large-scale measurement

Unintentional information disclosure by users in digital environments poses significant risks—including identity theft and privacy violations—necessitating empirically grounded insights into user behavior and mental models. This study systematically reviews 101 empirical papers published at top-tier conferences between 2018 and 2023, offering the first large-scale, cross-contextual classification and methodological comparison of unintentional disclosure research across data privacy, browser security, and privacy tool usage. Applying mixed-methods coding analysis, we identify critical gaps: a severe paucity of experimental studies and disproportionate focus on privacy and browser contexts. Our core contributions are threefold: (1) a novel, cross-contextual analytical framework for unintentional disclosure; (2) user-centered design principles for mitigating associated risks; and (3) an empirically grounded foundation and research agenda for next-generation privacy-enhancing technologies.

Current research on online behavioral change suffers from narrow behavioral coverage, overreliance on API-restricted platforms as data sources, and a persistent theory–empiricism gap. To address these limitations, this study conducts a systematic literature review of 148 peer-reviewed articles published between 2000 and 2023, constructing a four-dimensional knowledge graph encompassing behavioral categories, detection methodologies, platform ecosystems, and theoretical foundations. Our analysis uncovers three salient trends: (1) affective orientation dominates behavioral modeling; (2) platform distribution is heavily skewed toward a few API-constrained platforms; and (3) theoretical integration remains markedly underdeveloped. We propose a novel methodology framework—“Multi-behavioral Modeling, Heterogeneous Data Integration, and Theory–Practice Alignment”—and deliver a structured research map that precisely identifies critical gaps. This work advances the computational behavioral paradigm and offers an actionable methodological guide for digital social governance.

Internet measurement research confronts pressing ethical challenges—including privacy risks, informed consent complexities, potential participant harm, and misalignment between conventional ethics review frameworks and technical practice—yet scholarly understanding of researchers’ lived ethical decision-making remains limited. This study employs thematic analysis of in-depth interviews with 16 internet measurement researchers across the EU, grounded in a case-study framework. It identifies five recurrent ethical challenge categories and corresponding mitigation strategies, and introduces the novel concept of “ethical craft knowledge,” highlighting the central role of mentorship and peer collaboration in cultivating situated ethical practice. Findings reveal that institutional review boards frequently lack technical literacy regarding measurement methodologies, while cross-institutional and cross-jurisdictional regulatory fragmentation imposes substantial invisible labor. The study calls for a discipline-specific, technically informed ethics support infrastructure tailored to the epistemic and operational realities of internet measurement.

Existing web measurement tools suffer from low accuracy, poor reproducibility, and weak evasion resistance, hindering result verification and replication. This paper introduces WebREC—the first general-purpose web measurement framework enabling high-fidelity event attribution—and proposes the executable, verifiable, and long-term archival .web binary archive format. WebREC achieves deep execution capture via browser automation and fine-grained event provenance, augmented by a lightweight Chromium instrumentation layer that jointly ensures measurement accuracy, broad applicability, and behavioral completeness. Experimental evaluation demonstrates: (1) a 62% reduction in measurement error when reproducing seminal studies; (2) direct support for 70% of measurement tasks from state-of-the-art SoK papers; and (3) offline analysis capability for 48% of tasks using archived .web files—eliminating the need for re-crawling. WebREC thus advances web measurement toward rigor, reproducibility, and sustainability.

This study addresses the challenge of complex etiologies of childhood obesity and the lack of large-scale, objective behavior–environment data to inform evidence-based policy. We propose the first passive, low-intervention, multimodal behavior–environment sensing framework. Leveraging unobtrusive smartphone and smartwatch sensors, it continuously captures gait, sleep, and geolocation time-series data. Integrated edge computing, lightweight sensor fusion algorithms, and spatiotemporal behavioral modeling enable real-time processing of million-scale datasets. The system achieves state-of-the-art performance: step-count error of 8–9 steps, location recognition F1-score of 0.86, and total sleep time estimation error <12 minutes. Deployed in multiple public health studies on childhood obesity, it provides a scalable, technically robust foundation for precision health interventions and data-driven policy optimization.

This study addresses the diagnostic feasibility of digital addiction among TikTok users. We propose a hybrid validation paradigm integrating large-scale survey data (N=1,590) with real-world behavioral logs (N=107). For the first time on a short-video platform, we empirically identify temporal behavioral patterns characteristic of addicted users—such as high-frequency revisits and sustained daytime engagement—and establish a hierarchical behavioral analytics framework grounded in viewing duration, visit frequency, and session inter-arrival intervals. Using temporal pattern mining and binary classification modeling, we achieve effective identification of high-risk users (F1 ≥ 0.55), yet uncover an inherent prediction ceiling (~0.55 F1) when relying solely on surface-level engagement metrics. Key contributions include: (1) establishing empirically grounded diagnostic criteria for behavioral addiction in the TikTok context; (2) revealing fundamental limitations of pure behavioral-data-driven prediction; and (3) providing an actionable, behaviorally anchored risk identification pathway for digital well-being interventions.

