Knowledge-Enhanced BERT for Aspect-Based Sentiment Analysis of Tourism Destinations Using Social Media Data
Received: 3 July 2025 | Revised: 13 September 2025 and 1 October 2025 | Accepted: 14 October 2025 | Online: 8 December 2025
Corresponding author: A. Irumporai
Abstract
Tourists are increasingly relying on social media platforms to share their impressions and ideas about various places. To improve customer satisfaction and service quality, tourism professionals must understand these sentiments. However, conventional methods of sentiment analysis often struggle to capture the subtle context and specific language of tourism content. Another factor that affects the accuracy of sentiment classification is the lack of integration of domain-specific knowledge. Using social media data, this study presents a Knowledge-Enhanced BERT (KE-BERT) model to analyze feelings about various things related to tourism destinations, with the aim of tackling the above challenges. The KE-BERT model enhances its understanding of aspect terms and sentiment within the BERT framework by incorporating knowledge from the tourism industry. A comprehensive dataset of social media reviews and comments on popular tourist destinations around the world was used. The training and evaluation of the KE-BERT model utilized several performance metrics, including accuracy, F1-score, recall, and precision. The experimental resultsshow that KE-BERT outperforms existing models, including traditional BERT- and LSTM-based models, achieving an accuracy of 92.7% and an F1 score of 91.5%.
Keywords:
aspect-based sentiment analysis, Knowledge-Enhanced BERT (KE-BERT), tourism destination, social media data, sentiment polarityDownloads
References
F. Mirzaalian and E. Halpenny, ''Exploring destination loyalty: Application of social media analytics in a nature-based tourism setting,''Journal of Destination Marketing & Management, vol. 20, June 2021, Art. no. 100598. DOI: https://doi.org/10.1016/j.jdmm.2021.100598
B. Shin, S. Ryu, Y. Kim, and D. Kim, ''Analysis on Review Data of Restaurants in Google Maps through Text Mining: Focusing on Sentiment Analysis,''Journal of Multimedia Information System, vol. 9, no. 1, pp. 61–68, 2022. DOI: https://doi.org/10.33851/JMIS.2022.9.1.61
M. Hoang, O. A. Bihorac, and J. Rouces, ''Aspect-Based Sentiment Analysis using BERT,'' in Proceedings of the 22nd Nordic Conference on Computational Linguistics, Turku, Finland, Sept. 2019, pp. 187–196.
H. Li, B. X. B. Yu, G. Li, and H. Gao, ''Restaurant survival prediction using customer-generated content: An aspect-based sentiment analysis of online reviews,''Tourism Management, vol. 96, June 2023, Art. no. 104707. DOI: https://doi.org/10.1016/j.tourman.2022.104707
J. Hartmann, M. Heitmann, C. Siebert, and C. Schamp, ''More than a Feeling: Accuracy and Application of Sentiment Analysis,''International Journal of Research in Marketing, vol. 40, no. 1, pp. 75–87, Mar. 2023. DOI: https://doi.org/10.1016/j.ijresmar.2022.05.005
O. A. George and C. M. Q. Ramos, ''Sentiment analysis applied to tourism: exploring tourist-generated content in the case of a wellness tourism destination,''International Journal of Spa and Wellness, vol. 7, no. 2, pp. 139–161, May 2024. DOI: https://doi.org/10.1080/24721735.2024.2352979
C. Sun, L. Huang, and X. Qiu, ''Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence.'' arXiv, Mar. 22, 2019.
B. Wan, P. Wu, C. K. Yeo, and G. Li, ''Emotion-cognitive reasoning integrated BERT for sentiment analysis of online public opinions on emergencies,''Information Processing & Management, vol. 61, no. 2, Mar. 2024, Art. no. 103609. DOI: https://doi.org/10.1016/j.ipm.2023.103609
M. M. Danyal, S. S. Khan, M. Khan, S. Ullah, F. Mehmood, and I. Ali, ''Proposing sentiment analysis model based on BERT and XLNet for movie reviews,''Multimedia Tools and Applications, vol. 83, no. 24, pp. 64315–64339, July 2024. DOI: https://doi.org/10.1007/s11042-024-18156-5
A. Booranakittipinyo, R. Y. M. Li, and N. Phakdeephirot, ''Travelers’ perception of smart airport facilities: An X (Twitter) sentiment analysis,''Journal of Air Transport Management, vol. 118, July 2024, Art. no. 102600. DOI: https://doi.org/10.1016/j.jairtraman.2024.102600
I. Karabila, N. Darraz, A. EL-Ansari, N. Alami, and M. ELMallahi, ''BERT-enhanced sentiment analysis for personalized e-commerce recommendations,''Multimedia Tools and Applications, vol. 83, no. 19, pp. 56463–56488, June 2024. DOI: https://doi.org/10.1007/s11042-023-17689-5
N. A. Alabdulkarim, M. A. Haq, and J. Gyani, ''Exploring Sentiment Analysis on Social Media Texts,''Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14442–14450, June 2024. DOI: https://doi.org/10.48084/etasr.7238
A. Bello, S.C. Ng, and M.F. Leung, ''A BERT Framework to Sentiment Analysis of Tweets,''Sensors, vol. 23, no. 1, Jan. 2023, Art. no. 506. DOI: https://doi.org/10.3390/s23010506
S. Yu, J. Su, and D. Luo, "Improving BERT-Based Text Classification With Auxiliary Sentence and Domain Knowledge," IEEE Access, vol. 7, pp. 176600–176612, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2953990
D. Araci, ''FinBERT: Financial Sentiment Analysis with Pre-trained Language Models.'' arXiv, Aug. 27, 2019.
Y. Gu et al., ''Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing,''ACM Transactions on Computing for Healthcare (HEALTH), vol. 3, no. 1, July 2021, Art. no. 2. DOI: https://doi.org/10.1145/3458754
''Social Media Sentiments Analysis Dataset .'' Kaggle, Available: https://www.kaggle.com/datasets/kashishparmar02/social-media-sentiments-analysis-dataset.
Downloads
How to Cite
License
Copyright (c) 2025 A. Irumporai, G. Anitha
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
