Xin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xin Wang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Ling Feng
Department of Computer Science and Technology, Tsinghua University, Beijing, China
11 shared publications - Lei Cao
Faculty of Psychology, Beijing Normal University, Beijing, China
10 shared publications - Huijun Zhang
Department of Computer Science and Technology, Tsinghua University, Beijing, China
9 shared publications - Ningyun Li
Department of Computer Science and Technology, Tsinghua University, Beijing, China
4 shared publications - Yang Ding
Department of Computer Science and Technology, Tsinghua University, Beijing, China
4 shared publications - Yi Dai
Department of Computer Science and Technology, Tsinghua University, Beijing, China
4 shared publications
Latest Publications
- Open Access
- 7 June 2026
- Published by Center for Open Science in PsyArXiv
The relationship between social media use and social isolation in young adults: a systematic review
Social isolation has become a growing public health concern, with increasing attention to the potential role of social media in shaping social connection and disconnection. This systematic review synthesises 21 empirical studies published between 2000 and 2024 that examined associations between social media use and social isolation among young adults. Following the PRISMA guidelines, studies were selected from five databases: PubMed, Web of Science, Scopus, EBSCOhost, and Google Scholar. Thematic analysis identified three major categories: (1) motivations and patterns of social media use, (2) Effects of Text-based and Visual Communication Channels, and (3) No Association Between Social Media and Social Isolation. While 15 studies reported a positive association between certain patterns of social media use and increased feelings of isolation, four identified potential benefits, and two found no significant relationships. Specifically, excessive or passive use without interaction was more commonly linked to negative outcomes, whereas purposeful and interactive use appeared to support social connection. Differences in platform specifics (e.g., text-based vs. image-based) and contextual variables such as the COVID-19 pandemic contributed to the variability of results. Most studies adopted cross-sectional designs and applied varied measurement tools, which may have influenced the consistency and comparability of results.
- 7 June 2026
- Published by Center for Open Science in PsyArXiv
Open AccessThe relationship between social media use and social isolation in young adults: a systematic review
Social isolation has become a growing public health concern, with increasing attention to the potential role of social media in shaping social connection and disconnection. This systematic review synthesises 21 empirical studies published between 2000 and 2024 that examined associations between social media use and social isolation among young adults. Following the PRISMA guidelines, studies were selected from five databases: PubMed, Web of Science, Scopus, EBSCOhost, and Google Scholar. Thematic analysis identified three major categories: (1) motivations and patterns of social media use, (2) Effects of Text-based and Visual Communication Channels, and (3) No Association Between Social Media and Social Isolation. While 15 studies reported a positive association between certain patterns of social media use and increased feelings of isolation, four identified potential benefits, and two found no significant relationships. Specifically, excessive or passive use without interaction was more commonly linked to negative outcomes, whereas purposeful and interactive use appeared to support social connection. Differences in platform specifics (e.g., text-based vs. image-based) and contextual variables such as the COVID-19 pandemic contributed to the variability of results. Most studies adopted cross-sectional designs and applied varied measurement tools, which may have influenced the consistency and comparability of results.
