• User-Based Collaborative Filtering Mobile Health System
    H.-T Kao, S. Yan, H. Hosseinmardi, S. Narayanan, K. Lerman, and E. Ferrara
    Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
  • Abstract: Mobile health systems predict health conditions based on multimodal signals. Users are often reluctant to provide their health status over privacy concerns. It is challenging to make health predictions without sufficient historical data from the users. In this paper, we propose a user-based collaborative filtering mobile health system. The...

  • Mitigating Biases in Multimodal Personality Assessment
    S. Yan, D. Huang, and M. Soleymani
    22nd International Conference on Multimodal Interaction (ICMI 2020)
  • Abstract: As algorithmic decision making systems are increasingly used in high-stake scenarios, concerns have risen about the potential unfairness of these decisions to certain social groups. Despite its importance, the bias and fairness of multimodal systems are not thoroughly studied. In this work, we focus on the multimodal systems designed...

  • Fair Class Balancing: Enhancing Model Fairness without Observing Sensitive Attributes
    S. Yan, H.-T Kao, and E. Ferrara
    29th ACM International Conference on Information and Knowledge Management (CIKM'20)
  • Abstract: Machine learning models are at the foundation of modern society. Accounts of unfair models penalizing subgroups of a population have been reported in domains including law enforcement, job screening, etc. Unfairness can spur from biases in the training data, as well as from class imbalance, i.e., when a sensitive...

  • Political polarization drives online conversations about COVID-19 in the United States
    J. Jiang, E. Chen, S. Yan, K. Lerman, and E. Ferrara
    Human Behavior and Emerging Technologies
  • Abstract: Since the outbreak in China in late 2019, the novel coronavirus (COVID‐19) has spread around the world and has come to dominate online conversations. By linking 2.3 million Twitter users to locations within the United States, we study in aggregate how political characteristics of the locations affect the evolution...

  • Affect Estimation with Wearable Sensors
    S. Yan, H. Hosseinmardi, H.-T Kao, S. Narayanan, K. Lerman, and E. Ferrara
    Journal of Healthcare Informatics Research
  • Abstract:Affective states are associated with people’s mental health status and have profound impact on daily life, thus unobtrusively understanding and estimating affects have been brought to the public attention. The pervasiveness of wearable sensors makes it possible to build automatic systems for affect tracking. However, constructing such systems is a...


  • Estimating individualized daily self-reported affect with wearable sensors
    S. Yan, H. Hosseinmardi, H.-T Kao, S. Narayanan, K. Lerman, and E. Ferrara
    IEEE 2019 International Conference on Healthcare Informatics (ICHI'19)
  • Abstract:Wearable sensors (smart watches, health/fitness trackers, etc.) are experiencing an explosion in popularity. Their pervasiveness allows for effective data collections to quantify human behavior in natural settings, enriching traditional behavioral science research opportunities. In this paper, we focus on the problem of affect estimation from sensor-generated data, whereas ground truth...

  • Understanding cyberbullying on Instagram and via social role detection
    H.-T Kao, S. Yan, D. Huang, N. Bartley, H. Hosseinmardi, and E. Ferrara
    4th Workshop on Computational Methods in Online Misbehavior Co-located with The Web Conference (CyberSafety'19)
  • Abstract: Cyberbullying is a major issue on online social platforms, and can have prolonged negative psychological impact on both the bullies and their targets. Users can be characterized by their involvement in cyberbullying according to different social roles including victim, bully, and victim supporter. In this work, we propose a...


  • Discovering latent psychological structures from self-report assessments of hospital workers
    H.-T Kao, H. Hosseinmardi, S. Yan, M. Hasan, S. Narayanan, K. Lerman and E. Ferrara
    5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC'18)
  • Abstract: Hospitals are high-stress environments where workers face a high risk of occupational burnout due to a mix of imbalanced schedules, understaffing, and emotional stress. In this paper, we propose a computational framework to infer the latent psychological makeup and traits of hospital workers. We apply machine learning models to...

  • Social bots for online public health interventions
    A. Deb, A. Majmundar, S. Seo, A. Matsui, R. Tandon, S. Yan, J. Allem, and E. Ferrara
    2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM'18)
  • Abstract: According to the Center for Disease Control and Prevention, in the United States hundreds of thousands initiate smoking each year, and millions live with smoking-related dis- eases. Many tobacco users discuss their habits and preferences on social media. This work conceptualizes a framework for targeted health interventions to inform...

  • SoundAuth: Secure zero-effort two-factor authentication based on audio signals
    M. Wang, W.-T. Zhu, S. Yan, and Q. Wang
    6th IEEE Conference on Communications and Network Security (CNS'18)
  • Abstract: Two-factor authentication (2FA) popularly works by verifying something the user knows (a password) and something she possesses (a token, popularly instantiated with a smart phone). Conventional 2FA systems require extra interaction like typing a verification code, which is not very user-friendly. For improved user experience, recent work aims at...


  • DynaEgo: Privacy-preserving collaborative filtering recommender system based on social-aware differential privacy
    S. Yan, S. Pan, W.-T. Zhu, and K. Chen
    18th International Conference on Information and Communication Security (ICICS'16)
  • Abstract: Collaborative filtering plays an important role in online recommender systems, which provide personalized services to consumers by collecting and analyzing their rating histories. At the same time, such personalization may unfavorably incur privacy leakage, which has motivated the development of privacy-preserving collaborative filtering (PPCF) mechanisms. Most previous research efforts...

  • A secure and fast dispersal storage scheme based on the learning with errors problem
    L. Yang, F. Fang, X. Lu, W. T. Zhu, Q. Wang, S. Yan, and S. Pan
    12th EAI International Conference on Security and Privacy in Communication Networks (SecureComm'16)
  • Abstract: Data confidentiality and availability are of primary concern in data storage. Dispersal storage schemes achieve these two security properties by transforming the data into multiple codewords and dispersing them across multiple storage servers. Existing schemes achieve confidentiality and availability by various cryptographic and coding algorithms, but only under the...

  • Towards Privacy-preserving data mining in online social networks: Distance-grained and item-grained differential privacy
    S. Yan, S. Pan, Y. Zhao, and W.-T. Zhu
    21st Australasian Conference on Information Security and Privacy (ACISP'16)
  • Abstract: Online social networks have becoming increasingly popular, where users are more and more lured to reveal their private information. This brings about convenient personalized services but also incurs privacy concerns. To balance utility and privacy, many privacy preserving mechanisms such as differential privacy have been proposed. However, most existent...

  • Security analysis on privacy-preserving cloud aided biometric identificaiton schemes
    S. Pan, S. Yan, and W.-T. Zhu
    21st Australasian Conference on Information Security and Privacy (ACISP'16)
  • Abstract: Biometric identification is to reliably and effectively identify an individual of interest, where a pre-established database of biometric records is scanned with the unknown individual's biometric sample to look for a close enough match. This has recently been aided with cloud computing, where the database owner achieves higher efficiency...


  • Guaranteed time slots allocation in multi-node wireless sensor networks
    S.R. Fan, S. Yan, and M. Gao
    Chinese Journal of Sensors and Actuators
  • Abstract: With the unique characteristics of low power consumption and low cost, IEEE 802.15.2 standard is widely used in the modern wireless networks. It can provide the lowest 0.006% of duty ratio to reduce power consumption, and offer real-time service for the node through the guarantee time slots (GTS) mechanism....