| En/De/Fr/It- (first 9 out of 183 sentences)
[pdf] |
Srpski - (prvih 9 od 183 rečenica)
[pdf]
|
| n1 | ABSTRACT: This study presents the creation of a synthetic evaluation dataset for the Serbian SentiWordNet using Large Language Models (LLMs), specifically focusing on the Mistral model. | n1 | SAŽETAK: U radu se predstavlja izrada sintetičkog skupa za evaluaciju Srpskog SentiWordNet-a koja koristi velike jezičke modele, posebno model Mistral. |
| n2 | Addressing the scarcity of the sentiment analysis resources for Serbian, this research aims to bridge this gap by generating a dataset to evaluate and enhance sentiment analysis tools for Serbian. | n2 | Zbog nedostatka resursa za analizu sentimenta na srpskom jeziku, cilj istraživanja je premošćavanje ovog jaza generisanjem skupa za evaluaciju i unapređenje alata za analizu sentimenta na srpskom. |
| n3 | Sentiment polarity values from the English SentiWordNet were automatically mapped to Serbian WordNet via the Inter-Lingual Index (ILI). | n3 | Vrednosti polariteta sentimenta iz engleskog SentiWordNet-a automatski su mapirane na Srpski Vordnet. |
| n4 | To refine these values for better alignment with the Serbian language, a new evaluation dataset was created. | n4 | Kako bi se ove vrednosti preciznije prilagodile srpskom jeziku, kreiran je poseban skup za evaluaciju. |
| n5 | Initially, 500 synsets from the Serbian WordNet were selected based on their alignment with the senti-pol-sr lexicon and with the mapped values from SentiWordNet. | n5 | Inicijalno je odabrano 500 sinsetova iz Srpskog Vordneta, na osnovu njihove usklađenosti sa senti-pol-sr leksikonom i mapiranim vrednostima iz SentiWordNet-a. |
| n6 | These synsets underwent sentiment polarity classification using the Mistral model. | n6 | Ovi sinsetovi su klasifikovani prema polaritetu sentimenta korišćenjem Mistral-a. |
| n7 | A balanced subset of 75 synsets was then randomly extracted. It was further refined for sentiment gradation, and manually reviewed. | n7 | Izbalansirani podskup od 75 sinsetova nasumično je izdvojen, dodatno profinjen finijom gradacijom sentimenta i ručno pregledan. |
| n8 | The findings demonstrate a high model reliability, with approximately 93% of responses meeting the established acceptability criteria. | n8 | Rezultati pokazuju visoku preciznost, približno 93%. |
| n9 | KEYWORDS: SentiWordNet, synthetic dataset, Large Language Models, Serbian, sentiment analysis | n9 | KLjUČNE REČI: Analiza sentimenta, veliki jezički modeli, sintetički skup podataka, Srpski jezik, SentiWordNet |