AI-driven insights into urban agriculture: Using youtube data to promote social resilience and self-sufficiency

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F25%3AA2603ANQ" target="_blank" >RIV/61988987:17310/25:A2603ANQ - isvavai.cz</a>

Výsledek na webu

<a href="https://linkinghub.elsevier.com/retrieve/pii/S2210670725001520" target="_blank" >https://linkinghub.elsevier.com/retrieve/pii/S2210670725001520</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.scs.2025.106275" target="_blank" >10.1016/j.scs.2025.106275</a>

Jazyk výsledku

angličtina

Název v původním jazyce

AI-driven insights into urban agriculture: Using youtube data to promote social resilience and self-sufficiency

Popis výsledku v původním jazyce

This study leverages YouTube as a rich data source to explore sustainable urban agriculture practices in small and underutilized yard areas. An innovative methodology integrates disparate data into a coherent dataset and employs deep learning techniques to analyze the coherence of visual and audio content. From 29 videos with similar content addressing self-sufficiency, 20,218 samples based on comments and 106,744 instances incorporating likes were selected. Sentiment scores were calculated using an ensemble approach combining Natural Language Processing and Neural Networks to enhance accuracy and reliability. Findings reveal a moderately positive sentiment towards urban agriculture initiatives, with weighted sentiment scores incorporating likes showing slightly higher positivity, though not significantly different in intensity. This comprehensive approach enhances accuracy by considering a larger population while maintaining dataset coherence. The comparison of positive and negative sentiments, along with weighted sentiments, indicates a faster growth in positive attitudes, highlighting an increasing acceptability of urban agriculture practices. These insights underscore the growing popularity of sustainable urban agriculture and the importance of considering weighted sentiment analysis for a nuanced understanding. This study contributes to the promotion of resilient cultivation practices in urban environments, offering valuable implications for policymakers and practitioners aiming to foster sustainable urban planning.

Název v anglickém jazyce

AI-driven insights into urban agriculture: Using youtube data to promote social resilience and self-sufficiency

Popis výsledku anglicky

This study leverages YouTube as a rich data source to explore sustainable urban agriculture practices in small and underutilized yard areas. An innovative methodology integrates disparate data into a coherent dataset and employs deep learning techniques to analyze the coherence of visual and audio content. From 29 videos with similar content addressing self-sufficiency, 20,218 samples based on comments and 106,744 instances incorporating likes were selected. Sentiment scores were calculated using an ensemble approach combining Natural Language Processing and Neural Networks to enhance accuracy and reliability. Findings reveal a moderately positive sentiment towards urban agriculture initiatives, with weighted sentiment scores incorporating likes showing slightly higher positivity, though not significantly different in intensity. This comprehensive approach enhances accuracy by considering a larger population while maintaining dataset coherence. The comparison of positive and negative sentiments, along with weighted sentiments, indicates a faster growth in positive attitudes, highlighting an increasing acceptability of urban agriculture practices. These insights underscore the growing popularity of sustainable urban agriculture and the importance of considering weighted sentiment analysis for a nuanced understanding. This study contributes to the promotion of resilient cultivation practices in urban environments, offering valuable implications for policymakers and practitioners aiming to foster sustainable urban planning.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50700 - Social and economic geography

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Sustainable Cities and Society

ISSN

2210-6707

e-ISSN

2210-6715

Svazek periodika

—

Číslo periodika v rámci svazku

1 April 2025

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

17

Strana od-do

—

Kód UT WoS článku

001447978100001

EID výsledku v databázi Scopus

—