All

Papers

Browse and search HCI research papers from All

Active Filters

Institution: Loyola University

18 results

Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems

Recommender systems (RS), which are widely deployed across high-stakes domains, are susceptible to biases that can cause large-scale societal impacts. Researchers have proposed methods to measure and mitigate such biases - but translating academic theory into practice is inherently challenging. Through a semi-structur…

Jing Nathan Yan et al.Cornell University

Embodying Facts, Figures, and Faiths in Narrative Artistic Performances in Rural Bangladesh

There is an increasing interest in telling serious stories with data. Designers organize information, construct narratives, and present findings to inform audiences. However, many of these practices emerge from modern information visualization rhetoric and ethical frameworks which may marginalize communities with low…

Sharifa Sultana et al.Cornell University

EvaluAId: Human-AI Collaborative Evaluation of Open-Ended Student Essays

Open-ended writing assignments are central to higher education, yet heterogeneous submissions and scale make evaluation difficult. Automated writing evaluation (AWE) promises speed but often trades away transparency and sidelines human judgment. This paper repositions AI as an on-demand collaborator that can provide s…

Chao Zhang et al.Cornell University

ThemeViz: Understanding the Effect of Human-AI Collaboration in Theme Development with an LLM-enhanced Interactive Visual System

This paper explores the potential role of AI, e.g., large language models (LLMs), in supporting theme development in thematic analysis. While prior applications of AI in qualitative data analysis have focused on supporting coding, we investigate whether LLMs can effectively contribute as collaborators in the more abst…

Daye Kang et al.Cornell University

Data Visualization

AdRecommended

Learn AI Coding at CodeNow

Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work.

Explore Now

Synthia: Visually Interpreting and Synthesizing Feedback for Writing Revision

While recent advances in HCI and generative AI have improved authors' access to feedback on their work, the abundance of critiques can overwhelm writers and obscure actionable insights. We introduce Synthia, a system that visually scaffolds feedback-based writing revision with LLM-powered synthesis. Synthia helps auth…

Chao Zhang et al.Cornell University

Navigating the Fog: How University Students Recalibrate Sensemaking Practices to Address Plausible Falsehoods in LLM Outputs

LLM interfaces, such as ChatGPT, are widely used by students in higher education. However, their reliability is compromised by the tendency to generate plausible yet factually inaccurate content. This issue is particularly critical as the HCI community shows growing interest in designing LLM-based educational technolo…

Chao Zhang et al.Cornell University

Friction: Deciphering Writing Feedback into Writing Revisions through LLM-Assisted Reflection

This paper introduces Friction, a novel interface designed to scaffold novice writers in reflective feedback-driven revisions. Effective revision requires mindful reflection upon feedback, but the scale and variability of feedback can make it challenging for novice writers to decipher it into actionable, meaningful ch…

Chao Zhang et al.Cornell University

Towards Hormone Health: An Autoethnography of Long-Term Holistic Tracking to Manage PCOS

Polycystic ovary syndrome (PCOS) is a common hormonal disorder affecting 11-13% of women of reproductive age, characterized by a wide range of symptoms (e.g., menstrual irregularity, acne, and obesity) that varies among individuals. While self-tracking tools help PCOS patients to monitor their symptoms and find person…

Daye Kang et al.Cornell University

Challenges and Opportunities for Tool Adoption in Industrial UX Research Collaborations

UX research practitioners analyze qualitative data to comprehend users’ needs and synthesize design implications for software systems. Collaborating with multiple stakeholders is inevitable for these professionals and adds additional pressure to their already laborious data analysis tasks. In this paper, we investigat…

Daye Kang et al.Cornell University

Session 2f: UX, Visual Communication and Design

Understanding Motivational Factors in Social Media News Sharing Decisions

News sharing has become prevalent on many social media platforms. Users are not only exposed to news shared by others, but also actively share information with a diverse set of motivations. In this work, we propose five news sharing motivations based on the intrinsic and extrinsic factors found in prior literature. Th…

Luping Wang et al.Cornell University

Social Regulation and Control

Communicating Consequences: Visual Narratives, Abstraction, and Polysemy in Rural Bangladesh

Information communication and visualization practices reflect two centuries of developments of conventions and best practices which may not be reflective of global audiences’ methods for conveying information. Contrasting between rural traditional visual culture and contemporary HCI and data-visualization, we argue th…

Sharifa Sultana et al.Cornell University

Crowdsourcing and Evaluating Concept-driven Explanations of Machine Learning Models

An important challenge in building explainable artificially intelligent (AI) systems is designing interpretable explanations. AI models often use low-level data features which may be hard for humans to interpret. Recent research suggests that situating machine decisions in abstract, human understandable concepts can h…

