The research team conducted their review with unusual methodological rigor. Registered in PROSPERO under code CRD42025641093 and following the PRISMA 2020 reporting guidelines, the study searched PubMed, Scopus, Web of Science, and Google Scholar for literature published up to January 2025. The initial search returned 6,352 records, which the researchers whittled down through duplicate removal, title and abstract screening, and full-text review until only ten studies remained. Each of those ten was assessed with the Mixed Methods Appraisal Tool, and all scored between 80 and 100 percent on methodological quality, meaning they met at least four of the tool’s five criteria. Two reviewers independently performed study selection, quality assessment, and data extraction, with disagreements resolved by a third author—a design intended to minimize bias in a field where subjective judgments about digital behavior are easy to make.

The ten included studies covered a strikingly diverse range of mass gatherings: the Hajj pilgrimage, music festivals, a professional boxing match, the Shanghai New Year’s Eve celebration, and social demonstrations. Using thematic analysis, the researchers coded the findings line by line and grouped them into three overarching domains: the benefits of social media integration, the challenges and risks it poses, and the strategic recommendations that follow. This structure allowed the team to move beyond anecdotal lessons from individual events and build a consolidated framework that organizers across different cultural and risk contexts could apply.

The benefits fall into two broad categories, the first of which is real-time monitoring and safety. One of the most compelling case studies comes from the 2014 Shanghai New Year’s Eve stampede, where researchers demonstrated that data from the Chinese microblogging platform Sina Weibo allowed for real-time detection of crowd aggregation and the reconstruction of the event’s timeline after the fact. In a separate study focused on high-profile sporting events, analysis of Twitter data enabled timely detection of crowd emotions—a capability the review identifies as vital for emergency management when tens of thousands of people are packed into a single venue. The emotional temperature of a crowd, in other words, can now be read from the stream of posts it produces, giving operators a window into shifting sentiment before it translates into dangerous physical behavior.

The public health implications may be even more significant. One included study demonstrated the feasibility of using search engine and Twitter data for the early detection of disease outbreaks during mass gatherings such as the Hajj and large music festivals. Because mass gatherings concentrate people from around the world in dense conditions ideal for pathogen transmission, the ability to spot an emerging outbreak from digital signals—before clinical surveillance systems catch it—represents a genuine advance in mass gathering medicine. The review also highlights how social media enables bidirectional communication: official accounts push information downward to attendees, while grassroots posts flow upward to organizers, and event-specific hashtags allow participants to become active co-creators of the experience, transforming them into co-marketers and community builders who enhance the emotional and functional value of the event itself.

Yet the same platforms that detect a forming crowd crush can also spread the misinformation that triggers one. The review identifies three clusters of challenges. The first is data accuracy: user-generated content depends on accurate geotagging, natural language processing models struggle with diverse languages, and health monitoring systems risk false positives—as when post-event fatigue is misinterpreted as disease symptoms, sending public health officials chasing an outbreak that does not exist. The second cluster involves security and ethics. A lack of platform oversight can allow misinformation to spread and violence to be incited during demonstrations, while the collection and analysis of personal crowd data without explicit consent raises ethical dilemmas that the review’s authors treat as far from settled. Privacy, they argue, remains a paramount concern that current monitoring practices have not adequately resolved.

The third cluster is social and behavioral. The review documents a phenomenon the researchers call value co-destruction: the digital counterpart to the co-creation of event value, in which excessive engagement with screens actually diminishes the live experience. Empirical studies cited in the review show that heavy social media use during events reduces attendees’ engagement and satisfaction, decreases the quality of face-to-face interaction, and can increase feelings of isolation—even in the middle of a joyful crowd. The paradox is sharp: the platforms that connect people to the event online can disconnect them from the people standing beside them.

From this evidence, the authors build a three-tiered set of strategic recommendations. To maximize benefits, they call for real-time digital communication protocols with official accounts and pre-approved messaging templates; the integration of social listening tools with artificial intelligence-driven dashboards and formal crowd models to improve prediction of patient presentation rates for emergency medical services; event-specific hashtags and digital touchpoints to encourage value co-creation; and the incorporation of search and social media data into public health surveillance for early outbreak warning. To mitigate risks, they recommend centralized verified information hubs to combat misinformation, collaboration with platforms to flag false content, clear privacy policies with anonymized monitoring data, investment in advanced natural language processing models to reduce false positives, and the promotion of mindful device usage—including media-free zones and offline activities at events.

