Tian Shen

Prof. Tian Shen


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
2 February 2022 in Behavioural Neurology
Verified
Journal Article
Open access
PDF file
SWSobia Wassan
Sobia Wassan
TSTian Shen
Tian Shen
CXChen Xi
Chen Xi
Kamal GulatiKamal Gulati
Kamal Gulati
DVDanish Vasan
Danish Vasan
BSBeenish Suhail
Beenish Suhail
Nowadays, sentimental analysis of consumers’ review is becoming much crucial in the marketing world. It is not just giving ideas to the firms that how consumers like their product or service, but it would also help them make their service better. In this article, the statistical method identifies the relationship of many factors in consumer feedback. It introduces a deep-based learning method called DSC (deep sentiment classifier) to determine whether or not to recommend the reviewed product thoroughly. Our suggested method also investigates the effect sizes of the feedback, such as positives, negatives, and neutrals. We used the women’s clothing review dataset containing 22,642 records after preprocessing of the results. Experimental studies show that the recommendations are an excellent positive sentiment indicator. In comparison, ratings become fuzzy performance metrics in product reviews. The 10-fold cross-validation analysis shows that the recommended form has the top F1 score (93.56%) in the sentimental classification on average and the recommended classification (88.32%) on average. A comparative description of other classifiers focused on machine learning, for example, KNN, random forest, logistic regression, decision tree, support vector machine multilayer perceptron, and naïve Bayes, also demonstrates that DSC gives the best possible result. We have tested DSC on the dataset IMDB (Internet Video Database), which includes the sentiment of the 50,000 movie reviews (25000 for training and 25000 for testing). In comparison to other baseline methods, DSC obtained an excellent classification score for this experiment.

7 February 2022 in Behavioural Neurology
Verified
Journal Article
Open access
PDF file
SWSobia Wassan
Sobia Wassan
CXChen Xi
Chen Xi
TSTian Shen
Tian Shen
Kamal GulatiKamal Gulati
Kamal Gulati
KIKinza Ibraheem
Kinza Ibraheem
RLRana Muhammad Amir Latif
Rana Muhammad Amir Latif
Stroke, also known as a cerebrovascular accident, is a medical emergency that causes temporary or permanent behavioral dysfunction in people. Sleep deprivation affects our brains in a variety of ways. The advantages of sleep much justify the risks of not having enough sleep. Sleep deprivation (SD) includes a variety of factors, including prolonged awake. Neuroimaging investigates SD’s impact on attention, working memory, mood, and hippocampal learning. We analyzed how this data enriches our mechanistic understanding of these alterations and the clinical illnesses linked with sleep disruption. We have used Cronbach’s alpha to test the reliability of a scale, so we then have 19 individual attributes responding to 174 participants via survey. The evaluated result shows the reliability statistics; the value for Cronbach’s alpha is .962, which is very excellent as it reaches 1. So, there is very strong reliability. If the value falls under .6, we look back to the mean and standard deviation table and remove the attribute with low values for mean or standard deviation and try the remaining attributes. Cronbach’s alpha tells us which attribute or item to delete to increase the reliability, and we also have analyzed the correlation among the class students while watching the same video lecture. We have collected data for at least ten students watching the same video using a webcam. Once the data is collected, we then have applied some correlation techniques to determine the class students’ behavior towards the same video lecture. This way, we can see the overall behavior of the class upon a specific video lecture. The study further reveals that subjective happiness is influenced by its efficiency, entertainment value, and effectiveness. Does the research offer an original emphasis on analyzing how does lack of sleep affect our brains? Sleep loss frameworks are minimal compared to the benefits of sleep.

1 January 2019 in Journal of Systems Engineering and Electronics
Verified
Journal Article
Closed access
PDF file
MZMengting Zong
Mengting Zong
TSTian Shen
Tian Shen
CXChen Xi
Chen Xi

YLYu Li
Yu Li
CZChujun Zhang
Chujun Zhang
TSTian Shen
Tian Shen
CXChen Xi
Chen Xi
The integration of AI into online platforms is reshaping consumer experience and behavior. While existing research has largely focused on the role of AI in search services and experience services, few studies have examined the role of AI in the context of credence services. This study fills this gap by investigating an AI-powered preview tool in the context of online medical aesthetic platforms. Specifically, this study investigates how the AI Magic Mirror influences consumer purchase intentions in medical aesthetic services. Using secondary data analysis and two experimental studies, we examine the main effects, as well as mediation and moderation effects. The findings consistently demonstrate that the AI Magic Mirror significantly increases consumer purchase intentions. This relationship is positively mediated by perceived value and negatively mediated by perceived risk. In addition, the main effect is stronger for procedures with higher fit uncertainty and is more pronounced for those with lower popularity. These results provide theoretical insights into AI application in credence service contexts and offer practical implications for the design of AI-enhanced online service platforms.

