- Data, Statistics and AI for Well-Being of People and Organisations
- A cura di Luigi Fabbris, Alberto Franci, Pietro Renzi
Topic modeling for monitoring perceived quality during the Jubilee 2025: A comparison between BERTopic and latent Dirichlet allocation
- Sandro Stancampiano
- © 2026 Author(s) |
- CC BY 4.0
- DOI: 10.36253/979-12-215-1062-1.67
The Jubilee 2025 is expected to attract millions of pilgrims to Rome, generating an unprecedented volume of user-generated content (UGC) through social media and online reviews. Unlike traditional surveys, reviews provide unsolicited and continuous feedback on visitors’ experiences, though their heterogeneity demands automated analysis. This study applies topic modeling to reviews of Roman churches, comparing Latent Dirichlet Allocation (LDA) with BERTopic. While LDA identifies broad thematic categories, BERTopic leverages semantic embeddings for more fine-grained distinctions. The contribution is threefold: (i) the design of a modular pipeline for UGC semantic analysis, (ii) a systematic comparison of statistical and neural approaches, and (iii) the demonstration of their relevance for monitoring perceived quality in large public events. Findings highlight insights into pilgrims’ experiences and suggest a scalable framework to support urban policy and service management during the Jubilee and beyond.
- Keywords:
- frailty,
- markov models,
- SHARE data,
ISTAT, Italian National Institute of Statistics, Italy - ORCID: 0009-0005-0571-0882
- Blei, D.M., Ng, A.Y., Jordan, M.I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3, pp. 993–1022. DOI: 10.7551/mitpress/1120.003.0082
- Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint, arXiv:2203.05794.
- Resch, B., Summa, A., Sagl, G., Zeile, P., Exner, J.P. (2015). Urban emotions—Geo-semantic emotion extraction from user-generated content for urban planning. GI_Forum 2015 – Geospatial Minds for Society, pp. 117–127. DOI: 10.1007/978-3-319-11879-6_14
- Röder, M., Both, A., Hinneburg, A. (2015). Exploring the space of topic coherence measures. Proceedings of the Eighth ACM International Conference on Web Search and Data Mining (WSDM), pp. 399–408. DOI: 10.1145/2684822.2685324
- Sievert, C., Shirley, K. (2014). LDAvis: A method for visualizing and interpreting topics. Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces, pp. 63–70. DOI: 10.3115/v1/w14-3110
- Xiang, Z., Gretzel, U. (2010). Role of social media in online travel information search. Tourism Management, 31(2), pp. 179–188. DOI: 10.1016/j.tourman.2009.02.016
Informazioni sul capitolo
Titolo del capitolo
Topic modeling for monitoring perceived quality during the Jubilee 2025: A comparison between BERTopic and latent Dirichlet allocation
Autori
Sandro Stancampiano
Lingua
Inglese
DOI
10.36253/979-12-215-1062-1.67
Opera sottoposta a peer review
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Informazioni bibliografiche
Titolo del libro
Data, Statistics and AI for Well-Being of People and Organisations
Curatori
Luigi Fabbris, Alberto Franci, Pietro Renzi
Opera sottoposta a peer review
Numero di pagine
420
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Editore
Firenze University Press
DOI
10.36253/979-12-215-1062-1
ISBN Print
979-12-215-1061-4
eISBN (pdf)
979-12-215-1062-1
eISBN (xml)
979-12-215-1063-8
Collana
Applied Statistics Series