Swati Mishra et al.Cornell University

Interpreting and Explaining AI

Designing Interactive Transfer Learning Tools for ML Non-Experts

Interactive machine learning (iML) tools help to make ML accessible to users with limited ML expertise. However, gathering necessary training data and expertise for model-building remains challenging. Transfer learning, a process where learned representations from a model trained on potentially terabytes of data can b…

Swati Mishra et al.Cornell University

Tessera: Discretizing Data Analysis Workflows on a Task Level

Researchers have investigated a number of strategies for capturing and analyzing data analyst event logs in order to design better tools, identify failure points, and guide users. However, this remains challenging because individual- and session-level behavioral differences lead to an explosion of complexity and there…

Jing Nathan Yan et al.Cornell University

“Turning the Invisible Visible”: Transdisciplinary Bioart Explorations in Human-DNA Interaction

Hybrid interactive systems that combine living and digital components can engage, educate, and inform users, and are of growing interest in the HCI community. Advances in synthetic biology are transforming what is possible to do with these living media interfaces (LMIs). Bioart is a practice in which artists, often us…

Foad Hamidi et al.UMBC

Seeing in Context: Traditional Visual Communication Practices in Rural Bangladesh

There is a risk that modern practices of information communication and visualization in human-computer interaction can sideline communities due to their prioritization of scientific rationality. Such ideological hegemony can complicate interactions with data and computers, especially for low-literate communities in th…

Sharifa Sultana et al.Cornell University

Storytelling / Research Method Reflections

Silva: Interactively Assessing Machine Learning Fairness Using Causality

Machine learning models risk encoding unfairness on the part of their developers or data sources. However, assessing fairness is challenging as analysts might misidentify sources of bias, fail to notice them, or misapply metrics. In this paper we introduce Silva, a system for exploring potential sources of unfairness…

Jing Nathan Yan et al.Cornell University

The Tools of Management: Adapting historical union tactics to platform mediated labor”

At the same time that workers' rights are generally declining in the United States (US), workplace computing systems gather more data about workers and their activities than ever before. The rise of large scale labor analytics raises questions about how and whether workers could use such data to advocate for their own…

