Xinni Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinni Wei has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Constantine Sedikides
School of Psychology, University of Southampton
2 shared publications - Tim Wildschut
University of Southampton
2 shared publications - Bing Xiang Yang
Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing Wuhan University Wuhan China
1 shared publication - Chunyan Luo
Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, No. 115, Donghu Road, Wuchang District, Wuhan, Hubei, China, +86 15902731922
1 shared publication Feng Yu
Department of Psychology Wuhan University Wuhan China
1 shared publication- Feng Yu
Department of Psychology, Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Taylor & Francis in The Journal of Positive Psychology
- p. 1-13
The humanizing power of nostalgia: a pathway to psychological richness
- 30 June 2026
- Published by Taylor & Francis in The Journal of Positive Psychology
- p. 1-13
Open AccessThe humanizing power of nostalgia: a pathway to psychological richness
- Open Access
- 5 December 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e78132
Detecting Sociodemographic Biases in the Content and Quality of Large Language Model–Generated Nursing Care: Cross-Sectional Simulation Study
Background: Large language models (LLMs) are increasingly applied in health care. However, concerns remain that their nursing care recommendations may reflect patients’ sociodemographic attributes rather than clinical needs. While this risk is acknowledged, there is a lack of empirical evidence evaluating sociodemographic bias in LLM-generated nursing care plans. Objective: To investigate potential biases in nursing care plans generated by LLMs, we focused on whether outputs differ systematically based on patients’ sociodemographic characteristics and assessed the implications for equitable nursing care. Methods: We used a mixed methods simulation study. A standardized clinical vignette experiment was used to prompt GPT-4 to generate 9600 nursing care plans for 96 patient profiles with varying sociodemographic characteristics (eg, sex, age, income, education, and residence). We first conducted a quantitative analysis of all plans, assessing variations in thematic content. Subsequently, a panel of senior nursing experts evaluated the clinical quality (eg, safety, applicability, and completeness) of a stratified subsample of 500 plans. Results: We analyzed 9600 LLM-generated nursing care plans and identified 8 consistent themes. Communication and Education (99.98%) and Emotional Support (99.97%) were nearly universal, while Nurse Training and Event Analysis were least frequent (39.3%). Multivariable analyses revealed systematic sociodemographic disparities. Care plans generated for low-income patient profiles were less likely to include the theme Environmental Adjustment (adjusted relative risk [aRR] 0.90). Profiles with lower education were associated with an increased likelihood of including Family Support (aRR 1.10). Similarly, plans generated for older patient profiles were more likely to contain recommendations for Pain Management (aRR 1.33) and Family Support (aRR 1.62) but were less likely to mention Nurse Training (aRR 0.78). Sex and regional differences were also significant. Expert review of 500 plans showed high overall quality (mean 4.47), with strong interrater reliability (κ=0.76‐0.81). However, urban profiles had higher completeness ( β =.22) and applicability ( β =.14) but lower safety scores (β=–0.09). These findings demonstrate that LLM-generated care plans exhibit systematic sociodemographic bias, raising important implications for fairness and safe deployment in nursing practice. Conclusions: This study identified that LLMs systematically reproduce sociodemographic biases in the generation of nursing care plans. These biases appear in two forms: they shape the thematic content and influence expert-rated clinical quality. These findings reveal a substantial risk that such models may reinforce existing health inequities. To our knowledge, this is the first empirical evidence documenting these nuanced biases in nursing. The study also contributes a replicable framework for evaluating LLM-generated care plans. Finally, it underscores the critical need for robust human oversight to ensure that artificial intelligence serves as a tool for advancing equity rather than perpetuating disparities.
- 5 December 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e78132
Open AccessDetecting Sociodemographic Biases in the Content and Quality of Large Language Model–Generated Nursing Care: Cross-Sectional Simulation Study
Background: Large language models (LLMs) are increasingly applied in health care. However, concerns remain that their nursing care recommendations may reflect patients’ sociodemographic attributes rather than clinical needs. While this risk is acknowledged, there is a lack of empirical evidence evaluating sociodemographic bias in LLM-generated nursing care plans. Objective: To investigate potential biases in nursing care plans generated by LLMs, we focused on whether outputs differ systematically based on patients’ sociodemographic characteristics and assessed the implications for equitable nursing care. Methods: We used a mixed methods simulation study. A standardized clinical vignette experiment was used to prompt GPT-4 to generate 9600 nursing care plans for 96 patient profiles with varying sociodemographic characteristics (eg, sex, age, income, education, and residence). We first conducted a quantitative analysis of all plans, assessing variations in thematic content. Subsequently, a panel of senior nursing experts evaluated the clinical quality (eg, safety, applicability, and completeness) of a stratified subsample of 500 plans. Results: We analyzed 9600 LLM-generated nursing care plans and identified 8 consistent themes. Communication and Education (99.98%) and Emotional Support (99.97%) were nearly universal, while Nurse Training and Event Analysis were least frequent (39.3%). Multivariable analyses revealed systematic sociodemographic disparities. Care plans generated for low-income patient profiles were less likely to include the theme Environmental Adjustment (adjusted relative risk [aRR] 0.90). Profiles with lower education were associated with an increased likelihood of including Family Support (aRR 1.10). Similarly, plans generated for older patient profiles were more likely to contain recommendations for Pain Management (aRR 1.33) and Family Support (aRR 1.62) but were less likely to mention Nurse Training (aRR 0.78). Sex and regional differences were also significant. Expert review of 500 plans showed high overall quality (mean 4.47), with strong interrater reliability (κ=0.76‐0.81). However, urban profiles had higher completeness ( β =.22) and applicability ( β =.14) but lower safety scores (β=–0.09). These findings demonstrate that LLM-generated care plans exhibit systematic sociodemographic bias, raising important implications for fairness and safe deployment in nursing practice. Conclusions: This study identified that LLMs systematically reproduce sociodemographic biases in the generation of nursing care plans. These biases appear in two forms: they shape the thematic content and influence expert-rated clinical quality. These findings reveal a substantial risk that such models may reinforce existing health inequities. To our knowledge, this is the first empirical evidence documenting these nuanced biases in nursing. The study also contributes a replicable framework for evaluating LLM-generated care plans. Finally, it underscores the critical need for robust human oversight to ensure that artificial intelligence serves as a tool for advancing equity rather than perpetuating disparities.
