Xiaoman Zhao | Renmin University of China (original) (raw)
Papers by Xiaoman Zhao
Sociology of Health & Illness
China's family planning policy has historically silenced the voices of women, especially unwe... more China's family planning policy has historically silenced the voices of women, especially unwed single mothers at the expense of their reproductive health and overall wellbeing. Further, reproductive decisions in China are closely intertwined with marriage decisions and intergenerational dynamics, highlighting the relevance of gender in women's reproductive health experiences. Chinese unwed single mothers are in particular penalized for violating the gendered social norms supported by the national reproductive policies. Drawing on previous work that calls on the need to explore gender system and its influence on health, this manuscript explores the ways in which gender norms are played out for the unwed single mothers within romantic and intergenerational relations, with impacts on their reproductive health and decision-making. The findings show that reproductive decisions are interwoven with the fulfilment of other gendered identities, such as daughter, daughter-in-law and wife. Although the decision to go through unwed motherhood is reflective of their agency, the tie between childbirth and marriage does not allow the women to entirely break free from the social system. The findings also highlight the importance of considering the role of gender system that is played out within social relations, which in turn impacts the health of the women.
Proceedings of the 2022 International Conference on Management of Data
The prevalence of misinformation, both online and offline, has prompted a great demand of fact ve... more The prevalence of misinformation, both online and offline, has prompted a great demand of fact verification. Table-based fact verification aims to check whether a textual claim is supported or refuted based on relational tables. However, most of the existing approaches are in a closed-domain setting, which may not be realistic in practice. To address this problem, in this paper, we introduce OpenTFV, a user-friendly system that supports open domain table-based fact verification. Given a claim input by an end-user, OpenTFV retrieves the relevant tables, and provides a verification result for each table with an intuitive interpretation in natural language. We have implemented OpenTFV and demonstrated OpenTFV in two representative scenarios, COVID-19 claims fact verification based on academic tables and general fact verification on Wiki-tables.
Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Social in-feed advertising delivers ads that seamlessly fit inside a user’s feed, and allows user... more Social in-feed advertising delivers ads that seamlessly fit inside a user’s feed, and allows users to engage in social actions (likes or comments) with the ads. Many businesses pay higher attention to “engagement marketing” that maximizes social actions, as social actions can effectively promote brand awareness. This paper studies social action prediction for in-feed advertising. Most existing works overlook the social influence as a user’s action may be affected by her friends’ actions. This paper introduces an end-to-end approach that leverages social influence for action prediction, and focuses on addressing the high sparsity challenge for in-feed ads. We propose to learn influence structure that models who tends to be influenced. We extract a subgraph with the near neighbors a user interacts with, and learn topological features of the subgraph by developing structure-aware graph encoding methods. We also introduce graph attention networks to learn influence dynamics that models ...
Health Communication, 2019
China's family planning policy prioritizes the state and has historically silenced the voices of ... more China's family planning policy prioritizes the state and has historically silenced the voices of women in their own reproductive discourse. Unwed single Chinese mothers are in particular penalized and remain invisible in the national reproductive health discourse that promotes childbirth only within the institution of marriage. Drawing on Giddens' theoretical framework of structure-agency, thirty in-depth interviews were conducted to understand the lived experiences of Chinese unwed single mothers. Specifically, this study explored the ways in which structural violence is communicatively enacted in the interactions within institutions such as police station, family planning office and health care system; and interpersonal relationships such as family and neighbors that silence the voices of the unwed single mothers. Further the study also explored the ways in which the women enact their agency to navigate these macro and micro level constrains and limitations. The findings revealed that the women's experience of structural violence is often a manifestation of the state-controlled sexuality discourse in the social institutions and interpersonal relationships, and highlighted the women's agency enactment through employing various communicative behaviors to manage these day-today struggles.
Health Promotion International
The lockdown that was deployed in Wuhan, China to combat the COVID-19 pandemic curbed the infecti... more The lockdown that was deployed in Wuhan, China to combat the COVID-19 pandemic curbed the infection but also created great information challenges for people in social isolation. This resulted in surge in online health information seeking (OHIS) behaviors of the patients and their families. While the Internet has been widely used by Chinese public to access and search health information, there is relatively little research in the context of pandemic outbreaks, especially at the onset of a strong lockdown while many people were panicking. From a total of 10 908 ‘#COVID-19 Patient Seeking Help’ posts on Weibo in a period of 20 days when the lockdown policy was first initiated, we identified 1496 unique patients living in or with family in Wuhan, China. Using textual analysis, we explored OHIS behaviors at the onset of the pandemic. Many faced increased difficulties accessing offline healthcare services and such turned to social media for help and information. In particular, the finding...