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1866-1876
MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1866-1876
Open AccessMISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (2) , 1128-1145
Leveraging Social Media for Real-Time Interpretable and Amendable Suicide Risk Prediction With Human-in-The-Loop
Suicide presents a global health challenge, prompting the development of diverse prevention strategies. Among them, timely identification of individuals at risk of suicide remains challenging. Although social media offers potential for tracking users' mental status, harnessing collaboration between AI and human experts for real-time prediction of suicide risk is inadequately explored. This study presents a human-in-the-loop framework for real-time suicide risk prediction based on social media. Once a user made a new post on social media, the AI model assesses user's suicide risk within the next month with explanation based on the historic and new posts plus domain knowledge. Human experts on the other side look into the explanation to confirm/clarify uncertain information as feedback, enabling consistent evolution of the model. Experiments on the constructed dataset, containing 66 suicidal users and 66 non-suicidal users, show that our method achieved 82.58% prediction accuracy, outperforming competitive baselines by 6.57%. Leveraging human feedback improved prediction accuracy by 4.12%. Consultation with 18 experts (including 6 medical staff and 12 psychologists) was conducted to examine the validity of our method. Ethics considerations, as well as potential and limitations of large language models in mental condition prediction, are also discussed at the end of the paper
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (2) , 1128-1145
Leveraging Social Media for Real-Time Interpretable and Amendable Suicide Risk Prediction With Human-in-The-Loop
Suicide presents a global health challenge, prompting the development of diverse prevention strategies. Among them, timely identification of individuals at risk of suicide remains challenging. Although social media offers potential for tracking users' mental status, harnessing collaboration between AI and human experts for real-time prediction of suicide risk is inadequately explored. This study presents a human-in-the-loop framework for real-time suicide risk prediction based on social media. Once a user made a new post on social media, the AI model assesses user's suicide risk within the next month with explanation based on the historic and new posts plus domain knowledge. Human experts on the other side look into the explanation to confirm/clarify uncertain information as feedback, enabling consistent evolution of the model. Experiments on the constructed dataset, containing 66 suicidal users and 66 non-suicidal users, show that our method achieved 82.58% prediction accuracy, outperforming competitive baselines by 6.57%. Leveraging human feedback improved prediction accuracy by 4.12%. Consultation with 18 experts (including 6 medical staff and 12 psychologists) was conducted to examine the validity of our method. Ethics considerations, as well as potential and limitations of large language models in mental condition prediction, are also discussed at the end of the paper
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10373-10381
Integrating Content-Semantics-World Knowledge to Detect Stress from Videos
Stress has rapidly emerged as a significant public health concern in the contemporary society, necessitating prompt identification and effective intervention strategies. Video-based stress detection offers a non-invasive, low-cost, and mass-reaching approach for identifying stress. In this paper, we propose a three-level content-semantic-world knowledge framework, addressing three particular issues for video-based stress detection. (1) How to abstract and encode video semantics with frame contents into visual representation? (2) How to leverage general-purpose LMMs to augment task-specific visual representation? (3) To what extent could general-purpose LMMs contribute to video-based stress detection? We design a Slow-Emotion-Fast-Action scheme to encode fast temporal changes of body actions revealed from video frames, as well as subtle details of emotions per video segment, into visual representation. We augment task-specific visual representation with linguistic facial expression descriptions by prompting general-purpose Large Multimodal Models (LMMs). A knowledge retriever is designed to evaluate and select the most proper deliverable of LMMs. Experimental results on two video-based stress detection datasets show that 1) our proposed three-level framework can achieve 90.89% F1-score in UVSD dataset and 80.79% F1-score, outperforming state-of-the-art; 2) leveraging LMMs helps to improve the F1-score by 2.25% in UVSD and 3.55% in RSL, compared to using the traditional Facial Action Coding System; 3) purely relying on general-purpose LMMs is insufficient with 88.73% F1-score in UVSD dataset and 77.48% F1-score in RSL dataset, demonstrating the necessity to combine task-specific dedicated solutions with world knowledge given by LMMs.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10373-10381
Open AccessIntegrating Content-Semantics-World Knowledge to Detect Stress from Videos
Stress has rapidly emerged as a significant public health concern in the contemporary society, necessitating prompt identification and effective intervention strategies. Video-based stress detection offers a non-invasive, low-cost, and mass-reaching approach for identifying stress. In this paper, we propose a three-level content-semantic-world knowledge framework, addressing three particular issues for video-based stress detection. (1) How to abstract and encode video semantics with frame contents into visual representation? (2) How to leverage general-purpose LMMs to augment task-specific visual representation? (3) To what extent could general-purpose LMMs contribute to video-based stress detection? We design a Slow-Emotion-Fast-Action scheme to encode fast temporal changes of body actions revealed from video frames, as well as subtle details of emotions per video segment, into visual representation. We augment task-specific visual representation with linguistic facial expression descriptions by prompting general-purpose Large Multimodal Models (LMMs). A knowledge retriever is designed to evaluate and select the most proper deliverable of LMMs. Experimental results on two video-based stress detection datasets show that 1) our proposed three-level framework can achieve 90.89% F1-score in UVSD dataset and 80.79% F1-score, outperforming state-of-the-art; 2) leveraging LMMs helps to improve the F1-score by 2.25% in UVSD and 3.55% in RSL, compared to using the traditional Facial Action Coding System; 3) purely relying on general-purpose LMMs is insufficient with 88.73% F1-score in UVSD dataset and 77.48% F1-score in RSL dataset, demonstrating the necessity to combine task-specific dedicated solutions with world knowledge given by LMMs.
