Abstract
Over the past decade, although the global demand for cruise tourism has steadily increased, a decline in customer satisfaction has also emerged as a significant challenge. Quality function deployment (QFD) is an effective approach for transforming customer requirements into product or service quality characteristics, which helps to identify key customer needs and optimize service quality. Therefore, this study aims to apply the QFD model to provide practical recommendations for improving cruise service quality. To achieve this, the large language models (LLMs) combined with prompt engineering is first utilized to extract from online cruise reviews and conduct sentiment analysis. Then, the Kano model is applied to classify customer requirements and the weight balance coefficient is introduced to ensure a rational allocation of weights. Hence, a social network-based bilateral interaction consensus mechanism is developed to resolve opinion conflicts within the QFD decision making team, enabling consensus-driven decisions and deriving the final prioritization of quality characteristics. Finally, a real-world cruise case study is conducted to validate the proposed approach, supported by systematic analysis and discussion to highlight its advantages. Overall, this study establishes a QFD framework that integrates LLMs, Kano model and group consensus methods based on online cruise reviews, which provides a data-driven and adaptive solution for improving cruise service quality.
Similar content being viewed by others
Data availability
The data supporting the findings of this study are available within the supplementary files. Specifically, the following materials have been shared:- Original Dataset: 500 cruise reviews collected between February 2019 and December 2024, which can be found in the supplementary file labeled “raw_cruise_reviews_copy_20241121”.- Processed Data: The corresponding sentiment analysis output data is available in the supplementary file labeled “SA_output_data”.
References
Ahn H, Park E (2023) Motivations for user satisfaction of mobile fitness applications: an analysis of user experience based on online review comments. Humanities and Social Sciences. Communications 10:1–7
Ali BJ, Gardi B, Othman BJ, Ahmed SA, Ismael NB, Hamza PA, Aziz HM, Sabir BY, Sorguli S, Anwar G (2021) Hotel service quality: The impact of service quality on customer satisfaction in hospitality. International Journal of Engineering. Bus Manag 5:14–28
Anas M (2024) Customer satisfaction in the hotel industry: a case study from Makassar City. J Econ Educ Entrep Stud 5:135–150
Bondy JA, Murty USR (1976) Graph theory with applications. Vol. 290: Macmillan London
Cao M, Chiclana F, Liu Y, Wu J, Herrera-Viedma E (2024) A bilateral negotiation mechanism by dynamic harmony threshold for group consensus decision making. Eng Appl Artif Intell 133:108225
Cao M, Gai T, Wu J, Chiclana F, Zhang Z, Dong Y, Herrera-Viedma E, Herrera F (2025) Social network group decision making: characterization, taxonomy, challenges and future directions from an AI and LLMs perspective. Inf Fusion 120:103107
Castillo-Manzano JI, Castro-Nuño M, Pozo-Barajas R (2022) Addicted to cruises? Key drivers of cruise ship loyalty behavior through an e-WOM approach. Int J Contemp Hosp Manag 34:361–381
Chandra T, Putra R (2021) Service quality and brand image on customer satisfaction and customer loyalty at Pesonna Hotel Pekanbaru. J Appl Bus Technol 2:142–153
Chen Y, Ran Y, Huang G, Xiao L, Zhang G (2021) A new integrated MCDM approach for improving QFD based on DEMATEL and extended MULTIMOORA under uncertainty environment. Appl Soft Comput 105:107222
Chrysafis KA, Papadopoulou GC, Theotokas IN (2024) Measuring financial performance through operating business efficiency in the global cruise industry: a fuzzy benchmarking study on the “big three”. Tour Manag 100:104830
Dagdelen J, Dunn A, Lee S, Walker N, Rosen AS, Ceder G, Persson KA, Jain A (2024) Structured information extraction from scientific text with large language models. Nat Commun 15: 1418
Dong Y, Ding Z & Kou G (2024) Social network DeGroot model. Springer Books
Fang H, Li J, Song W (2020) A new method for quality function deployment based on rough cloud model theory. IEEE Trans Eng Manag 69:2842–2856
Gai T, Wu J, Liang C, Cao M, Zhang Z (2024a) A quality function deployment model by social network and group decision making: application to product design of e-commerce platforms. Eng Appl Artif Intell 133:108509