BACKGROUND First detected in Wuhan, China in December 2019, the novel coronavirus (i.e., “COVID-1... more BACKGROUND First detected in Wuhan, China in December 2019, the novel coronavirus (i.e., “COVID-19”) pandemic stretched the medical system in Wuhan and posed an immense challenge to the state’s risk communication efforts. Timely access to quality healthcare information during outbreaks of infectious diseases can be effective to curtail the spread of disease and feelings of anxiety. While these existing studies have greatly extended our knowledge about online health information seeking behavior, processes and motivations, rarely have the findings been applied to an outbreak. Moreover, there is relatively little recent research on how people in China are using the Internet for seeking health information in a time of a pandemic. OBJECTIVE The objective of our study was to explore how people in China are using the Internet for seeking health information in a time of a pandemic. Drawing on previous research of online health information seeking, this study asks the following research ques...
2021 IEEE 37th International Conference on Data Engineering (ICDE)
Behavioral targeting plays an important role in social media advertising for capturing users’ pre... more Behavioral targeting plays an important role in social media advertising for capturing users’ preferences of ads. While existing studies of behavioral targeting mainly focus on the user behaviors that have explicit correlations with ads, such as ad clicking and web search, many implicit relationships between users and ads, which reside in a variety of heterogeneous sources in social media platforms, are not utilized to enhance the prediction of users’ preferences of ads.In this paper, we propose a two-pronged approach to behavioral targeting that effectively addresses the above difficulties. First, we model the implicit relationships between users and ads as a heterogeneous information network (HIN), and propose a method that first performs representation learning in the HIN and then uses the learned representations to train a prediction model for boosting the performance of behavioral targeting. Second, we develop a human-in-the-loop framework to address the incompleteness challenge in HIN construction that may result in inferior performance of model prediction. The framework judiciously selects the most "beneficial" tasks to ask human for completing the HIN and utilizes the results from human to update the representation learning of HIN. We validate the effectiveness of our approach through extensive experiments on real datasets collected from WeChat, the largest social media platform in China. The experimental results show that our approach is effective at constructing a high-quality HIN at a low cost of human involvement, and the HIN can significantly improve the performance of social behavioral targeting.
Sociology of Health & Illness
China's family planning policy has historically silenced the voices of women, especially unwe... more China's family planning policy has historically silenced the voices of women, especially unwed single mothers at the expense of their reproductive health and overall wellbeing. Further, reproductive decisions in China are closely intertwined with marriage decisions and intergenerational dynamics, highlighting the relevance of gender in women's reproductive health experiences. Chinese unwed single mothers are in particular penalized for violating the gendered social norms supported by the national reproductive policies. Drawing on previous work that calls on the need to explore gender system and its influence on health, this manuscript explores the ways in which gender norms are played out for the unwed single mothers within romantic and intergenerational relations, with impacts on their reproductive health and decision-making. The findings show that reproductive decisions are interwoven with the fulfilment of other gendered identities, such as daughter, daughter-in-law and wife. Although the decision to go through unwed motherhood is reflective of their agency, the tie between childbirth and marriage does not allow the women to entirely break free from the social system. The findings also highlight the importance of considering the role of gender system that is played out within social relations, which in turn impacts the health of the women.
Proceedings of the 2022 International Conference on Management of Data
The prevalence of misinformation, both online and offline, has prompted a great demand of fact ve... more The prevalence of misinformation, both online and offline, has prompted a great demand of fact verification. Table-based fact verification aims to check whether a textual claim is supported or refuted based on relational tables. However, most of the existing approaches are in a closed-domain setting, which may not be realistic in practice. To address this problem, in this paper, we introduce OpenTFV, a user-friendly system that supports open domain table-based fact verification. Given a claim input by an end-user, OpenTFV retrieves the relevant tables, and provides a verification result for each table with an intuitive interpretation in natural language. We have implemented OpenTFV and demonstrated OpenTFV in two representative scenarios, COVID-19 claims fact verification based on academic tables and general fact verification on Wiki-tables.
Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Social in-feed advertising delivers ads that seamlessly fit inside a user’s feed, and allows user... more Social in-feed advertising delivers ads that seamlessly fit inside a user’s feed, and allows users to engage in social actions (likes or comments) with the ads. Many businesses pay higher attention to “engagement marketing” that maximizes social actions, as social actions can effectively promote brand awareness. This paper studies social action prediction for in-feed advertising. Most existing works overlook the social influence as a user’s action may be affected by her friends’ actions. This paper introduces an end-to-end approach that leverages social influence for action prediction, and focuses on addressing the high sparsity challenge for in-feed ads. We propose to learn influence structure that models who tends to be influenced. We extract a subgraph with the near neighbors a user interacts with, and learn topological features of the subgraph by developing structure-aware graph encoding methods. We also introduce graph attention networks to learn influence dynamics that models ...
Health Communication, 2019
China's family planning policy prioritizes the state and has historically silenced the voices of ... more China's family planning policy prioritizes the state and has historically silenced the voices of women in their own reproductive discourse. Unwed single Chinese mothers are in particular penalized and remain invisible in the national reproductive health discourse that promotes childbirth only within the institution of marriage. Drawing on Giddens' theoretical framework of structure-agency, thirty in-depth interviews were conducted to understand the lived experiences of Chinese unwed single mothers. Specifically, this study explored the ways in which structural violence is communicatively enacted in the interactions within institutions such as police station, family planning office and health care system; and interpersonal relationships such as family and neighbors that silence the voices of the unwed single mothers. Further the study also explored the ways in which the women enact their agency to navigate these macro and micro level constrains and limitations. The findings revealed that the women's experience of structural violence is often a manifestation of the state-controlled sexuality discourse in the social institutions and interpersonal relationships, and highlighted the women's agency enactment through employing various communicative behaviors to manage these day-today struggles.
Health Promotion International
The lockdown that was deployed in Wuhan, China to combat the COVID-19 pandemic curbed the infecti... more The lockdown that was deployed in Wuhan, China to combat the COVID-19 pandemic curbed the infection but also created great information challenges for people in social isolation. This resulted in surge in online health information seeking (OHIS) behaviors of the patients and their families. While the Internet has been widely used by Chinese public to access and search health information, there is relatively little research in the context of pandemic outbreaks, especially at the onset of a strong lockdown while many people were panicking. From a total of 10 908 ‘#COVID-19 Patient Seeking Help’ posts on Weibo in a period of 20 days when the lockdown policy was first initiated, we identified 1496 unique patients living in or with family in Wuhan, China. Using textual analysis, we explored OHIS behaviors at the onset of the pandemic. Many faced increased difficulties accessing offline healthcare services and such turned to social media for help and information. In particular, the finding...
BACKGROUND First detected in Wuhan, China in December 2019, the novel coronavirus (i.e., “COVID-1... more BACKGROUND First detected in Wuhan, China in December 2019, the novel coronavirus (i.e., “COVID-19”) pandemic stretched the medical system in Wuhan and posed an immense challenge to the state’s risk communication efforts. Timely access to quality healthcare information during outbreaks of infectious diseases can be effective to curtail the spread of disease and feelings of anxiety. While these existing studies have greatly extended our knowledge about online health information seeking behavior, processes and motivations, rarely have the findings been applied to an outbreak. Moreover, there is relatively little recent research on how people in China are using the Internet for seeking health information in a time of a pandemic. OBJECTIVE The objective of our study was to explore how people in China are using the Internet for seeking health information in a time of a pandemic. Drawing on previous research of online health information seeking, this study asks the following research ques...
2021 IEEE 37th International Conference on Data Engineering (ICDE)
Behavioral targeting plays an important role in social media advertising for capturing users’ pre... more Behavioral targeting plays an important role in social media advertising for capturing users’ preferences of ads. While existing studies of behavioral targeting mainly focus on the user behaviors that have explicit correlations with ads, such as ad clicking and web search, many implicit relationships between users and ads, which reside in a variety of heterogeneous sources in social media platforms, are not utilized to enhance the prediction of users’ preferences of ads.In this paper, we propose a two-pronged approach to behavioral targeting that effectively addresses the above difficulties. First, we model the implicit relationships between users and ads as a heterogeneous information network (HIN), and propose a method that first performs representation learning in the HIN and then uses the learned representations to train a prediction model for boosting the performance of behavioral targeting. Second, we develop a human-in-the-loop framework to address the incompleteness challenge in HIN construction that may result in inferior performance of model prediction. The framework judiciously selects the most "beneficial" tasks to ask human for completing the HIN and utilizes the results from human to update the representation learning of HIN. We validate the effectiveness of our approach through extensive experiments on real datasets collected from WeChat, the largest social media platform in China. The experimental results show that our approach is effective at constructing a high-quality HIN at a low cost of human involvement, and the HIN can significantly improve the performance of social behavioral targeting.