Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights
In the age of social networks, user-generated content has become vital for organizations in tourism and hospitality. Traditional sentiment analysis methods often struggle to process large volumes of data and capture implicit sentiments. This study examines the potential of Aspect-Based Sentiment Ana...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of the Algarve - ESGHT - CIEO
2025-01-01
|
| Series: | Tourism & Management Studies |
| Subjects: | |
| Online Access: | https://www.tmstudies.net/index.php/ectms/article/view/2996 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554301390946304 |
|---|---|
| author | Mariana Água Nuno Antonio Marco P. Carrasco Carimo Rassal |
| author_facet | Mariana Água Nuno Antonio Marco P. Carrasco Carimo Rassal |
| author_sort | Mariana Água |
| collection | DOAJ |
| description | In the age of social networks, user-generated content has become vital for organizations in tourism and hospitality. Traditional sentiment analysis methods often struggle to process large volumes of data and capture implicit sentiments. This study examines the potential of Aspect-Based Sentiment Analysis (ABSA) using Large Language Models (LLMs) to enhance sentiment analysis. By employing GPT-4o via ChatGPT, we benchmark three approaches: a fuzzy logic-based method, manual human analysis, and a new ChatGPT-based analysis. We analyze a dataset of 500 all-inclusive hotel reviews, comparing these methods to assess ChatGPT's effectiveness in identifying nuanced language and handling subjectivity. The findings reveal a high similarity between ChatGPT and human analysis, showcasing ChatGPT’s ability to interpret complex sentiments and automate sentiment classification tasks. This study highlights the potential of LLMs in transforming customer feedback analysis, providing deeper insights, and improving responsiveness in the hospitality industry. These results contribute to academia by presenting a framework for using LLMs in ABSA and guiding future applications and development. |
| format | Article |
| id | doaj-art-08b5908597894da3b9bc678865e0f7ba |
| institution | Kabale University |
| issn | 2182-8466 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | University of the Algarve - ESGHT - CIEO |
| record_format | Article |
| series | Tourism & Management Studies |
| spelling | doaj-art-08b5908597894da3b9bc678865e0f7ba2025-01-08T14:40:43ZengUniversity of the Algarve - ESGHT - CIEOTourism & Management Studies2182-84662025-01-01211119Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer InsightsMariana Água 0Nuno Antonio 1Marco P. Carrasco 2Carimo Rassal 3NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Portugal NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa & Centre for Tourism Research, Development and Innovation (CiTUR), Portugal School of Management, Hospitality and Tourism (ESGHT), Universidade do Algarve & Centre for Tourism Research, Development and Innovation (CiTUR), Portugal School of Management, Hospitality and Tourism (ESGHT), Universidade do Algarve, & CIDEHUS - Interdisciplinary Center for History, Cultures, and Societies of the University of Évora, Portugal In the age of social networks, user-generated content has become vital for organizations in tourism and hospitality. Traditional sentiment analysis methods often struggle to process large volumes of data and capture implicit sentiments. This study examines the potential of Aspect-Based Sentiment Analysis (ABSA) using Large Language Models (LLMs) to enhance sentiment analysis. By employing GPT-4o via ChatGPT, we benchmark three approaches: a fuzzy logic-based method, manual human analysis, and a new ChatGPT-based analysis. We analyze a dataset of 500 all-inclusive hotel reviews, comparing these methods to assess ChatGPT's effectiveness in identifying nuanced language and handling subjectivity. The findings reveal a high similarity between ChatGPT and human analysis, showcasing ChatGPT’s ability to interpret complex sentiments and automate sentiment classification tasks. This study highlights the potential of LLMs in transforming customer feedback analysis, providing deeper insights, and improving responsiveness in the hospitality industry. These results contribute to academia by presenting a framework for using LLMs in ABSA and guiding future applications and development.https://www.tmstudies.net/index.php/ectms/article/view/2996automated sentiment analysisaspect-based sentiment analysislarge language modelscustomer feedback analysischatgpt applicationsnatural language processing |
| spellingShingle | Mariana Água Nuno Antonio Marco P. Carrasco Carimo Rassal Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights Tourism & Management Studies automated sentiment analysis aspect-based sentiment analysis large language models customer feedback analysis chatgpt applications natural language processing |
| title | Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights |
| title_full | Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights |
| title_fullStr | Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights |
| title_full_unstemmed | Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights |
| title_short | Large Language Models Powered Aspect-Based Sentiment Analysis for Enhanced Customer Insights |
| title_sort | large language models powered aspect based sentiment analysis for enhanced customer insights |
| topic | automated sentiment analysis aspect-based sentiment analysis large language models customer feedback analysis chatgpt applications natural language processing |
| url | https://www.tmstudies.net/index.php/ectms/article/view/2996 |
| work_keys_str_mv | AT marianaagua largelanguagemodelspoweredaspectbasedsentimentanalysisforenhancedcustomerinsights AT nunoantonio largelanguagemodelspoweredaspectbasedsentimentanalysisforenhancedcustomerinsights AT marcopcarrasco largelanguagemodelspoweredaspectbasedsentimentanalysisforenhancedcustomerinsights AT carimorassal largelanguagemodelspoweredaspectbasedsentimentanalysisforenhancedcustomerinsights |