei Zhang
Pei Zhang
QCQiong Chen
Qiong Chen
JLJiahui Lao
Jiahui Lao
JSJuan Shi
Juan Shi
JCJia Cao
Jia Cao
XHXin Huang
Xin Huang
Background: Acute kidney injury (AKI) is a significant concern among hospitalized patients receiving aminoglycosides. Identifying the risk factors associated with aminoglycoside-induced AKI and developing machine learning models are imperative in clinical practice.Objective: This study aims to identify the risk factors associated with AKI in hospitalized patients receiving aminoglycosides, and develop machine learning models for evaluation of the AKI risk in these patients.Methods: This study retrospectively analyzed 7,028 hospitalized patients who received treatment with amikacin or etimicin between 2018 and 2020. According to the type of medication used, patients were divided into amikacin group (n = 307) and etimicin group (n = 6,901). Univariate analyses and the least absolute shrinkage and selection operator algorithm were used to screen risk factors and construct the model. The machine learning models were developed using five different algorithms, including logistic regression (LR), random forest (RF), gradient boosting machine (GBM), extreme gradient boosting model (XGBoost), and light gradient boosting machine (Light GBM).Results: The XGBoost model exhibited the most superior performance in predicting amikacin-associated AKI among the developed machine learning models. For the training set, the area under the receiver-operator characteristic curve (AUC) was 0.916, and for the test set, it was 0.841. The model can be accessed online. Regarding AKI risk in etimicin-treated patients, the GBM model demonstrated the best overall performance, with AUC values of 0.886 for the training set and 0.900 for the test set. The model was also made available online.Conclusion: These predictive models may offer a valuable tool for estimating the risk of AKI in patients receiving amikacin or etimicin, facilitating clinical decision-making and aiding in the prevention of AKI.Trial Registration: ClinicalTrials.gov NCT05533593.

22 May 2023 in PLOS ONE
Verified
Journal Article
Open access
PDF file
JSJuan Shi
Juan Shi
KLKin Keung Lai
Kin Keung Lai
GCGang Chen
Gang Chen
On social networking sites, people can express themselves in a variety of ways such as creating personalized profiles, commenting on some topics, sharing their experiences and thoughts. Among these technology-enabled features, retweeting other-sourced tweet is a powerful way for users to present themselves. We examine users’ retweeting behavior from the perspective of online identity and self-presentation. The empirical results based on a panel dataset crawled from Twitter reveal that, people are prone to retweet topics they are interested in and familiar with, in order to convey a consistent and clear online identity. In addition, we also examine which user groups exhibit a stronger propensity for a clear online identity, considering the practical value of these users to both social media platforms and marketers. By integrating self-presentation theory with social influence theory and social cognitive theory, we propose and confirm that users with higher value in online self-presentation efficacy and users who are more involved with the social media platform have a stronger than average propensity to maintain a consistent online identity, and thus are more likely to retweet familiar topics. These users are characterized by (1) owning a larger number of followers, (2) authoring longer and more original tweets than average, (3) being active in retweeting other-sourced posts. This study contributes to our understanding of SNS users’ retweeting behavior and adds to the emerging line of research on online identity. It also provides insights on how microblogging service providers and enterprises can promote people’s retweeting behavior.

29 June 2017 in Information Technology and Management
Verified
Journal Article
Closed access
PDF file
JSJuan Shi
Juan Shi
KLKin Keung Lai
Kin Keung Lai
PHPing Hu
Ping Hu
GCGang Chen
Gang Chen

1 March 2011
Verified
Conference Paper
Closed access
GCGang Chen
Gang Chen
Yuanli CaiYuanli Cai
Yuanli Cai
JSJuan Shi
Juan Shi
Outlier detection plays important roles in intelligent cyber systems, especially for fault-tolerant and adaptive ones. Traditional algorithms always need to evaluate distances or densities, which are very time-consuming. On the increasingly urgent demand for real-time, during past years, various novel algorithms have been proposed. They are much faster, but less stable and accurate. To cope with these problems, with the core idea of ordinal optimization and the `few and different' characteristics of outliers, by introducing the concept of outlier probability, we propose the ordinal isolation algorithm, which extracts outliers in terms of the order of being isolated in a recursive uniform data space partition process. It doesn't need any distance or density evaluating, and the complexity is reduced to O(n). Experiments show that, the CPU time of ordinal isolation increases linearly with linearly growing data sets. Furthermore, compared with recent iForest algorithm, ordinal isolation is about 30 times faster, with 20% to 30% improvement in accuracy, and especially is much more stable. Ordinal isolation also has good scalability, so it works well in high-dimensional data sets which have a huge number of instances and irrelevant attributes.

27 December 2012 in Sensors
Verified
Journal Article
Open access
PDF file
GCGang Chen
Gang Chen
Yuanli CaiYuanli Cai
Yuanli Cai
JSJuan Shi
Juan Shi
Feature selection, also known as attribute selection, is the technique of selecting a subset of relevant features for building robust object models. It is becoming more and more important for large-scale sensors applications with AI capabilities. The core idea of this paper is derived from a straightforward and intuitive principle saying that, if a feature subset (pattern) has more representativeness, it should be more self-organized, and as a result it should be more insensitive to artificially seeded noise points. In the light of this heuristic finding, we established the whole set of theoretical principles, based on which we proposed a two-stage framework to evaluate the relative importance of feature subsets, called seeding and harvest (S&H for short). At the first stage, we inject a number of artificial noise points into the original dataset; then at the second stage, we resort to an outlier detector to identify them under various feature patterns. The more precisely the seeded points can be extracted under a particular feature pattern, the more valuable and important the corresponding feature pattern should be. Besides, we compared our method with several state-of-the-art feature selection methods on a number of real-life datasets. The experiment results significantly confirm that our method can accomplish feature reduction tasks with high accuracy as well as low computing complexity.