LZLina Zhou

Lina Zhou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lina Zhou has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From Explainability to Actionability: a Tiered Adaptable Multi-Agent Framework with Agent Reasoning Tools for Collaborative Failure Recovery

    by Jie Tao, Lina Zhou

    Effective human-AI collaboration, especially in failure scenarios, requires systems that function as active partners rather than static tools. This research addresses this requirement by introducing a tiered multi-agent architecture grounded in Human-Centered eXplainable AI principles. The architecture consists of three novel design artifacts: tiered reasoning that adapts explanation depth to failure severity, a traceable memory bus for auditability, and flexible reasoning tools for enhanced adaptability. These designs enable agents to not only perform evidence-based diagnoses of performance gaps but devise recovery strategies and propose actionable improvement plans as well. We empirically evaluate this architecture on an aspect term extraction task using hybrid methods that combine performance comparisons against state-of-the-art baselines, human expert user studies, and multi-role user simulations. The results demonstrate that our architecture significantly enhances both task performance and failure recovery diagnosis and plans. We then validate the generalizability of our architecture with a second task of comparable complexity. This research contributes an adaptable and generalizable framework and foundational artifacts for trustworthy AI teammates.

  • Open Access

    Digital Voices of Survival: From Social Media Disclosures to Support Provisions for Domestic Violence Victims

    by Kanlun Wang, Zhe Fu, Wangjiaxuan Xin, Lina Zhou, Shashi Kiran Chandrappa

    Domestic Violence (DV) is a pervasive public health problem characterized by patterns of coercive and abusive behavior within intimate relationships. With the rise of social media as a key outlet for DV victims to disclose their experiences, online self-disclosure has emerged as a critical yet underexplored avenue for support-seeking. In addition, existing research lacks a comprehensive and nuanced understanding of DV self-disclosure, support provisions, and their connections. To address these gaps, this study proposes a novel computational framework for modeling DV support-seeking behavior alongside community support mechanisms. The framework consists of four key components: self-disclosure detection, post clustering, topic summarization, and support extraction and mapping. We implement and evaluate the framework with data collected from relevant social media communities. Our findings not only advance existing knowledge on DV self-disclosure and online support provisions but also enable victim-centered digital interventions.

  • Open Access

    Beyond Privacy: Understanding and Mitigating Doxing in the Digital Environment

    by Tharun Bottlapally, Lina Zhou

    The proliferation of social media has transformed digital communication, offering unprecedented connectivity while also exposing individuals to privacy risks like doxing—the malicious disclosure of private information. This study investigates doxing through the lenses of digital ethics and cyber safety, seeking to develop effective mitigation strategies. Among the various countermeasures to online doxing, including technical solutions, legal reforms, and educational initiatives, this study focuses on technical solutions by leveraging transform-based models such as BERT and RoBERTa to detect doxing activities in textual data. Our empirical results demonstrate the effectiveness of the transformer-based models in detecting online doxing behavior. Additionally, this study discusses the socio-ethical implications of doxing, taking into account the different stakeholders involved. Using a multidisciplinary approach, this study offers strategies to strengthen digital security and ethics, fostering a safer online environment.


  • Open Access

    Generative AI for Intelligence Augmentation: Categorization and Evaluation Frameworks for Large Language Model Adaptation

    by Fairfield University, Jie Tao, Lina Zhou, The University of North Caorlina, Xing Fang, Illinois State University

    Generative AI (GenAI) has transformed how businesses operate and innovate and how individuals learn, live, and work. Large language models (LLMs), a specific type of GenAI, focus on generating human-like text based on user instructions. Like other types of GenAI, LLMs have received wide recognition for their potential to augment human intelligence, but several challenges hinder efforts to realize their full potential in practice. Some notable challenges include not adequately exploring LLM applications beyond chatbots and/or text generation, the difficulty in categorizing various LLM adaptation strategies (particularly regarding human interactions), and the lack of a reference framework for evaluating and selecting LLM adaptation strategies from a human-centered perspective. To address these challenges, we propose a categorization framework for LLM adaptation that features two human-centered dimensions and stage LLM adaptation with respect to when it interacts with human intelligence. Additionally, we introduce an evaluation framework that incorporates a human-centered perspective that goes beyond the common machine-centered measures. Our empirical investigations, in which we use text classification as use cases, not only demonstrate the application of these frameworks but also compare various adaptation strategies. These artifacts and findings provide fresh insights and practical recommendations for selecting effective adaptation strategies to improve the efficacy of LLMs for intelligence augmentation. We further identify future research issues to address current limitations and suggest improvements for the proposed frameworks.


  • Open Access

    The Effects of Email Illegitimacy and Phishing Behavior Training on Eye Movement Behavior in Spear Phishing Detection

    by Lina Zhou, Jaewan Lim, Dongsong Zhang

    Email phishing, such as spear phishing attacks, has become increasingly sophisticated. Automatic phishing detection models and anti-phishing education and awareness programs remain insufficient in guarding against general phishing attacks, which are even more ineffective in dealing with spear phishing. Understanding human receivers' interaction behavior with phishing emails can be instrumental in improving the effectiveness of antiphishing training and human phishing detection. To this end, eye movement behavior can serve as a lens reflecting human cognitive processes and attention. This study focuses on examining the effects of email legitimacy and phishing behavior training on receivers' eye movement behavior by analyzing their eye-tracking data. The findings have implications for developing spear phishing training programs and improving phishing detection models that can improve online safety of human users.


  • Open Access

    Beyond the Social Media Contents: The Role of Social Interactions in Stance Detection

    by Lina Zhou, Kanlun Wang, Jie Tao

    Stance detection categorizes the stance toward a specific target or topic, or other aspects of interest (e.g., a social media comment) as favor, against, or neutral. The discourse of stance detection has evolved from court debate to social media, particularly in the analyses of political, social, and health issues. Despite its long-standing history, stance detection still faces significant challenges partly due to ambiguous, diverse, and informal expressions of human language in social media. Motivated by the affordance of social interactions on social media platforms, this study aims to investigate whether social interactions are useful and how to represent and incorporate them into stance detection models effectively. To this end, we propose a framework that integrates graph learning with transformers. The empirical evaluation results with an extended benchmark dataset in the political discourse demonstrate the superior performance of the framework to the state-of-the-art baseline models and highlight the significant role of social interaction networks in stance detection. The framework can also be used to guide the efforts in social media monitoring, marketing, and informed decision-making.