The discussion section of the paper is notably candid about implementation barriers. Integrating social media analytics into crowd monitoring is technically feasible, but the high cost of AI-driven infrastructure and the data silo problem—where information is not shared in real time between event organizers and emergency services—remain serious obstacles. The effectiveness of verified information hubs depends heavily on public trust in official institutions; in volatile contexts such as protests, attendees may favor peer-to-peer information over official channels, rendering top-down protocols less effective. The authors also flag a digital blind spot: the reviewed literature relies heavily on Twitter and Facebook data, while modern attendees increasingly migrate toward visual-centric platforms like Instagram and TikTok and encrypted services like WhatsApp and Telegram. If management protocols do not evolve to capture visual and private-group dynamics, organizers risk missing the emotional signals that matter most.

Perhaps the review’s most important insight is that context changes everything. Value co-creation is a benefit at a music festival, but the same participatory dynamic can manifest as mobilization for unrest at a political demonstration. A sentiment analysis strategy that works for a boxing match may fail against the strategic misinformation circulating during a protest. The authors urge organizers to distinguish between recreational crowds and contested crowds, and they call for national and organizational guidelines defining usage standards and ethical boundaries, scenario-based simulation training for staff in digital communication and misinformation control, and cross-sector collaboration among organizers, health authorities, security agencies, and technology providers. The review acknowledges its own limitations—the synthesis is primarily conceptual, and the fast-moving nature of social platforms means findings may not capture emerging trends—but its conclusion is unambiguous. Social media can either enhance or disrupt the health management of mass gatherings, and the difference lies in structured strategy and adaptive governance. Embedded properly into operational planning, these platforms can be transformed from a volatile factor into a resilient asset for safe, engaging, and well-managed events.

Subject of Research: The role of social media in the health management of mass gathering events

Article Title: The role of social media in health management of mass gathering events including opportunities risks and strategic implications

Article References: Tahernejad, A., Jahangiri, K., & Esbakian, B. (2026). The role of social media in health management of mass gathering events including opportunities risks and strategic implications. Discover Social Science and Health, 6(1), Article 99. https://doi.org/10.1007/s44155-026-00434-2

Image Credits: AI Generated

DOI: 10.1007/s44155-026-00434-2

Keywords: social media, mass gatherings, public health, crowd monitoring, misinformation, systematic review, disease surveillance, event management, privacy, sentiment analysis, emergency management, digital governance

Developed by Ji’an Liao, Zifa Wang, Dengke Zhao, Jianming Wang, Zhaoyan Li, and Siran Yang, SHM-EM addresses a deceptively simple failure mode: machine learning models used for forecasting demand their inputs in a fixed order with fixed columns, while monitoring platforms store data in vendor-specific tables with inconsistent fields, units, and point identifiers. The result is brittle glue code that is hard to verify, harder to reuse, and nearly impossible to audit when something goes wrong. Existing standards such as the Open Geospatial Consortium’s SensorThings API standardize how sensors and observations are described and queried, and complex-event-processing research supplies tools for windows, conditions, and event generation, but neither specifies how a persisted forecast should be inspected, aligned, and conditionally admitted into an official event workflow. That boundary is precisely where the new framework concentrates its effort.

Architecturally, SHM-EM is organized into four layers: a Vue-based user interface, Spring Boot application services, a Python forecasting runtime named PIT_PRE that runs fixed-version models, and a MySQL persistent store holding observations, model registrations, predictions, events, and responses. The authors deliberately keep the Python modelling ecosystem separate from the Java services, which isolates inference from page-access frequency and prevents model dependencies from leaking into the back end. Formal event creation is reserved exclusively for back-end services, a design choice that reflects the framework’s central concern: the difference between looking at a forecast and acting on one must be enforced by the software itself, not by user discipline.

The first of the framework’s three core mechanisms is a versioned, engineering-semantic data-model contract. This contract binds monitoring objects, source fields, ordered input features, fixed-version models, and prediction targets into a single inspectable registration. Cryptographic bundle hashes cover model weights, preprocessors, scripts, parameters, and runtime metadata, while feature mappings retain input order, source identity, units, conversion versions, and target roles. When anything drifts, whether the bundle, the schema, the contract, or the feature ordering, PIT_PRE rejects the run outright. Before inference, observations are aligned to a registered three-minute grid using backward as-of matching within one cadence, followed by linear interpolation and boundary fill, with signed time offsets and fill diagnostics recorded. Unresolved required inputs are rejected rather than silently imputed, and data freshness is checked separately.

The second mechanism is the project future state, a software-level representation of synchronized forecasts and risk summaries. In the reference deployment, six Transformer-CNN models forecast deep horizontal displacements in two directions, earth-pressure strain and pressure, groundwater elevation, and surface settlement. Five of the models consume 114 input features each while the settlement model uses 164, and together they produce 124 target channels across 40 future steps at three-minute intervals. All models share a single prediction origin and future timeline, so a project manager sees one coherent 120-minute view of predicted risk rather than six disconnected model outputs. A policy-bound aggregation algorithm then evaluates rule-level conditions step by step, activates severity levels when consecutive-step requirements are satisfied, assigns the highest activated severity, and merges forecast risk with any open risk from already-observed events.

