Objective: Coronavirus disease 2019 (COVID-19) has caused substantial panic worldwide since its outbreak in December 2019. This study uses social networks to track the evolution of public emotion during COVID-19 in China and analyzes the root causes of these public emotions from an event-driven perspective. Methods: A dataset was constructed using microblogs (n = 125,672) labeled with COVID-19-related super topics (n = 680) from 40,891 users from 1 December 2019 to 17 February 2020. Based on the skeleton and key change points of COVID-19 extracted from microblogging contents, we tracked the public’s emotional evolution modes (accumulated emotions, emotion covariances, and emotion transitions) by time phase and further extracted the details of dominant social events. Results: Public emotions showed different evolution modes during different phases of COVID-19. Events about the development of COVID-19 remained hot, but generally declined, and public attention shifted to other aspects of the epidemic (e.g., encouragement, support, and treatment). Conclusions: These findings suggest that the public’s feedback on COVID-19 predated official accounts on the microblog platform. There were clear differences in the trending events that large users (users with many fans and readings) and common users paid attention to during each phase of COVID-19.
19 August 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Change captioning aims to describe the semantic change between a pair of images with natural language while remaining immune to viewpoint change. Based on the encoder-decoder architecture, most existing methods primarily focus on encoding effective change representations for transmission to the decoder. However, they suffer from an insufficient understanding of visual semantics, inadequate single-pass feature comparison, and a confounding bias caused by imbalanced viewpoint change data. These impair change representations and hinder unbiased caption generation. In this paper, we analyze and identify the confounding bias from a causality perspective and propose a Relation-aware Multi-pass Comparison Deconfounded (RMCD) network for change captioning, which elevates the encoding of change representations and mitigates the bias. Specifically, in the encoding stage, to sufficiently understand visual semantics, a position-guided context aggregating module is presented to capture the positional and contextual relations among objects in the image. Then, to achieve comprehensive change representations, we present a multi-pass feature comparison module to recognize semantic differences at various feature levels and progressively integrate them. In the decoding stage, to generate de-biased captions, the causal intervention is employed to remove the confounding bias which introduces spurious correlations between encoded change representations and captions. The newly achieved state-of-the-art performance on four publicly available benchmark datasets and further visual analysis demonstrate the superiority of our method.
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.
18 September 2025 in IEEE Transactions on Affective Computing
State anxiety is a temporary reaction to external stressors. In online classroom scenarios, severe state anxiety over a long period significantly affects the physical and mental health of high school students. Researchers often use students' facial videos to assess their state anxiety. However, videobased assessment methods face challenges with data and clues, limiting their effectiveness in assessing student state anxiety. First, previous datasets mainly focused on the general population and there was a lack of a domain-specific dataset. Second, a single video provides limited clues, making it challenging for assessment methods to make accurate judgments when the student consistently displays a neutral expression. To address the data challenge, we collected the first state anxiety dataset containing 3,701 video clips from 106 high school students. To solve the clue challenge, we constructed a student-level stateanxiety-oriented graph and proposed a graph-based assessment method for student state anxiety at the video-level. This method incorporates course information, event information, students' academic and mental health statuses, and the earlier video information. Three well-designed attention modules are used to fuse these clues for better performance. Experimental results on the collected dataset demonstrate that our method is highly accurate in assessing students' state anxiety, with minimal errors (MSE = 0.1380, MAE = 0.2768).
Although gratitude journaling applications are widely used to support mental well-being, it remains unclear whether autonomy-driven self-help or guided recommendation strategies better support effective and sustainable outcomes. In this study, we compared three interaction strategies for gratitude journaling, autonomous journaling, guided journaling with random/ heuristic topic recommendation. A two-phase longitudinal randomized controlled trial (N = 175) was conducted, consisting of a 14-day intervention followed by a two-month follow-up. Results revealed an interesting trade-off between short-term and long-term effects. Autonomous journaling supported richer gratitude expression and stronger immediate psychological benefits during the intervention. In contrast, guided journaling, particularly random topic recommendation, was associated with more sustained reductions in perceived stress after the intervention ended. These findings highlight the importance of balancing autonomy and guidance in the design of gratitude journaling applications and offer practical implications for supporting both engagement and long-term well-being.