- Open Access
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 191-195
GratitudeGuider: A Smart Positive Psychological Intervention System for Mental Wellbeing
Psychological research has confirmed that positive psychological intervention methods, such as gratitude journaling, hold promising potential for promoting mental wellbeing. However, when applied in daily practices, lacking of personalized guidance has often negatively damaged its efficacy and user engagement. This paper proposes a smart system named GratitudeGuider that leverages social network data as personalized resource to provide personalized gratitude journaling service for mental wellbeing. Taking social network data as the recorder of users' real-world life, GratitudeGuider facilitates users with comprehensive stress awareness and intelligent gratitude topic recommendation aligning with their real life experience for more friendly guidance. We implemented GratitudeGuider as a lightweight mobile application and show its superiority in real user study.
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 191-195
Open AccessGratitudeGuider: A Smart Positive Psychological Intervention System for Mental Wellbeing
Psychological research has confirmed that positive psychological intervention methods, such as gratitude journaling, hold promising potential for promoting mental wellbeing. However, when applied in daily practices, lacking of personalized guidance has often negatively damaged its efficacy and user engagement. This paper proposes a smart system named GratitudeGuider that leverages social network data as personalized resource to provide personalized gratitude journaling service for mental wellbeing. Taking social network data as the recorder of users' real-world life, GratitudeGuider facilitates users with comprehensive stress awareness and intelligent gratitude topic recommendation aligning with their real life experience for more friendly guidance. We implemented GratitudeGuider as a lightweight mobile application and show its superiority in real user study.
- 22 August 2024
- Published by Springer Nature
- p. 287-302
SAGS-DynamicBio: Integrating Semantic-Aware and Graph Structure-Aware Embedding for Dynamic Biological Data with Knowledge Graphs
- 22 August 2024
- Published by Springer Nature
- p. 287-302
SAGS-DynamicBio: Integrating Semantic-Aware and Graph Structure-Aware Embedding for Dynamic Biological Data with Knowledge Graphs
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (5) , 6056-6071
Stress Prediction Based on Chaos Theory and an Event–Behavior–Stress Triangle Model
Predicting stress can help people take timely action to manage stress before potential physical and psychological problems arise. In this study, we analyze and verify chaotic features of human’s stress response to stressor and uplift events, and present an event–behavior–stress triangle model for stress prediction. We reconstruct the phase space based on chaos theory, and integrate stress-correlated pre and postfactors (events and behaviors) through an event–behavior–stress correlation memory and a behavior-stress correlation memory for stress prediction. User’s personal features (including self-cognition, opinion about school, personality traits, and future event’s impact) are also involved in stress prediction. We conduct the experiments on the publicly available StudentLife dataset collected from a mobile phone app, including users’ daily activities inferred through the automatic and continuous sensing application and users’ self-reported ecological momentary assessments (EMA) data. The experimental results show that the proposed method outperforms four baseline methods, achieving (88.13% accuracy, 79.38% precision, 77.10% recall, 78.19% F1-score) for 2-labeled (nonstressed/stressed) stress prediction, and (70.42% accuracy, 69.21% precision, 67.90% recall, 68.53% F1-score) for 3-label (nonstressed/little-stressed/huge-stressed) stress prediction. Further possible improvements and implications related to chaos-based stress prediction are also discussed at the end of the article.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (5) , 6056-6071
Stress Prediction Based on Chaos Theory and an Event–Behavior–Stress Triangle Model