This study addresses a critical gap in cybersecurity research by systematically examining the relationship between malware developers’ coding behaviors and their cognitive styles, an aspect largely overlooked in prior work that predominantly focuses on attack techniques. For the first time, code metrics are employed as behavioral proxies, integrating static application security testing (SAST) with software engineering measures—such as cyclomatic complexity, use of abstraction mechanisms, and vulnerability distributions—to comparatively analyze leaked malware samples against benign open-source projects. The findings reveal that malicious code tends to be smaller in scale, lacks documentation, exhibits higher function complexity, employs fewer abstraction mechanisms, and contains vulnerability types typically avoided by legitimate developers. These patterns reflect distinct motivational drivers, risk tolerance, and development priorities among malware authors, underscoring a strategy prioritizing efficiency and stealth over maintainability, thereby offering a novel empirical foundation for profiling cybercriminal behavior.

This study addresses the reliability of Google Play’s Data Safety disclosures, which rely on self-reports from developers and lack empirical validation against apps’ actual privacy practices. Focusing on mobile games, the authors conduct the first fine-grained empirical analysis by statically examining 41 APKs to extract privacy-relevant behaviors involving device identifiers, location data, and personal information. They develop a structured evaluation framework and apply chi-square tests to assess consistency between declared and observed behaviors. The findings reveal high consistency for device identifier disclosures (87.8%) but a substantial inconsistency rate for location data (56.1%). No significant differences emerge between children’s apps and general-audience apps, underscoring a systemic transparency deficit across the mobile application ecosystem.

Accurately measuring the proportion of policy-violating content actually encountered by users is challenged by the rarity of violations, high annotation costs, and the difficulty of conducting frequent, representative assessments. This work proposes a design-based measurement system that draws daily probability samples from user exposure streams using machine learning–assisted weighting. It enables efficient annotation through multimodal large language models, policy-guided prompting, and gold-set validation, and constructs unbiased estimators to produce prevalence metrics with confidence intervals. The system supports multidimensional post-stratification—such as by platform interface, user geography, or content age—using a single global sample, maintaining statistical unbiasedness while prioritizing high-exposure and high-risk content. This approach substantially improves monitoring efficiency, timeliness, and flexibility while significantly reducing annotation costs.

This study addresses the lack of a unified methodology in empirical research on quantum software testing, which has hindered result interpretability and reproducibility. To this end, the work proposes a systematic analytical framework encompassing ten critical dimensions—including test subjects, baseline comparisons, and experimental configurations—and conducts a comprehensive literature review of 59 empirical studies coupled with multidimensional cross-analysis. The analysis reveals prevalent methodological flaws and inconsistencies in current practices. Beyond identifying common issues, the study formulates actionable methodological guidelines and concrete recommendations for improvement, thereby establishing both theoretical grounding and practical benchmarks to guide future empirical research in quantum software testing.

This study addresses the pervasive presence of deceptive design patterns in mobile applications targeting distinct age groups, which can inadvertently prompt unintended user behaviors. It presents the first systematic comparison of such patterns across adolescents, adults, and older adults within 30 apps spanning six categories, employing a qualitative analysis that integrates heuristic evaluation and cognitive walkthroughs. The findings reveal that 93% of the examined apps employ nagging-type dark patterns, with entertainment apps exhibiting particularly high prevalence. Crucially, entertainment applications designed for older adults deploy stealth strategies significantly more often than those targeting other age groups, uncovering a novel age-directed characteristic of deceptive design. These results provide empirical evidence to inform age-appropriate digital governance and regulatory interventions.

This study addresses the growing prevalence of bot detection in browser automation, which leads to systematic sample loss in web security and privacy research. Through large-scale measurements across 10,000 websites (40,000 visits) under four browser configurations, this work constructs a taxonomy of bot detection mechanisms and reveals that 82% of access denials are attributable to such detection, with Cloudflare and Akamai accounting for 37% and 26%, respectively. The authors propose a conditional-dependence-based inference method to uncover undeclared detection behaviors, combining custom instrumentation, header spoofing, and cross-configuration comparison. Their analysis shows that HTTP header signals alone explain 75% of the blocks unique to Chromium’s headless mode. Notably, 83% of recent top-tier publications fail to report this bias, underscoring its substantial threat to research validity.