- Open Access
- 17 June 2025
- Published by Taylor & Francis in The Journal of Positive Psychology
- p. 1-15
Nostalgia and self-humanity: processes and consequences
- 17 June 2025
- Published by Taylor & Francis in The Journal of Positive Psychology
- p. 1-15
Open AccessNostalgia and self-humanity: processes and consequences
- 26 February 2024
- Published by Wiley in British Journal of Social Psychology
- Vol. 63 (3) , 1410-1428
Seeing is more than believing: Personal experience increases climate action
Although global warming is a serious problem that influences numerous people worldwide, individuals are still reluctant to change their behaviours. The present research investigates how local hot temperatures affect climate action in non‐Western groups. In Study 1, an analysis of temperature and information acquisition by Shanghai residents in 122 days found that heat increased attention and awareness of climate change. In Study 2 and Study 3, participants who were primed with heat‐related perceptions were more likely to take climate action in private and public spheres. In Study 4, we further identified that people who experienced hot temperature events increased their beliefs and efficacy about climate change, which in turn motivated them to take more climate action. Importantly, the mediating effects were significant both in the manipulation of heat and real‐world settings. Consistent with our theoretical perspective, seeing is more than believing because personal experience increases climate action by fostering climate change beliefs and efficacy.
- 26 February 2024
- Published by Wiley in British Journal of Social Psychology
- Vol. 63 (3) , 1410-1428
Seeing is more than believing: Personal experience increases climate action
Although global warming is a serious problem that influences numerous people worldwide, individuals are still reluctant to change their behaviours. The present research investigates how local hot temperatures affect climate action in non‐Western groups. In Study 1, an analysis of temperature and information acquisition by Shanghai residents in 122 days found that heat increased attention and awareness of climate change. In Study 2 and Study 3, participants who were primed with heat‐related perceptions were more likely to take climate action in private and public spheres. In Study 4, we further identified that people who experienced hot temperature events increased their beliefs and efficacy about climate change, which in turn motivated them to take more climate action. Importantly, the mediating effects were significant both in the manipulation of heat and real‐world settings. Consistent with our theoretical perspective, seeing is more than believing because personal experience increases climate action by fostering climate change beliefs and efficacy.
- Open Access
- 6 January 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (2) , 639
Envy and Environmental Decision Making: The Mediating Role of Self-Control
Emotions have strong impacts on decision making, yet research on the association between social interpersonal emotion and environmental decisions is limited. The present study uses experimental manipulation and cross-sectional investigation to examine how envy state and personality trait envy influence environmental actions. In Study 1, participants were manipulated to elicit benign and malicious envy, and it was found that benign envy acts as an antecedent of pro-environmental behavior, while malicious envy could contribute to behavior harmful to the environment. Study 2 replicated the results of Study 1 and examined the mediator of self-control through a correlational study. Consequently, people who are high in malicious envy tend to engage in more environmentally harmful activities rather than living a sustainable life, while dispositional benign envy could significantly predict pro-environmental behavior. Moreover, the link between dispositional malicious envy and environmental behavior can be explained by trait self-control, while the mediating effect was silent in dispositional benign envy. The findings shed new light on the impact of social interpersonal emotion on making environmental decisions and its related psychological mechanisms.
- 6 January 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (2) , 639
Open AccessEnvy and Environmental Decision Making: The Mediating Role of Self-Control
Emotions have strong impacts on decision making, yet research on the association between social interpersonal emotion and environmental decisions is limited. The present study uses experimental manipulation and cross-sectional investigation to examine how envy state and personality trait envy influence environmental actions. In Study 1, participants were manipulated to elicit benign and malicious envy, and it was found that benign envy acts as an antecedent of pro-environmental behavior, while malicious envy could contribute to behavior harmful to the environment. Study 2 replicated the results of Study 1 and examined the mediator of self-control through a correlational study. Consequently, people who are high in malicious envy tend to engage in more environmentally harmful activities rather than living a sustainable life, while dispositional benign envy could significantly predict pro-environmental behavior. Moreover, the link between dispositional malicious envy and environmental behavior can be explained by trait self-control, while the mediating effect was silent in dispositional benign envy. The findings shed new light on the impact of social interpersonal emotion on making environmental decisions and its related psychological mechanisms.