15 February 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
XWXi Wang
Xi Wang
TSTian Shen
Tian Shen
CXChen Xi
Chen Xi
KHKejia He
Kejia He
YZYuxiang Chris Zhao
Yuxiang Chris Zhao
Background: Online health information–seeking (OHIS) behavior shapes health self-management, and eHealth literacy—the ability to seek, appraise, and apply electronic health information—is regarded as its key driver. Previous reviews aggregated heterogeneous outcomes, focused on measurement properties, or examined single clinical populations, without isolating the eHealth literacy–OHIS link. Objective: This study quantified the strength and heterogeneity of the eHealth literacy–OHIS association and identified its boundary conditions across generation, morbidity status, and information source credibility. Methods: Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), we searched PubMed, Embase, Web of Science Core Collection, PsycINFO, Psychology and Behavioral Sciences Collection, and Library, Information Science, and Technology Abstracts (LISTA) up to March 15, 2026 (PROSPERO [International Prospective Register of Systematic Reviews] CRD420251088300). Eligible studies enrolled participants, measured eHealth literacy with validated instruments, and assessed OHIS. Risk of bias used the modified Newcastle-Ottawa Scale. Correlations were Fisher z–transformed and pooled under a random-effects model with the Hartung-Knapp-Sidik-Jonkman correction; subgroups were age cohort, morbidity status, and source type. Heterogeneity was quantified with I ² and τ²; a univariate meta-regression examined temporal trends, and certainty of evidence was rated using GRADE (Grading of Recommendations, Assessment, Development, and Evaluation). Results: Of 9249 nonduplicate records, 32 studies entered the qualitative synthesis, and 19 (20 effect sizes) the meta-analysis. The grand mean correlation was 0.27 (95% CI 0.15-0.38; P <.001) but is of limited interpretive value given extreme heterogeneity ( I ²=99%; τ²=0.064; 95% prediction interval −0.26 to 0.67). Correlations were stronger in non–Gen Z (k=12; r=0.39; 95% CI 0.27-0.50; P <.001) than in Gen Z (k=8; r=0.07; 95% CI −0.06 to 0.20; P =.23), in patients (k=3; r=0.58; 95% CI 0.01-0.86; P =.049) than in nonpatients (k=17; r=0.22; 95% CI 0.11-0.32; P <.001), and in professional (k=5; r=0.41; 95% CI 0.11-0.64; P =.02) than in nonprofessional (k=14; r=0.21; 95% CI 0.06-0.35; P =.01) sources. Meta-regression on collection year showed no significant temporal change (b=−0.005 per year; P =.55), and neither the Egger test ( P =.60) nor trim-and-fill indicated small-study effects. Conclusions: The eHealth literacy–OHIS association is best understood through its boundary conditions, not the overall estimate. The association was robust in non–Gen Z and professional-source contexts but near-null in Gen Z, showing that the eHealth literacy scale’s behavioral predictive validity is cohort- and platform-dependent. Interventions for Gen Z and nonpatient populations should pair literacy training with motivational cues and professionally curated information environments. GRADE certainty was very low, underscoring the need for longitudinal, performance-based research.

YLYu Li
Yu Li
TSTian Shen
Tian Shen
SYShuyi Yang
Shuyi Yang
CXChen Xi
Chen Xi
The development of generative AI has disrupted various fields, and the field of online healthcare is no exception. However, there is a lack of research on patients’ intention to adopt generative AI on online healthcare platforms. Therefore, the aim of this study is to investigate the factors influencing patients’ intention to adopt generative AI. Employing a questionnaire-based survey, we explore the factors influencing patients’ intention to adopt generative AI through the UTAUT2 model, considering the moderating effects of construal level, health literacy, and AI literacy. We find that performance expectancy, social influence, and facilitating conditions are positively associated with patients’ intention. Surprisingly, effort expectancy and hedonic motivation do not have a significant impact on patients’ intention. Construal level positively moderates the relationship between performance expectancy and patients’ intention; health literacy negatively moderates the relationship between social influence and patients’ intention. AI literacy positively moderates the relationship between effort expectancy and patients’ intention but negatively moderates the relationship between social influence and patients’ intention. This study enriches UTAUT2 theory and provides practical insights for the development and promotion of generative AI on online healthcare platforms.