Progress on image analytics: Implications for tourism and hospitality research

Zhan, Lingxue; Cheng, Mingming; Zhu, Jingjie

doi:10.1016/j.tourman.2023.104798

Cited by 20 publications

(3 citation statements)

References 135 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In doing so, we contribute to the ongoing discourse on text-image inconsistency and respond to the growing interest in exploring interactions between text and image (Hou and Pan, 2023;Li et al, 2023). Moreover, we introduce the concept of utilizing multimodal deep learning for sentiment detection, where our GCN model outperforms the baseline model, demonstrating the value of incorporating sentiment features from images (Zhan et al, 2024). Our proposed framework holds the potential for extension to other domains and provides valuable insights for consumer behavior research.…”

Section: Theoretical Implicationsmentioning

confidence: 97%

See 1 more Smart Citation

Sarcasm detection in hotel reviews: a multimodal deep learning approach

Liu,

Chi,

Sun

2024

JHTT

View full text Add to dashboard Cite

Purpose This study aims to detect consumer sarcasm through inconsistencies in sentiment features between text and images of hotel reviews. Design/methodology/approach This paper proposes a model for sarcasm detection based on multimodal deep learning using reviews of three hotel brands collected from two travel platforms, which can identify emotional inconsistencies within a modality and across modalities. Text-image interaction information is explored using graph neural networks (GNN) to detect essential clues in sarcasm sentiment. Findings The research results show that the multimodal deep learning model outperforms other baseline models, which can help to understand hotel service evaluation and provide hotel managers with decision-making opinions. Originality/value This research can help hoteliers in two ways: detecting service quality and formulating strategies. By selecting reference hotel brands, hoteliers can better assess their level of service quality (optimal resource allocation ensues); therefore, sarcasm detection research is not only beneficial for hotel managers seeking to improve service quality. The multimodal deep learning method introduced in the present study can be replicated in other industries to help travel platforms optimize their products and services.

show abstract

Section: Theoretical Implicationsmentioning

confidence: 97%

“…There is no consensus on the most effective sarcasm detection in consumer reviews in existing literature (Zhan et al , 2024). Although deep learning methods achieve higher accuracy in detection, multimodal data limit their practical capabilities.…”

Section: Introductionmentioning

confidence: 99%

Sarcasm detection in hotel reviews: a multimodal deep learning approach

Liu,

Chi,

Sun

2024

JHTT

View full text Add to dashboard Cite

show abstract

“…For example, photos of dishes from an upscale restaurant do not show simple ingredients but rather represent the distinctiveness and sophistication of haute cuisine. In this area, computerized image recognition and analysis techniques (i.e., image analytics) have advanced significantly in recent years [20].…”

Section: Introductionmentioning

confidence: 99%

Destination Image Semiotics: Evidence from Asian and European Upscale Hospitality Services

Marine-Roig

2024

Tourism and Hospitality

View full text Add to dashboard Cite

Given the importance of semiotics and destination image (TDI) in the field of tourism and hospitality marketing, this study proposes a conceptual model that integrates Peirce’s semiotic triad, Grönroos’s quality service model, and Morris’s semiotic trichotomies in the TDI formation circle. The new framework aims to measure the contribution of quality hospitality services to online TDI formation. Using scaled comparisons of homogeneous big data, this framework was empirically tested with all two- and three-star Michelin restaurants in a sample of 100 four- and five-star hotels, all located in Asia and Europe, reviewed in 317,979 online travel reviews (OTRs) hosted on TripAdvisor. The results showed that three-star restaurants and five-star hotels are more popular in terms of the number of OTRs, but diners and guests are more satisfied with and loyal to two-star restaurants and four-star hotels. This big data finding contradicts previous survey-based research on quality services. Instead, the results confirm that consumer satisfaction positively affects consumer loyalty. The new approach to the TDI from a semiotic perspective—destination image semiotics—can represent a paradigm shift in the analysis of TDI through user-generated content (UGC). The proposed conceptual framework integrates several sound theoretical models to extract maximum insights from UGC.

show abstract