arXiv subjects

Mauro Cherubini

Publications and source records attributed to Mauro Cherubini.

11 recordsLinked to original sources

arXiv2026

When Workout Buddies Are Virtual: AI Agents and Human Peers in a Longitudinal Physical Activity Study

Physical inactivity remains a critical global health issue, yet scalable strategies for sustained motivation are scarce. Conversational agents designed as simulated exercising peers (SEPs) represent a promising alternative, but their long-term impact is unclear. We report a six-month randomized controlled trial (N=280) comparing individuals exercising alone, with a human peer, or with a large language model-driven SEP. Results revealed a partnership paradox: human peers evoked stronger social presence, while AI peers provided steadier encouragement and more reliable working alliances. Humans motivated through authentic comparison and accountability, whereas AI peers fostered consistent, low-stakes support. These complementary strengths suggest that AI agents should not mimic human authenticity but augment it with reliability. Our findings advance human-agent interaction research and point to hybrid designs where human presence and AI consistency jointly sustain physical activity.

cs.HC↗

arXiv2025

The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms

We analyzed nearly 460,000 AI model cards from Hugging Face to examine how developers report risks. From these, we extracted around 3,000 unique risk mentions and built the \emph{AI Model Risk Catalog}. We compared these with risks identified by researchers in the MIT Risk Repository and with real-world incidents from the AI Incident Database. Developers focused on technical issues like bias and safety, while researchers emphasized broader social impacts. Both groups paid little attention to fraud and manipulation, which are common harms arising from how people interact with AI. Our findings show the need for clearer, structured risk reporting that helps developers think about human-interaction and systemic risks early in the design process. The catalog and paper appendix are available at: https://social-dynamics.net/ai-risks/catalog.

cs.CY↗

arXiv2025

Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models

Artificial Intelligence (AI) is increasingly used in hiring, with large language models (LLMs) having the potential to influence or even make hiring decisions. However, this raises pressing concerns about bias, fairness, and trust, particularly across diverse cultural contexts. Despite their growing role, few studies have systematically examined the potential biases in AI-driven hiring evaluation across cultures. In this study, we conduct a systematic analysis of how LLMs assess job interviews across cultural and identity dimensions. Using two datasets of interview transcripts, 100 from UK and 100 from Indian job seekers, we first examine cross-cultural differences in LLM-generated scores for hirability and related traits. Indian transcripts receive consistently lower scores than UK transcripts, even when they were anonymized, with disparities linked to linguistic features such as sentence complexity and lexical diversity. We then perform controlled identity substitutions (varying names by gender, caste, and region) within the Indian dataset to test for name-based bias. These substitutions do not yield statistically significant effects, indicating that names alone, when isolated from other contextual signals, may not influence LLM evaluations. Our findings underscore the importance of evaluating both linguistic and social dimensions in LLM-driven evaluations and highlight the need for culturally sensitive design and accountability in AI-assisted hiring.

cs.CY↗

arXiv2025

When motivation can be more than a message: designing agents to boost physical activity

Virtual agents are commonly used in physical activity interventions to support behavior change, often taking the role of coaches that deliver encouragement and feedback. While effective for compliance, this role typically lacks relational depth. This pilot study explores how such agents might be perceived not just as instructors, but as co-participants: entities that appear to exert effort alongside users. Drawing on thematic analysis of semi-structured interviews with 12 participants from a prior physical activity intervention, we examine how users interpret and evaluate agent effort in social comparison contexts. Our findings reveal a recurring tension between perceived performance and authenticity. Participants valued social features when they believed others were genuinely trying. In contrast, ambiguous or implausible activity levels undermined trust and motivation. Many participants expressed skepticism toward virtual agents unless their actions reflected visible effort or were grounded in relatable human benchmarks. Based on these insights, we propose early design directions for fostering co-experienced exertion in agents, including behavioral cues, narrative grounding, and personalized performance. These insights contribute to the design of more engaging, socially resonant agents capable of supporting co-experienced physical activity.

cs.HC↗

arXiv2023

Revisiting the Design Agenda for Privacy Notices and Security Warnings

System-generated user-facing notices, dialogs, and warnings in privacy and security interventions present the opportunity to support users in making informed decisions about identified risks. However, too often, they are bypassed, ignored, and mindlessly clicked through, mainly in connection to the well-studied effect of user fatigue and habituation. The contribution of this position paper is to provide a summarized review of established and emergent design dimensions and principles to limit such risk-prone behavior, and to identify three emergent research and design directions for privacy-enhancing dialogs.

cs.HC↗

arXiv2018

Activity Self-Tracking with Smart Phones: How to Approach Odd Measurements?