Predicting stress can help people take timely action to manage stress before potential physical and psychological problems arise. In this study, we analyze and verify chaotic features of human’s stress response to stressor and uplift events, and present an event–behavior–stress triangle model for stress prediction. We reconstruct the phase space based on chaos theory, and integrate stress-correlated pre and postfactors (events and behaviors) through an event–behavior–stress correlation memory and a behavior-stress correlation memory for stress prediction. User’s personal features (including self-cognition, opinion about school, personality traits, and future event’s impact) are also involved in stress prediction. We conduct the experiments on the publicly available StudentLife dataset collected from a mobile phone app, including users’ daily activities inferred through the automatic and continuous sensing application and users’ self-reported ecological momentary assessments (EMA) data. The experimental results show that the proposed method outperforms four baseline methods, achieving (88.13% accuracy, 79.38% precision, 77.10% recall, 78.19% F1-score) for 2-labeled (nonstressed/stressed) stress prediction, and (70.42% accuracy, 69.21% precision, 67.90% recall, 68.53% F1-score) for 3-label (nonstressed/little-stressed/huge-stressed) stress prediction. Further possible improvements and implications related to chaos-based stress prediction are also discussed at the end of the article.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5137-5149
Contrastive Learning of Stress-specific Word Embedding for Social Media based Stress Detection
Detecting stress via user's social media posts has attracted increasing research interests in recent years. The majority of the methods leverage word embeddings to represent each of the posted words as a vector, and then perform classification on a sequence of word vectors. To enhance the performance of distinguishing words/phrases related to stressors and stressful emotions from others, in this study, we present a stress-specific word embedding learning framework upon the pre-trained language model BERT. Specifically, we formulate three self-supervised contrastive learning tasks with a joint learning objective. (1) The stressor discrimination task, which is designed to allow the framework to be sensitive to words/phrases about stressors. (2) The stressor cluster discrimination task, which is designed to allow the framework to distinguish stressors into different categories. (3) The stressful emotion discrimination task, which is designed to allow the framework to grasp words/phrases about stressful emotions. Our performance study shows that the learned stress-specific word embedding can significantly benefit social media based stress detection tasks, especially in the more practical scenarios with insufficient labeled data. Besides, we build two user-level social media based stress detection datasets that can help train machine learning models to facilitate human well-being.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5137-5149
Open AccessContrastive Learning of Stress-specific Word Embedding for Social Media based Stress Detection
Detecting stress via user's social media posts has attracted increasing research interests in recent years. The majority of the methods leverage word embeddings to represent each of the posted words as a vector, and then perform classification on a sequence of word vectors. To enhance the performance of distinguishing words/phrases related to stressors and stressful emotions from others, in this study, we present a stress-specific word embedding learning framework upon the pre-trained language model BERT. Specifically, we formulate three self-supervised contrastive learning tasks with a joint learning objective. (1) The stressor discrimination task, which is designed to allow the framework to be sensitive to words/phrases about stressors. (2) The stressor cluster discrimination task, which is designed to allow the framework to distinguish stressors into different categories. (3) The stressful emotion discrimination task, which is designed to allow the framework to grasp words/phrases about stressful emotions. Our performance study shows that the learned stress-specific word embedding can significantly benefit social media based stress detection tasks, especially in the more practical scenarios with insufficient labeled data. Besides, we build two user-level social media based stress detection datasets that can help train machine learning models to facilitate human well-being.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (9) , 4500-4511
Continuous Stress Detection Based on Social Media
