Attention-Deficit/Hyperactivity Disorder (ADHD) poses daily challenges for children and caregivers. This thesis designs a data-driven recommender system to deliver context- appropriate behavioural strategies and exercises. The work comprises: (i) a structured Compendium of Strategies; (ii) a prototype ABC (Antecedent–Behaviour–Consequence) feature for neutral, structured event recording that provides contextual input to the rec- ommendations; and (iii) a scorecard consolidating user growth, product adoption, and marketing indicators. While the scorecard does not measure data reliability directly, its engagement metrics provide an indirect view of dataset robustness. Recommendations combine two inputs—child conditions reported at registration and caregiver feedback on completed activities. Collaborative or hybrid methods remain limited by the current user base, but the resulting transparent, knowledge-based framework already supports personalisation and establishes a foundation for future adaptive systems.
Il Disturbo da Deficit di Attenzione e Iperattività (ADHD) comporta sfide quotidiane per bambini e caregiver. Questa tesi progetta un sistema di raccomandazione data- driven per offrire strategie comportamentali ed esercizi adeguati al contesto. Il lavoro comprende: (i) un Compendio di Strategie strutturato; (ii) un prototipo ABC (An- tecedente–Comportamento–Conseguenza) per la registrazione neutrale e strutturata degli eventi che fornisce input contestuali alle raccomandazioni; e (iii) una scorecard che consol- ida indicatori di crescita utenti, adozione del prodotto e marketing. Pur non misurando direttamente l’affidabilità, tali metriche di engagement offrono una vista indiretta della robustezza dei dati. Le raccomandazioni combinano condizioni del bambino riportate alla registrazione e feedback dei caregiver sulle attività. Gli approcci collaborativi restano limitati dall’attuale base utenti, ma il framework trasparente e knowledge-based supporta già la personalizzazione e pone le basi per futuri sistemi adattivi.
Data-driven recommender system design for supporting caregivers of children with ADHD
KOUCHAKI, HASTI
2024/2025
Abstract
Attention-Deficit/Hyperactivity Disorder (ADHD) poses daily challenges for children and caregivers. This thesis designs a data-driven recommender system to deliver context- appropriate behavioural strategies and exercises. The work comprises: (i) a structured Compendium of Strategies; (ii) a prototype ABC (Antecedent–Behaviour–Consequence) feature for neutral, structured event recording that provides contextual input to the rec- ommendations; and (iii) a scorecard consolidating user growth, product adoption, and marketing indicators. While the scorecard does not measure data reliability directly, its engagement metrics provide an indirect view of dataset robustness. Recommendations combine two inputs—child conditions reported at registration and caregiver feedback on completed activities. Collaborative or hybrid methods remain limited by the current user base, but the resulting transparent, knowledge-based framework already supports personalisation and establishes a foundation for future adaptive systems.| File | Dimensione | Formato | |
|---|---|---|---|
|
2025_10_Kouchaki.pdf
accessibile in internet solo dagli utenti autorizzati
Descrizione: Text of the thesis
Dimensione
2.16 MB
Formato
Adobe PDF
|
2.16 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/243523