Predicting equine behavior from small datasets using machine learning with LLM-generated explanations

Topal, Oleksandra (avtor), Novalija, Inna (avtor), Mladenić, Dunja (avtor), Gobbo, Elena (avtor), Zupan Šemrov, Manja (avtor)

Understanding horse fearfulness is crucial for building strong human–animal relationships, influencing training methods, task selection, and predicting reactions to new stimuli. This interdisciplinary study aimed to identify key characteristics for predicting a horse’s fearfulness. Using classical machine learning, we analyzed anatomical, kinematic, and housing-related data from 49 horses, with fear scores obtained through a standardized behavioral test. To ensure an unbiased evaluation, the leave-one-out cross-validation method was applied. The study’s main contributions are: (1) an iterative feature selection approach that reduces the number of required measurements while maintaining prediction accuracy; (2) a unique dataset on Lipizzan horses, revealing that head and body anatomical characteristics are critical for assessing fearfulness; (3) identification of the Decision Tree algorithm as the most accurate machine learning method for modeling fearfulness; (4) integration of Large Language Models (LLMs) to generate clear, interpretable textual explanations of the Decision Tree, improving the understanding of key predictive features. This study bridges behavioral science and artificial intelligence, offering a novel AI-driven approach to equine behavior analysis, with practical applications in horse training, selection, and welfare management.

• Jezik: Angleški jezik
• Ključne besede: machine learning, Lipizzan horses, data analysis, horse fearfulness, supervised learning, horse welfare
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: BF - Biotehniška fakulteta
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Datum objave: 06.11.2025
• Leto izida: 2025
• Št. strani: 13 str.
• Številčenje: Vol. 293, [article no.] ǂ106863
• PID: 20.500.12556/RUL-175824
• UDK: 636.1:591.5
• ISSN pri članku: 1872-9045
• DOI: 10.1016/j.applanim.2025.106863
• COBISS.SI-ID: 256506115
• Datum objave v RUL: 10.11.2025

Gradivo je del revije

• Naslov: Applied animal behaviour science
• Skrajšan naslov: Appl. anim. behav. sci.
• Založnik: Elsevier
• ISSN: 1872-9045
• COBISS.SI-ID: 23187973

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: konji, obnašanje živali, etologija, plašnost, strojno učenje, umetna inteligenca

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: J7-3154-2021
• Naslov: Povezovanje želenih fenotipskih lastnosti na podlagi meritev obnašanja in anatomskih ter fizioloških lastnosti z genetskimi markerji pri lipicancih