Generazione automatica di una knowledge base con applicazione ai Sustainable Development Goals

Questa tesi di laurea compie uno studio sull’ utilizzo di tecniche di web crawling, web scraping e Natural Language Processing per costruire automaticamente un dataset di documenti e una knowledge base di coppie verbo-oggetto utilizzabile per la classificazione di testi. Dopo una breve introduzione sulle tecniche utilizzate verrà presentato il metodo di generazione, prima in forma teorica e generalizzabile a qualunque classificazione basata su un insieme di argomenti, e poi in modo specifico attraverso un caso di studio: il software SDG Detector. In particolare quest ultimo riguarda l’applicazione pratica del metodo esposto per costruire una raccolta di informazioni utili alla classificazione di documenti in base alla presenza di uno o più Sustainable Development Goals. La parte relativa alla classificazione è curata dal co-autore di questa applicazione, la presente invece si concentra su un’analisi di correttezza e performance basata sull’espansione del dataset e della derivante base di conoscenza.

Portofino Seaweed Garden: a local citizen science case study on Ericaria amentacea (C.Agardh) Molinari & Guiry, 2020 restoration

Ericaria amentacea is an endemic alga of the Mediterranean Sea that lives in the littoral rocky fringe. The species is sensitive to environmental changes, so it’s used to assess the water ecological quality. Nevertheless, E. amentacea is deeply impacted by coastal development which cause rapid regression despite data on its distribution and healthy status are still limited. Moreover, it’s little known by people outside the scientific community. In this context, Portofino Seaweed Garden was born, a conservation and citizen science project aim to involve marine outdoor enthusiasts in protecting and restoring E. amentacea, creating a submerged garden. Restoration measures have been encouraged by EU regulations. Here, using citizen science, 1) I evaluated the spatial variability of E. amentacea abundance along the central-eastern Ligurian coast, to evaluate its status and choose donor and restoration sites. 2) I carried out an E. amentacea restoration (with outplanting lab-cultured embryos on 50 clay tiles). 3) I assessed the community involvement and education of volunteers. Simple protocol was created to train them on the monitoring. Unprecedented E. amentacea reproductive mismatch affected the restoration performance, probably caused by marine heat wave that hit the Mediterranean in summer 2022. After fertile apices collection in Pontetto (GE) and during laboratory phase, gametes spawned on the discs didn’t settle as expected. Only 16 tiles showed juveniles and they were outplanted at Punta Castello (C zone of Portofino MPA). Unfortunately, they didn’t survive in the field due to an interplay of physical and biological factors. From citizen science point of view, the project demonstrated positive outcomes of collaborations between people and scientists by involving more than 100 participants. Citizen scientists became specialize in the protocol providing quality data for E. amentacea conservation. Current results suggest that outplanting should be further tested.