The third mechanism, and arguably the most consequential, is the controlled transition from forecasts to formal engineering events. After a prediction batch is stored, SHM-EM validates it and prepares a unified engineering series in which observed and forecast values share object, metric, time, engineering-value, unit, and provenance fields. A gate then checks batch status, required runs and steps, timing, quality, bundle hashes, and the recomputed integrity of persisted results. Only then are two independent paths exposed. Evaluate returns candidate events and calculation snapshots, storing an audit run without creating any formal event or response record. Execute, by contrast, never consumes a stored evaluation result; it reloads the series, persists a fresh execution-gate result, revalidates rule and unit semantics, and creates the formal event, response workflow, and provenance chain only when every condition is satisfied. This separation means that a mutation of data after evaluation cannot slip a stale decision into formal execution, a failure path the authors explicitly test.

Provenance receives equally careful treatment. Every formal event can be traced to its rule version, prediction batch, model and input hashes, the exact input window, the exceedance details including lead time, peak value, and consecutive steps, and a result hash. In the published reproduction, a captured event resolves to rule version 2, a 40-step batch, a settlement model run, and an input window spanning late December 2024 into the first minutes of 2025, with the machine-readable trace retaining a peak settlement of roughly 9.43 millimeters. Such traces transform what is usually an opaque alerting pipeline into an auditable record that a reviewer can reconstruct end to end.

The evidence base for these claims is unusually concrete. A public reference case built on 2,464 de-identified, time-shifted observations from nine excavation points verifies the software chain without claiming predictive accuracy, since confidentiality prevents release of the complete training data. A 15-case validation matrix combined one positive control, twelve injected failure paths, and two input controls; every expected blocked case produced zero formal business records, while audit writes remained permitted. Scripted reproduction families passed in full, including 55 back-end tests, 13 PIT_PRE tests, and the end-to-end reference workflow, and a Docker Compose route reproduced the entire six-model, 4,960-record pipeline. A synthetic bridge fixture then demonstrated reuse: adding three stations, twelve instruments, and new mappings required no changes to back-end, front-end, forecasting, or event code, with missing mappings correctly rejected. Runtime measurements on a warm-cache Windows machine showed a full six-model prediction batch completing in a median of about 16.8 seconds, with the execution gate itself taking only a few hundred milliseconds.

The authors are candid about limits, which strengthens rather than weakens the contribution. The excavation case and synthetic fixture do not validate predictions for other structure types, the point forecasts provide no calibrated uncertainty or safety confidence, and MySQL is the only tested back end behind a 50,000-row application-level gate cap. Cross-platform reproduction revealed that while input and model-contract hashes matched between Windows and Ubuntu, normalized prediction hashes differed slightly, with a maximum persisted absolute difference of about 0.00285, so Windows remains the exact-output reference. The public baseline lacks authentication, and the security documentation requires TLS, external identity and role-based access control, separate Execute privileges, least-privilege database accounts, and protected audit logs. Most importantly, the authors state plainly that forecasts must never be the sole basis for automated safety decisions.

Even within those boundaries, the significance of SHM-EM lies in what it makes routine. Researchers can register compatible model versions, thresholds, and rule settings without rewriting acquisition, forecasting, or event-handling workflows. After one-time registration, non-specialist users work through a web interface to inspect observed and forecast series, review threshold exceedances and lead times, and, crucially, distinguish a candidate event from a formally executed one, with eligibility or blocking reasons, model versions, input windows, and hashes all visible. Released under the MIT license with locked dependencies, immutable model cards, and a SHA-256-verified archive, the framework offers the structural health monitoring community something rarer than another forecasting algorithm: a disciplined, reproducible pathway by which a prediction earns the right to become an official record of engineering concern.

Subject of Research: A forecast-aware event management software framework for structural health monitoring of civil engineering projects

Article Title: SHM-EM: a forecast-aware event management framework for heterogeneous engineering monitoring

Article References: Liao, J., Wang, Z., Zhao, D., Wang, J., Li, Z., & Yang, S. (2026). SHM-EM: a forecast-aware event management framework for heterogeneous engineering monitoring. SoftwareX, 36, Article 103082. https://doi.org/10.1016/j.softx.2026.103082

Image Credits: AI Generated

DOI: 10.1016/j.softx.2026.103082

Keywords: structural health monitoring, SHM-EM, machine learning forecasting, Transformer-CNN models, sensor data integration, event management, provenance, reproducibility, open-source software, excavation monitoring, data-model contract, civil engineering