Vera Khovanskaya et al.Cornell University

Labor and Justice

Paper Title	Authors	Research Topics
Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems Recommender systems (RS), which are widely deployed across high-stakes domains, are susceptible to biases that can cause large-scale societal impacts. Researchers have proposed methods to measure and mitigate such biases - but translating academic theory into practice is inherently challenging. Through a semi-structur…	JY Jing Nathan Yan et al.Cornell University
Embodying Facts, Figures, and Faiths in Narrative Artistic Performances in Rural Bangladesh There is an increasing interest in telling serious stories with data. Designers organize information, construct narratives, and present findings to inform audiences. However, many of these practices emerge from modern information visualization rhetoric and ethical frameworks which may marginalize communities with low…	SS Sharifa Sultana et al.Cornell University
EvaluAId: Human-AI Collaborative Evaluation of Open-Ended Student Essays Open-ended writing assignments are central to higher education, yet heterogeneous submissions and scale make evaluation difficult. Automated writing evaluation (AWE) promises speed but often trades away transparency and sidelines human judgment. This paper repositions AI as an on-demand collaborator that can provide s…	CZ Chao Zhang et al.Cornell University
emoji_events ThemeViz: Understanding the Effect of Human-AI Collaboration in Theme Development with an LLM-enhanced Interactive Visual System This paper explores the potential role of AI, e.g., large language models (LLMs), in supporting theme development in thematic analysis. While prior applications of AI in qualitative data analysis have focused on supporting coding, we investigate whether LLMs can effectively contribute as collaborators in the more abst…	DK Daye Kang et al.Cornell University	Data Visualization
AdRecommended Learn AI Coding at CodeNow Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work. Explore Now
Synthia: Visually Interpreting and Synthesizing Feedback for Writing Revision While recent advances in HCI and generative AI have improved authors' access to feedback on their work, the abundance of critiques can overwhelm writers and obscure actionable insights. We introduce Synthia, a system that visually scaffolds feedback-based writing revision with LLM-powered synthesis. Synthia helps auth…	CZ Chao Zhang et al.Cornell University
Navigating the Fog: How University Students Recalibrate Sensemaking Practices to Address Plausible Falsehoods in LLM Outputs LLM interfaces, such as ChatGPT, are widely used by students in higher education. However, their reliability is compromised by the tendency to generate plausible yet factually inaccurate content. This issue is particularly critical as the HCI community shows growing interest in designing LLM-based educational technolo…	CZ Chao Zhang et al.Cornell University
Friction: Deciphering Writing Feedback into Writing Revisions through LLM-Assisted Reflection This paper introduces Friction, a novel interface designed to scaffold novice writers in reflective feedback-driven revisions. Effective revision requires mindful reflection upon feedback, but the scale and variability of feedback can make it challenging for novice writers to decipher it into actionable, meaningful ch…	CZ Chao Zhang et al.Cornell University
emoji_events Towards Hormone Health: An Autoethnography of Long-Term Holistic Tracking to Manage PCOS Polycystic ovary syndrome (PCOS) is a common hormonal disorder affecting 11-13% of women of reproductive age, characterized by a wide range of symptoms (e.g., menstrual irregularity, acne, and obesity) that varies among individuals. While self-tracking tools help PCOS patients to monitor their symptoms and find person…	DK Daye Kang et al.Cornell University
Challenges and Opportunities for Tool Adoption in Industrial UX Research Collaborations UX research practitioners analyze qualitative data to comprehend users’ needs and synthesize design implications for software systems. Collaborating with multiple stakeholders is inevitable for these professionals and adds additional pressure to their already laborious data analysis tasks. In this paper, we investigat…	DK Daye Kang et al.Cornell University	Session 2f: UX, Visual Communication and Design
Understanding Motivational Factors in Social Media News Sharing Decisions News sharing has become prevalent on many social media platforms. Users are not only exposed to news shared by others, but also actively share information with a diverse set of motivations. In this work, we propose five news sharing motivations based on the intrinsic and extrinsic factors found in prior literature. Th…	LW Luping Wang et al.Cornell University	Social Regulation and Control
Communicating Consequences: Visual Narratives, Abstraction, and Polysemy in Rural Bangladesh Information communication and visualization practices reflect two centuries of developments of conventions and best practices which may not be reflective of global audiences’ methods for conveying information. Contrasting between rural traditional visual culture and contemporary HCI and data-visualization, we argue th…	SS Sharifa Sultana et al.Cornell University
Crowdsourcing and Evaluating Concept-driven Explanations of Machine Learning Models An important challenge in building explainable artificially intelligent (AI) systems is designing interpretable explanations. AI models often use low-level data features which may be hard for humans to interpret. Recent research suggests that situating machine decisions in abstract, human understandable concepts can h…	SM Swati Mishra et al.Cornell University	Interpreting and Explaining AI
emoji_events Designing Interactive Transfer Learning Tools for ML Non-Experts Interactive machine learning (iML) tools help to make ML accessible to users with limited ML expertise. However, gathering necessary training data and expertise for model-building remains challenging. Transfer learning, a process where learned representations from a model trained on potentially terabytes of data can b…	SM Swati Mishra et al.Cornell University
Tessera: Discretizing Data Analysis Workflows on a Task Level Researchers have investigated a number of strategies for capturing and analyzing data analyst event logs in order to design better tools, identify failure points, and guide users. However, this remains challenging because individual- and session-level behavioral differences lead to an explosion of complexity and there…	JY Jing Nathan Yan et al.Cornell University
“Turning the Invisible Visible”: Transdisciplinary Bioart Explorations in Human-DNA Interaction Hybrid interactive systems that combine living and digital components can engage, educate, and inform users, and are of growing interest in the HCI community. Advances in synthetic biology are transforming what is possible to do with these living media interfaces (LMIs). Bioart is a practice in which artists, often us…	FH Foad Hamidi et al.UMBC
Seeing in Context: Traditional Visual Communication Practices in Rural Bangladesh There is a risk that modern practices of information communication and visualization in human-computer interaction can sideline communities due to their prioritization of scientific rationality. Such ideological hegemony can complicate interactions with data and computers, especially for low-literate communities in th…	SS Sharifa Sultana et al.Cornell University	Storytelling / Research Method Reflections
Silva: Interactively Assessing Machine Learning Fairness Using Causality Machine learning models risk encoding unfairness on the part of their developers or data sources. However, assessing fairness is challenging as analysts might misidentify sources of bias, fail to notice them, or misapply metrics. In this paper we introduce Silva, a system for exploring potential sources of unfairness…	JY Jing Nathan Yan et al.Cornell University
emoji_events The Tools of Management: Adapting historical union tactics to platform mediated labor” At the same time that workers' rights are generally declining in the United States (US), workplace computing systems gather more data about workers and their activities than ever before. The rise of large scale labor analytics raises questions about how and whether workers could use such data to advocate for their own…	VK Vera Khovanskaya et al.Cornell University	Labor and Justice