FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381614911> ?p ?o ?g. }

• W4381614911 abstract "<sec> <title>BACKGROUND</title> Healthcare providers and health-related researchers face significant challenges when applying sen- timent analysis tools to health-related free-text survey data. Most state-of-the-art applications were developed in domains like social media, and their performance in the healthcare context remains relatively unknown. Moreover, existing studies indicate that these tools often lack accuracy and produce inconsistent results. </sec> <sec> <title>OBJECTIVE</title> This study aims to address the lack of comparative analysis on sentiment analysis tools applied to health-related free-text survey data in the context of COVID-19. The objective is to automatically predict sentence sentiment for two independent COVID-19 survey datasets from NIH and Stanford University. </sec> <sec> <title>METHODS</title> Gold-standard labels were created for a subset of each dataset using a panel of human raters. We compared eight state-of- the-art sentiment analysis tools on both datasets to evaluate variability and disagreement across tools. Additionally, few-shot learning was explored by fine-tuning OPT (a large language model [LLM] with publicly available weights) using a small annotated subset and zero-shot learning using ChatGPT (an LLM without available weights). </sec> <sec> <title>RESULTS</title> The comparison of sentiment analysis tools revealed high variability and disagreement across the evaluated tools when applied to health-related survey data. OPT and ChatGPT demonstrated superior performance, outperform- ing all other sentiment analysis tools. Moreover, ChatGPT exhibited higher accuracy, outperforming OPT by 6%, and f-score by 4% to 7%. </sec> <sec> <title>CONCLUSIONS</title> The findings suggest that using LLMs is a viable method for predicting sentiment in health surveys. The comparative analysis highlights the potential of LLMs in reducing the need for human labor in dataset annotation or redeploying it toward quality control of LLM predictions. The study demonstrates the effectiveness of LLMs, particularly the few-shot learning and zero-shot learning approaches, in sentiment analysis of health-related survey data. These results have implications for saving hu- man labor and improving efficiency in sentiment analysis tasks, contributing to advancements in the field of automated sentiment analysis. </sec>" @default.
• W4381614911 created "2023-06-23" @default.
• W4381614911 creator A5005082781 @default.
• W4381614911 creator A5011754983 @default.
• W4381614911 creator A5026151796 @default.
• W4381614911 creator A5041962211 @default.
• W4381614911 creator A5042047082 @default.
• W4381614911 creator A5055888839 @default.
• W4381614911 creator A5062151713 @default.
• W4381614911 creator A5079554685 @default.
• W4381614911 date "2023-06-21" @default.
• W4381614911 modified "2023-09-26" @default.
• W4381614911 title "Sentiment Analysis of COVID-19 Survey Data: A Comparison of ChatGPT and Fine-tuned OPT Against Widely Used Sentiment Analysis Tools (Preprint)" @default.
• W4381614911 doi "https://doi.org/10.2196/preprints.50150" @default.
• W4381614911 hasPublicationYear "2023" @default.
• W4381614911 type Work @default.
• W4381614911 citedByCount "0" @default.
• W4381614911 crossrefType "posted-content" @default.
• W4381614911 hasAuthorship W4381614911A5005082781 @default.
• W4381614911 hasAuthorship W4381614911A5011754983 @default.
• W4381614911 hasAuthorship W4381614911A5026151796 @default.
• W4381614911 hasAuthorship W4381614911A5041962211 @default.
• W4381614911 hasAuthorship W4381614911A5042047082 @default.
• W4381614911 hasAuthorship W4381614911A5055888839 @default.
• W4381614911 hasAuthorship W4381614911A5062151713 @default.
• W4381614911 hasAuthorship W4381614911A5079554685 @default.
• W4381614911 hasConcept C124101348 @default.
• W4381614911 hasConcept C136764020 @default.
• W4381614911 hasConcept C142724271 @default.
• W4381614911 hasConcept C154945302 @default.
• W4381614911 hasConcept C166957645 @default.
• W4381614911 hasConcept C205649164 @default.
• W4381614911 hasConcept C23123220 @default.
• W4381614911 hasConcept C2522767166 @default.
• W4381614911 hasConcept C2777530160 @default.
• W4381614911 hasConcept C2779134260 @default.
• W4381614911 hasConcept C2779343474 @default.
• W4381614911 hasConcept C3008058167 @default.
• W4381614911 hasConcept C41008148 @default.
• W4381614911 hasConcept C43169469 @default.
• W4381614911 hasConcept C524204448 @default.
• W4381614911 hasConcept C66402592 @default.
• W4381614911 hasConcept C71472368 @default.
• W4381614911 hasConcept C71924100 @default.
• W4381614911 hasConceptScore W4381614911C124101348 @default.
• W4381614911 hasConceptScore W4381614911C136764020 @default.
• W4381614911 hasConceptScore W4381614911C142724271 @default.
• W4381614911 hasConceptScore W4381614911C154945302 @default.
• W4381614911 hasConceptScore W4381614911C166957645 @default.
• W4381614911 hasConceptScore W4381614911C205649164 @default.
• W4381614911 hasConceptScore W4381614911C23123220 @default.
• W4381614911 hasConceptScore W4381614911C2522767166 @default.
• W4381614911 hasConceptScore W4381614911C2777530160 @default.
• W4381614911 hasConceptScore W4381614911C2779134260 @default.
• W4381614911 hasConceptScore W4381614911C2779343474 @default.
• W4381614911 hasConceptScore W4381614911C3008058167 @default.
• W4381614911 hasConceptScore W4381614911C41008148 @default.
• W4381614911 hasConceptScore W4381614911C43169469 @default.
• W4381614911 hasConceptScore W4381614911C524204448 @default.
• W4381614911 hasConceptScore W4381614911C66402592 @default.
• W4381614911 hasConceptScore W4381614911C71472368 @default.
• W4381614911 hasConceptScore W4381614911C71924100 @default.
• W4381614911 hasLocation W43816149111 @default.
• W4381614911 hasOpenAccess W4381614911 @default.
• W4381614911 hasPrimaryLocation W43816149111 @default.
• W4381614911 hasRelatedWork W2175120218 @default.
• W4381614911 hasRelatedWork W2911752708 @default.
• W4381614911 hasRelatedWork W3084937509 @default.
• W4381614911 hasRelatedWork W3198674709 @default.
• W4381614911 hasRelatedWork W3206224646 @default.
• W4381614911 hasRelatedWork W4205110123 @default.
• W4381614911 hasRelatedWork W4205691910 @default.
• W4381614911 hasRelatedWork W4281761953 @default.
• W4381614911 hasRelatedWork W4378901338 @default.
• W4381614911 hasRelatedWork W4380536702 @default.
• W4381614911 isParatext "false" @default.
• W4381614911 isRetracted "false" @default.
• W4381614911 workType "article" @default.