Just Accepted Manuscripts
Articles

Mining Users’ Perceptions through Sentiment and Emotion Analysis to Address Heritage Conservation Strategies

PDF
  • Marco D'Orazio,
  • Elisa Di Giuseppe,
  • Maria Francesca Muccioli
Marco D'Orazio
Università Politecnica delle Marche
Elisa Di Giuseppe
Università Politecnica delle Marche
Maria Francesca Muccioli
Università Politecnica delle Marche
DOI: https://doi.org/10.36253/tema-16921

Published 2025-11-28

Keywords

  • Architectural heritage,
  • Heritage monitoring,
  • Resources allocation,
  • User sentiment,
  • User emotion

Abstract

Monitoring architectural heritage is a crucial step in the planning of proper conservation strategies and resource allocation. Current protocols rely on periodic, though infrequent, expert-led inspections, which assess the state of conservation of heritage assets and inform intervention priorities. However, public perceptions, which may suggest alternative courses of action, are seldom considered. This study proposes an innovative methodology integrating public feedback into heritage monitoring via Natural Language Processing (NLP). The framework, applied to ‘70s heritage sites in Italy’s Marche region, integrates Aspect-Based Sentiment Analysis (ABSA) and Aspect-Based Emotion Analysis (ABEA) to systematically analyze user-generated content, identifying heritage-related aspects and classifying sentiment (positive, negative, neutral) and emotions (e.g., joy, anger) from Google Maps reviews. Heritage-specific targets were first identified in user reviews using spaCy-based tokenization. Sentiment classification (positive, negative, neutral) was performed using a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model, while emotions (joy, anger, sadness, fear) were identified using the FEEL-IT algorithm. User perceptions were effectively retrieved, revealing a generally positive sentiment and joy as the most dominant emotion. This approach enables large-scale monitoring based on continuously updated user feedback, which can be integrated into current monitoring protocols to adopt a more comprehensive decision-making approach.

PDF

References

  1. [1] Stovel H (2004) Monitoring world heritage. In: International Congress on World Heritage 2002: Shared Legacy, Common Responsibility, Venice, 2002. UNESCO World Heritage Centre and ICCROM, Venice
  2. [2] Kioussi A, Karoglou M, Labropoulos K, et al (2013) Integrated documentation protocols enabling decision making in cultural heritage protection. J Cult Herit 14:e141–e146. https://doi.org/10.1016/j.culher.2013.01.007
  3. [3] Li J, Krishnamurthy S, Pereira Roders A, van Wesemael P (2020) Community participation in cultural heritage management: A systematic literature review comparing Chinese and international practices. Cities 96:. https://doi.org/10.1016/j.cities.2019.102476
  4. [4] Foroughi M, de Andrade B, Pereira Roders A (2023) Capturing public voices: The role of social media in heritage management. Habitat Int 142:102934. https://doi.org/10.1016/j.habitatint.2023.102934
  5. [5] Liu B (2015) Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge University Press
  6. [6] Nandwani P, Verma R (2021) A review on sentiment analysis and emotion detection from text. Soc Netw Anal Min 11:1–19. https://doi.org/10.1007/s13278-021-00776-6
  7. [7] D’Orazio M, Di Giuseppe E, Bernardini G (2022) Automatic detection of maintenance requests: Comparison of Human Manual Annotation and Sentiment Analysis techniques. Autom Constr 134:104068. https://doi.org/10.1016/j.autcon.2021.104068
  8. [8] D’Orazio M, Di Giuseppe E, Bernardini G (2023) End-user’s perception of the state of the building systems through sentiment and emotion analysis methods. Transizione sfide e Oppor per l’ambiente Costr Transit challenges Oppor build Herit 859–870
  9. [9] Rosin U, Bonazzi M, Casarin F, others (2022) eWom and sentiment analysis to support decision processes within maritime heritage museum networks. The case of Arca Adriatica. In: Proceedings of 16th International AIMAC Conference on Arts and Cultural Management
  10. [10] Hutto C, Gilbert E (2014) VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. Proc Int AAAI Conf Web Soc Media 8:216–225. https://doi.org/10.1609/icwsm.v8i1.14550
  11. [11] Mendes MP, Torres-González M, Valença J, Silva A (2022) The Maintenance of Monuments as the Main Trigger to Negative Feelings in Tourists. Buildings 12:. https://doi.org/10.3390/buildings12122153
  12. [12] Ginzarly M, Srour FJ, Roders AP (2022) The Interplay of Context, Experience, and Emotion at World Heritage Sites: a Qualitative and Machine Learning Approach. Tour Cult Commun 22:321–340. https://doi.org/10.3727/109830421X16345418234065
  13. [13] Valdivia A, Martínez-Cámara E, Chaturvedi I, et al (2020) What do people think about this monument? Understanding negative reviews via deep learning, clustering and descriptive rules. J Ambient Intell Humaniz Comput 11:39–52. https://doi.org/10.1007/s12652-018-1150-3
  14. [14] Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL HLT 2019 - 2019 Conf North Am Chapter Assoc Comput Linguist Hum Lang Technol - Proc Conf 1:4171–4186
  15. [15] Loyola M (2018) Big data in building design: A review. J Inf Technol Constr 23:259–284
  16. [16] Bianchi F, Nozza D, Hovy D (2021) FEEL-IT: Emotion and Sentiment Classification for the Italian Language. In: WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop. pp 76–83
  17. [17] Spacy.Io. https://spacy.io/. Accessed 8 Jul 2024
  18. [18] nlptown (2020) bert-base-multilingual-uncased-sentiment. In: Hugging Face. https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment. Accessed 6 Jul 2024
  19. [19] Ekman P (1992) Basic Emotions. In: Encyclopedia of Personality and Individual Differences. pp 1–6
  20. [20] Almeida AMG, Cerri R, Paraiso EC, et al (2018) Applying multi-label techniques in emotion identification of short texts. Neurocomputing 320:35–46. https://doi.org/10.1016/j.neucom.2018.08.053
  21. [21] Marche R Patrimonio culturale. In: Reg. Marche. https://www.regione.marche.it/Regione-Utile/Cultura/Patrimonio-culturale
  22. [22] ICCD Catalogo generale dei Beni Culturali. https://www.catalogo.beniculturali.it/. Accessed 16 Apr 2024
  23. [23] Mancinelli ML (2018) Gli standard catalografici dell’Istituto Centrale per il Catalogo e la Documentazione. In: Le voci, le opere e le cose. La catalogazione dei beni culturali demoetnoantropologici. pp 279–302
  24. [24] dati.cultura.gov.it. In: dati.cultura.gov.it. https://dati.cultura.gov.it/. Accessed 29 Apr 2024
  25. [25] Picone R (2012) Il rudere architettonico nella storia del restauro. CONFRONTI 27–40