Ester Zumpano

The levers a small tourism operator can genuinely control are pre-publication ones yet most Instagram engagement models lean on post-publication signals unavailable at decision time and pool heterogeneous content formats into a single feature space. We develop INSPIRE (INstagram Scheduling and PredIction for Reach and Engagement), a replicable, dataset-agnostic framework that honours the pre-publication constraint and separates content by format. It is instantiated on a competitor-intelligence corpus of 27,956 raw items (25,020 after cleaning) from 80+ public accounts in Zanzibar (Tanzania) tourism ecosystem, using only caption text and structured metadata. A Twitter-tuned RoBERTa layer profiles caption polarity descriptively (≈67–70% positive across formats), and hashtags are segmented by K-Means (K = 4; Silhouette = 0.665). For static posts, gradient-boosting ensembles (XGBoost, LightGBM, CatBoost) fused with Sentence-BERT caption embeddings and tuned by Optuna reach a weighted F1 ≈ 0.78 on three-class engagement under a strict leakage audit, with Shapley-additive explanations exposing how dense semantic and sparse temporal/structural features jointly drive the prediction (cf. 0.61–0.82 in adjacent Instagram engagement classification studies). Engagement concentrates on weekends and across the June–September high season, a structure we translate into a rolling 12-month publication scheduler. The same leakage-controlled protocol on the video/Reels track yields markedly higher accuracy (R2 ≈ 0.98 regression, weighted F1 ≈ 0.96 three-class), reflecting the steadier consumption dynamics and richer ex-ante descriptors of short-form video. We frame the contribution as a reproducible methodology rather than a transferable parameter set: the single-destination corpus and text-only feature space bound external validity and motivate multi-destination, multimodal extensions.

Healthcare digitalization demands platforms capable of integrating heterogeneous biomedical data and delivering AI-powered clinical decision support at scale [1, 2]. The SupportAI project, funded by the Italian National Recovery and Resilience Plan (PNRR) through the Tech4You program (grant ECS 00000009, Spoke 6, Line B, Project 2.1), addresses this challenge through a comprehensive modular platform that unifies real-time clinical data integration, advanced 3D imaging, generative AI assistance, and collaborative tools within a standards-compliant architecture. The platform’s core architectural innovation is the embedding of Retrieval-Augmented Generation (RAG) directly within live HL7 FHIR R4 and DICOM infrastructure. Unlike offline RAG systems that operate on pre-exported or periodically updated datasets, SupportAI queries the Microsoft FHIR Server and Orthanc PACS at inference time, ensuring AI-generated responses always reflect the patient’s current multimodal record with full traceability to FHIR resource IDs and DICOM study UIDs. Additional contributions include Fourier frequency-domain imaging for anomaly detection beyond the spatial domain, an AI-assisted 3D bioprinting pipeline converting DICOM studies into patient-specific STL anatomical models, and a Jitsi-based telecollaboration infrastructure for multidisciplinary remote consultation. The platform comprises seven interconnected microservices: a Multimodal Data Source Module with automated ETL pipelines and GDPR pseudonymization; a FHIR Server organizing clinical information via RESTful APIs; an Orthanc PACS for DICOMweb-compatible image access; an Advanced 3D Imaging Module with GPU-accelerated Cornerstone3D rendering; a 3D Bioprinting Module supporting AI-assisted MONAI segmentation and manual VTK workflows for STL generation; an AI Module implementing LangChain-orchestrated generative assistance grounded in live clinical records; and a Collaboration Module providing Jitsi-based video consultation in virtual 3D laboratory environments. Security is enforced through TLS 1.3, OAuth 2.0/OpenID Connect, and role-based access control. Technical validation at Technology Readiness Level 6 was conducted using Apache JMeter with 10 concurrent virtual users. Results demonstrate platform robustness across all modules. 3D imaging visualization, AI segmentation, and FHIR patient reads achieved sub-15 ms mean response times; the 3D bioprinting pipeline completed end-to-end within minutes even for complex studies; and the generative chat pipeline averaged 23,629 ms, consistent with GPT-4-class deployments under equivalent context complexity. All eight tested configurations achieved a 0.00% error rate under concurrent load. Static code analysis (SonarQube) on the full 1,214k-line codebase achieved Quality Gate: Passed with zero open security issues. Functional correctness was confirmed through complete User Acceptance Testing across all modules and four representative clinical scenarios: 3D imaging and bioprinting, generative AI clinical assistance, AI-assisted image segmentation, and telecollaboration. Physician evaluators reported substantially increased trust in AI outputs due to transparent source attribution, and post-segmentation manual correction requirements were markedly reduced compared to purely manual workflows. These results confirm the technical feasibility of unified multimodal biomedical data integration within a standards-compliant clinical AI platform and establish SupportAI as a solid foundation for AI-powered decision support targeting personalized, accessible healthcare.