Gai T, Wu J, Chiclana F, Cao M, Yager RR (2024b) Dynamic compromise behavior driven bidirectional feedback mechanism for group consensus with overlapping communities in social network. IEEE Trans Syst, Man Cybern Syst 54:6149–6161
Guo W, Wang H, Zhang W-G, Gong Z, Xu Y, Słowiński R (2024) Multi-dimensional multi-round minimum cost consensus models with iterative mechanisms involving reward and punishment measures. Knowl Based Syst 293:111710
He L, Wu Z, Xiang W, Goh M, Xu Z, Song W, Ming X, Wu X (2021) A novel Kano-QFD-DEMATEL approach to optimise the risk resilience solution for sustainable supply chain. Int J Prod Res 59:1714–1735
Ji F, Cao Q, Li H, Fujita H, Liang C, Wu J (2023) An online reviews-driven large-scale group decision making approach for evaluating user satisfaction of sharing accommodation. Expert Syst Appl 213:118875
Ji F, Wu J, Chiclana F, Sun Q, Liang C, Herrera-Viedma E (2025) Supporting group cruise decisions with online collective wisdom: an integrated approach combining review helpfulness analysis and consensus in social networks. Inf Process Manag 62:103936
Jiao Y, Lau Y-y, Gao J (2024) Exploring the factors affecting cruise passengers’ perceptions of value for money expressed in online reviews. Humanities and Social Sciences. Communications 11:1–11
Kano N, Seraku N, Takahashi F & Tsuji S (1984) Attractive quality and must-be quality. J Japn Soc Qual Control 14:147–156
Li S, Tang D, Wang Q (2019) Rating engineering characteristics in open design using a probabilistic language method based on fuzzy QFD. Comput Ind Eng 135:348–358
Liu H-C, Wu S-M, Wang Z-L, Li X-Y (2019) A new method for quality function deployment with extended prospect theory under hesitant linguistic environment. IEEE Trans Eng Manag 68:442–451
Liu P, Zhang K, Dong X, Wang P (2022) A big data-Kano and SNA-CRP based QFD model: application to product design under Chinese new E-commerce model. IEEE Trans Eng Manag 71:4246–4260
Liu P, Li Y, Wang P (2023) Social trust-driven consensus reaching model for multiattribute group decision making: exploring social trust network completeness. IEEE Trans Fuzzy Syst 31:3040–3054
Ma W, Ji F, Liang C, Sun Q, Wu J (2024) A deep learning and large group consensus based cruise satisfaction evaluation model with online reviews. Inf Sci 676:120801
Qorib M, Oladunni T, Denis M, Ososanya E, Cotae P (2023) Covid-19 vaccine hesitancy: text mining, sentiment analysis and machine learning on COVID-19 vaccination Twitter dataset. Expert Syst Appl 212:118715
Perdomo-Verdecia V, Garrido-Vega P, Sacristán-Díaz M (2024) An fsQCA analysis of service quality for hotel customer satisfaction. Int J Hosp Manag 122:103793
PJ S, Singh K, Kokkranikal J, Bharadwaj R, Rai S, Antony J (2023) Service quality and customer satisfaction in hospitality, leisure, sport and tourism: an assessment of research in Web of Science. J Qual Assur Hosp Tour 24:24–50
Sardesai S, D’Souza E, Govekar S (2024) Analysing the impacts of artificial intelligence service quality and human service quality on customer satisfaction and customer loyalty in the hospitality sector. Turizam 28:37–48
Sun X, Kwortnik R, Xu M, Lau Y-Y, Ni R (2021) Shore excursions of cruise destinations: product categories, resource allocation, and regional differentiation. J Destin Mark Manag 22:100660
Sun X, Cao X, Lau Y-Y (2023) Exploring cruise tourists’ sentiment expression pattern from online reviews: an insight into market positioning. Tour Manag Perspect 49:101195
Suresh Kumar K, Radha Mani A, Ananth Kumar T, Jalili A, Gheisari M, Malik Y, Chen H-C, Jahangir Moshayedi A (2024) Sentiment analysis of short texts using SVMs and VSMs-based multiclass semantic classification. Appl Artif Intell 38:2321555
Tiutiu M, Nemțeanu S, Dabija D-C, Pelau C (2025) The impact of online customer service and store features on consumer experience and willingness to revisit their preferred online store. Human Soc Sci Commun 12:1–13
Venugopalan M, Gupta D (2022) An enhanced guided LDA model augmented with BERT based semantic strength for aspect term extraction in sentiment analysis. Knowl -based Syst 246:108668
Victor P, Cornelis C, De Cock M, Da Silva PP (2009) Gradual trust and distrust in recommender systems. Fuzzy Sets Syst 160:1367–1382
Wan B, Wu P, Yeo CK, Li G (2024) Emotion-cognitive reasoning integrated BERT for sentiment analysis of online public opinions on emergencies. Inf Process Manag 61:103609
Wang J, Liu H-C, Zhang J, Shi H, Zhang Q-Z (2024) New approach for quality function development based on cooperative game-based consensus mechanism and three-way decision method. Int J Prod Econ 276:109380
