arXiv subjects

Matthew Louis Mauriello

Publications and source records attributed to Matthew Louis Mauriello.

6 recordsLinked to original sources

arXiv2026

ResonaVis: Visualizing Interactive Music Data to Support Reflective Music Composition for Therapeutic Contexts

Designing music for therapeutic contexts requires navigating complex relationships between musical structure and listeners' sensory responses, yet composers often lack structured representations of these interactions, relying instead on intuition. We present ResonaVis, an interactive visualization system that helps composers analyze interaction and audio data from prior sessions with children with Autism Spectrum Disorder (ASD), informing future compositions. ResonaVis integrates audio features and interaction logs to capture how children engage with layered musical compositions, representing this engagement through coordinated visualizations of temporal transitions, layer co-occurrence, rhythmic activity, and spectral characteristics. Rather than prescribing strategies or supporting therapy sessions directly, the system surfaces patterns in past session data to support data-informed reflection during composition. We evaluated ResonaVis through a mixed-methods study with eight music students and a follow-up case study with two experienced composers. Results demonstrate good usability (SUS = 72.23), exceeding benchmarks for early prototypes, and show that participants could identify interaction patterns, reason about layer relationships, and make informed compositional decisions with high perceived performance and low frustration. Confidence in interpreting interaction and acoustic data for ASD-focused composition increased significantly across multiple dimensions (p < 0.05), with qualitative findings suggesting a shift toward more adaptive, data-informed composition. This work contributes a visualization design space for therapeutic music interaction data, an integrated system for compositional reflection, and empirical evidence that visualization tools support analytical reasoning and confidence in data-informed creative practice. (Abstract shortened for arXiv.)

cs.HC↗

arXiv2026

Echoes in the Sky: Computational Thematic Analysis of Online Public Discourse on Bluesky Across Trump's Reelection

As political disruption intensifies online discourse, Bluesky has become an important platform for political discussion and public reaction. In this study, we examine large-scale discourse on Bluesky related to U.S. policy developments associated with the Trump administration. Using the historical retrieval API, we collected all available posts matching Trump and related keywords from 2019 to 2026, yielding 38.5 million posts. We leverage a large language model (LLM)-assisted clustering pipeline, combined with human validation, to identify 14 interpretable thematic domains in English-language posts and 19 thematic categories across 258 executive orders (EOs) signed between January 20, 2025, and May 1, 2026. Our findings identify several dominant themes in Bluesky discourse, including executive governance, political identity, and national security, as well as recurring themes in EOs, including executive task forces, border enforcement, and foreign policy. We also find substantial variation in the persistence and volatility of issue attention, accompanied by an increasing proportion of negative sentiment over time. The dataset and resources are publicly available at https://github.com/Sensify-Lab/Echoes-in-the-Sky

cs.HC↗

arXiv2026

Wisdom of the LLM Crowd: A Large Scale Benchmark of Multi-Label U.S. Election-Related Harmful Social Media Content

The spread of election misinformation and harmful political content conveys misleading narratives and poses a serious threat to democratic integrity. Detecting harmful content at early stages is essential for understanding and potentially mitigating its downstream spread. In this study, we introduce USE24-XD, a large-scale dataset of nearly 100k posts collected from X (formerly Twitter) during the 2024 U.S. presidential election cycle, enriched with spatio-temporal metadata. To substantially reduce the cost of manual annotation while enabling scalable categorization, we employ six large language models (LLMs) to systematically annotate posts across five nuanced categories: Conspiracy, Sensationalism, Hate Speech, Speculation, and Satire. We validate LLM annotations with crowdsourcing (n = 34) and benchmark them against human annotators. Inter-rater reliability analyses show comparable agreement patterns between LLMs and humans, with LLMs exhibiting higher internal consistency and achieving up to 0.90 recall on Speculation. We apply a wisdom-of-the-crowd approach across LLMs to aggregate annotations and curate a robust multi-label dataset. 60% of posts receive at least one label. We further analyze how human annotator demographics, including political ideology and affiliation, shape labeling behavior, highlighting systematic sources of subjectivity in judgments of harmful content. The USE24-XD dataset is publicly released to support future research.

cs.HC↗

arXiv2026

"The explanation makes sense": An Empirical Study on LLM Performance in News Classification and its Influence on Judgment in Human-AI Collaborative Annotation

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. While large language models (LLMs) can scale classification tasks, concerns remain about their trustworthiness. To advance human-AI collaboration, we investigate the feasibility of using LLMs to classify U.S. news by political ideology and examine their effect on user decision-making. We first compared GPT models with prompt engineering to state-of-the-art supervised machine learning on a 34k public dataset. We then collected 17k news articles and tested GPT-4 predictions with brief and detailed explanations. In a between-subjects study (N=124), we evaluated how LLM-generated explanations influence human annotation, judgment, and confidence. Results show that AI assistance significantly increases confidence ($p<.001$), with detailed explanations more persuasive and more likely to alter decisions. We highlight recommendations for AI explanations through thematic analysis and provide our dataset for further research.

cs.HC↗

arXiv2025

Regulating Social Media: Surveying the Impact of Nepali Government's TikTok Ban

Social media platforms have transformed global communication and interaction, with TikTok emerging as a critical tool for education, connection, and social impact, including in contexts where infrastructural resources are limited. Amid growing political discussions about banning platforms like TikTok, such actions can create significant ripple effects, particularly impacting marginalized communities. We present a study on Nepal, where a TikTok ban was recently imposed and lifted. As a low-resource country in transition where digital communication is rapidly evolving, TikTok enables a space for community engagement and cultural expression. In this context, we conducted an online survey (N=108) to explore user values, experiences, and strategies for navigating online spaces post-ban. By examining these transitions, we aim to improve our understanding of how digital technologies, policy responses, and cultural dynamics interact globally and their implications for governance and societal norms. Our results indicate that users express skepticism toward platform bans but often passively accept them without active opposition. Findings suggest the importance of institutionalizing collective governance models that encourage public deliberation, nuanced control, and socially resonant policy decisions.

cs.HC↗

arXiv2018

"It was Colonel Mustard in the Study with the Candlestick": Using Artifacts to Create An Alternate Reality Game-The Unworkshop

Workshops are used for academic social networking, but connections can be superficial and result in few enduring collaborations. This unworkshop offers a novel interactive format to create deep connections, peer- learning, and produces a technology-enhanced experience. Participants will generate interactive technological artifacts before the unworkshop, which will be used together and orchestrated at the unworkshop to engage all participants in an alternate reality game set in local places at the conference.

cs.HC↗