Leveraging social media for stress detection has been growing attention in recent years. Most relevant studies so far concentrated on training a stress detection model on the entire data in a closed environment, and did not continuously incorporate new information into the already established models but instead regularly reconstruct a new model from scratch. In this study, we formulate a social media based continuous stress detection task with two particular questions to be addressed: (1) when to adapt a learned stress detection model? and (2) how to adapt a learned stress detection model? We design a protocol to quantify the conditions that trigger model's adaptation, and develop a layer-inheritance based knowledge distillation method to continually adapt the learned stress detection model to incoming data, while retaining the knowledge gained previously. The experimental results on a constructed dataset containing 69 users on Tencent Weibo validate the effectiveness of the proposed adaptive layer-inheritance based knowledge distillation method, achieving 86.32% and 91.56% of accuracy in 3-label and 2-label continuous stress detection. Implications and further possible improvements are also discussed at the end of the paper.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (9) , 4500-4511
Continuous Stress Detection Based on Social Media
Leveraging social media for stress detection has been growing attention in recent years. Most relevant studies so far concentrated on training a stress detection model on the entire data in a closed environment, and did not continuously incorporate new information into the already established models but instead regularly reconstruct a new model from scratch. In this study, we formulate a social media based continuous stress detection task with two particular questions to be addressed: (1) when to adapt a learned stress detection model? and (2) how to adapt a learned stress detection model? We design a protocol to quantify the conditions that trigger model's adaptation, and develop a layer-inheritance based knowledge distillation method to continually adapt the learned stress detection model to incoming data, while retaining the knowledge gained previously. The experimental results on a constructed dataset containing 69 users on Tencent Weibo validate the effectiveness of the proposed adaptive layer-inheritance based knowledge distillation method, achieving 86.32% and 91.56% of accuracy in 3-label and 2-label continuous stress detection. Implications and further possible improvements are also discussed at the end of the paper.
- 28 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (2) , 1280-1296
Learning Users Inner Thoughts and Emotion Changes for Social Media Based Suicide Risk Detection
Suicide has become a serious problem, hurting the well-being of human society. Thanks to social media, from peopleslinguistic posts, suicide risk detection has achieved good performance. The aim of this study is to investigate whether more significantaccuracy could be achieved. Motivated by the observation that the prior solutions strived to detect suicide risk based on users explicitouter post expressions on social media, and no attempt was made to infer users inner true thoughts and emotion changes from theirnormal open posts for suicide risk detection, we propose to firstly learn the correlations between users normal open posts and hiddencomments, trying to understand users inner true thoughts and emotion changes from his open posts, and then detect users suiciderisk upon the generated intermediate results. The performance study on the microblog dataset (3,652 at-risk microblog users and 3,652ordinary microblog users) and forum dataset (392 at-risk forum users and 108 ordinary forum users) shows that, based on the inferredhidden thoughts and inner emotion changes, the proposed approach can achieve 95% and 90% detection accuracy, respectively.
- 28 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (2) , 1280-1296
Learning Users Inner Thoughts and Emotion Changes for Social Media Based Suicide Risk Detection
Suicide has become a serious problem, hurting the well-being of human society. Thanks to social media, from peopleslinguistic posts, suicide risk detection has achieved good performance. The aim of this study is to investigate whether more significantaccuracy could be achieved. Motivated by the observation that the prior solutions strived to detect suicide risk based on users explicitouter post expressions on social media, and no attempt was made to infer users inner true thoughts and emotion changes from theirnormal open posts for suicide risk detection, we propose to firstly learn the correlations between users normal open posts and hiddencomments, trying to understand users inner true thoughts and emotion changes from his open posts, and then detect users suiciderisk upon the generated intermediate results. The performance study on the microblog dataset (3,652 at-risk microblog users and 3,652ordinary microblog users) and forum dataset (392 at-risk forum users and 108 ordinary forum users) shows that, based on the inferredhidden thoughts and inner emotion changes, the proposed approach can achieve 95% and 90% detection accuracy, respectively.