Wang Q, Zhang W, Li J, Mai F, Ma Z (2024) The devil is in the details! Effect of differentiated platform governance on online review manipulation. Human Soc Sci Commun 11:1–14
Wasserman S (1994) Social network analysis: methods and applications. The Press Syndicate of the University of Cambridge
Wu H, Zhang Z, Shi S, Wu Q, Song H (2022) Phrase dependency relational graph attention network for aspect-based sentiment analysis. Knowl Based Syst 236:107736
Wu T, Liu X, Qin J, Herrera F (2021) An interval type-2 fuzzy Kano-prospect-TOPSIS based QFD model: application to Chinese e-commerce service design. Appl Soft Comput 111:107665
Xu Y, Ju Y, Gong Z, Sun J, Dong P, Ju T, Herrera-Viedma E (2024) Improving consensus in social network group decision-making: emphasizing overlapping subgroups and interactive behaviors. Inf Sci 679:121065
Yang Q, Chen Z-S, Zhu J-H, Martínez L, Pedrycz W, Skibniewski MJ (2024) Concept design evaluation of sustainable product–service systems: a QFD–TOPSIS integrated framework with basic uncertain linguistic information. Group Decis Negot 33:469–511
Yu G, Zhang Z, Wu J (2025) A stability analysis for the online retailing cyber security situation piecewise variable weight rating method. Appl Intell 55:1144
Zha Q, Liang H, Kou G, Dong Y, Yu S (2019) A feedback mechanism with bounded confidence-based optimization approach for consensus reaching in multiple attribute large-scale group decision-making. IEEE Trans Comput Soc Syst 6:994–1006
Zhang Y, Yang X, Xu X, Gao Z, Huang Y, Mu S, Feng S, Wang D, Zhang Y, Song K (2024) Affective computing in the era of large language models: a survey from the NLP perspective. arXiv Prepr arXiv 2408:04638
Zhou X, Li S, Wei C (2024) Consensus reaching process for group decision-making based on trust network and ordinal consensus measure. Inf Fusion 101:101969
Acknowledgements
This work was sponsored by National Natural Science Foundation of China (NSFC) (Nos.72471137 and 72561015), China Scholarship Council (202408310287), and Innovative Talent Training Project of Graduate Students in Shanghai Maritime University of China (No.2023YBR002).
Author information
Authors and Affiliations
Contributions
Tiantain Gai: Data curation, Writing—Original draft preparation, Data collection. Jian Wu: Method, supervision, funding, writing, reviewing. YumeiXing: Methodology. Yujia Liu: Conceptualization, polishing english. Mingshuo Cao: Methodology, Rewriting of the draft.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
Ethical approval was not required for this study. This research does not involve human participants, experimental interventions, or personally identifiable data. The study relies exclusively on the observational, secondary analysis of 500 publicly available cruise reviews crawled from a public website between February 2019 and December 2024. According to the Trial Measures for Ethical Review of Science and Technology (issued by the Ministry of Science and Technology of the People’s Republic of China in 2023), research involving the secondary analysis of existing, legally obtained, and publicly accessible data where human subjects cannot be identified is not classified as human subjects research requiring ethical oversight. Because this study falls outside the regulatory scope of institutional ethical review, formal ethical approval and institutional waiver processes are not applicable.
Informed consent
Informed consent was not applicable for this study. The research does not involve direct interaction with any individuals. The dataset consists solely of pre-existing, publicly accessible online reviews voluntarily posted by users in the public domain. According to Article 27 of the Personal Information Protection Law of the People’s Republic of China (PIPL), personal information handlers may process personal information disclosed by the individuals themselves or otherwise legally disclosed within a reasonable scope without requiring explicit consent. All data extracted between February 2019 and December 2024 were strictly anonymized prior to analysis, and no personally identifiable information (PII) was collected. Therefore, the requirement for obtaining informed consent is legally and practically waived.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Gai, T., Wu, J., Xing, Y. et al. Cruise service quality improvement: a quality function deployment approach with online reviews by large language models. Humanit Soc Sci Commun (2026). https://doi.org/10.1057/s41599-026-06941-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1057/s41599-026-06941-6