Tracking physical activity reliably is becoming central to many research efforts. In the last years specialized hardware has been proposed to measure movement. However, asking study participants to carry additional devices has drawbacks. We focus on using mobile devices as motion sensors. In the paper we detail several issues that we found while using this technique in a longitudinal study involving hundreds of participants for several months. We hope to sparkle a lively discussion at the workshop and attract interest in this method from other researchers.

cs.HC↗

arXiv2017

Not a Technology Person: Motivating Older Adults Toward the Use of Mobile Technology

Older users population is rapidly increasing all over the World. Presently, we observe efforts in the human-computer interaction domain aiming to improve life quality of age 65 and over through the use of mobile apps. Nonetheless, these efforts focus primary on interface and interaction de- sign. Little work has focused on the study of motivation to use and adherence to, of elderly to technology. Developing specific design guidelines for this population is relevant, however it should be parallel to the study of desire of elderly to embrace specific technology in their life. Designers should not be limited to technology design but consider as well how to fully convey the value that technology can bring to the lives of the users and motivate adoption. This position paper discusses techniques that might nudge elderly towards the use of new technology.

cs.HC↗

arXiv2011

Your browsing behavior for a Big Mac: Economics of Personal Information Online

Most online services (Google, Facebook etc.) operate by providing a service to users for free, and in return they collect and monetize personal information (PI) of the users. This operational model is inherently economic, as the "good" being traded and monetized is PI. This model is coming under increased scrutiny as online services are moving to capture more PI of users, raising serious privacy concerns. However, little is known on how users valuate different types of PI while being online, as well as the perceptions of users with regards to exploitation of their PI by online service providers. In this paper, we study how users valuate different types of PI while being online, while capturing the context by relying on Experience Sampling. We were able to extract the monetary value that 168 participants put on different pieces of PI. We find that users value their PI related to their offline identities more (3 times) than their browsing behavior. Users also value information pertaining to financial transactions and social network interactions more than activities like search and shopping. We also found that while users are overwhelmingly in favor of exchanging their PI in return for improved online services, they are uncomfortable if these same providers monetize their PI.

cs.HC↗

arXiv2010

Gaze and Gestures in Telepresence: multimodality, embodiment, and roles of collaboration

This paper proposes a controlled experiment to further investigate the usefulness of gaze awareness and gesture recognition in the support of collaborative work at a distance. We propose to redesign experiments conducted several years ago with more recent technology that would: a) enable to better study of the integration of communication modalities, b) allow users to freely move while collaborating at a distance and c) avoid asymmetries of communication between collaborators.

cs.HC↗

arXiv2009

A Refined Experience Sampling Method to Capture Mobile User Experience

This paper reviews research methods used to understand the user experience of mobile technology. The paper presents an improvement of the Experience Sampling Method and case studies supporting its design. The paper concludes with an agenda of future work for improving research in this field. Keywords: Research methods, topology, case study, contrasting graph, Experience Sampling Method

cs.HC↗

arXiv2009

Shopping Uncertainties in a Mobile and Social Context

We conducted a qualitative user study with 77 consumers to investigate what social aspects are relevant when supporting customers during their shopping activities and particularly in situations when they are undecided. Twenty-five respondents (32%) reported seeking extra information on web pages and forums, in addition to asking their peers for advice (related to the nature of the item to be bought). Moreover, from the remaining 52 subjects, only 6 (8%) were confident enough to make prompt comparisons between items and an immediate purchasing choice, while 17 respondents (22%) expressed the need for being away from persuasive elements. The remaining 29 respondents (38%) reported having a suboptimal strategy for making their shopping decisions (i.e. buying all items, not buying, or choosing randomly). Therefore, the majority of our participants (70% = 32% + 38%) had social and information needs when making purchasing decisions. This result motivates the development of applications that would allow consumers to ask shopping questions to their social network while on-the-go.

cs.HC↗