TL;DR
This paper investigates why hotel guests choose (or avoid) face recognition systems for room unlocking. By extending the Unified Theory of Acceptance and Use of Technology (UTAUT) model to include "Privacy Concerns," the researchers found that while performance and social influence matter, the strongest driver for adoption is the quality of "facilitating conditions"—essentially, how well the hotel's infrastructure supports a seamless, hands-free experience.
What Problem Does This Paper Address?
As the hospitality industry shifts toward "smart hotels," biometric technologies like face recognition are being deployed to replace physical keys and streamline check-ins. However, technology is only effective if guests are willing to use it.
The authors identify a gap in understanding the specific psychological and environmental factors that drive guest acceptance in a hotel context. Unlike office security systems where usage might be mandatory, hotel guests are consumers with choices. The paper seeks to determine which factors—ranging from ease of use to privacy fears—actually move the needle on a guest's intention to stay at a face-recognition-enabled hotel.
Methods
The researchers employed a quantitative approach based on the UTAUT model, a standard framework in information systems used to explain user intentions.
- Model Extension: The standard UTAUT variables—Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), and Facilitating Conditions (FC)—were used. Crucially, the authors added Privacy Concerns (PC) as a fifth independent variable, recognizing that biometrics carry unique risks regarding personal data.
- Survey Design: A three-part questionnaire was developed, covering demographics, a measurement scale for the five variables, and behavioral intention.
- Analysis: Data was processed using SPSS 26.0. The team performed reliability and validity tests (to ensure the survey was consistent and accurate) followed by regression analysis to see which variables most strongly predicted the "Behavioral Intention" (BI) to use the system.
Datasets
The study relied on primary data collection rather than pre-existing datasets:
- Sample Size: 318 questionnaires were collected, resulting in 308 valid responses (a 96.68% recovery rate).
- Target Demographic: Guests who had recently stayed in smart hotels in Guangzhou, China, specifically those using face recognition for room unlocking.
- Collection Period: A pre-survey in November 2023, followed by the main survey from January to May 2024. Data was gathered via on-site surveys and online platforms like Wenjuanwang, Ctrip, and Fliggy.
Key Insights and Ideas
- The "Convenience King": Surprisingly, "Facilitating Conditions" had the highest positive impact (coefficient of 0.217). This suggests that guests value the infrastructure—the fact that they don't need to carry a key or use their own hardware—above almost everything else.
- The Privacy Paradox: The paper notes that "Privacy Concerns" have a significant positive impact on behavioral intention. In the context of this study's regression model, this implies that when hotels successfully address privacy (e.g., through clear agreements or using trusted platforms like Alipay/WeChat), it becomes a proactive driver for adoption rather than just a hurdle to clear.
- The Youth Factor: The primary user base for these systems is concentrated in the 18–39 age bracket. This group is highly influenced by social media, suggesting that "Social Influence" (what others think or post) is a potent marketing tool for smart hotels.
- Passive vs. Active Biometrics: The authors highlight that face recognition is "passive"—it identifies users without requiring them to touch a scanner (like fingerprints). This "relaxed" interaction style is a major factor in its growing acceptance compared to older biometric methods.
Key Results
The regression analysis confirmed that all five hypothesized factors positively influence a guest's intention to use face recognition:
- Facilitating Conditions (0.217): The strongest predictor.
- Performance Expectancy (0.191): Guests use it because it's useful and efficient.
- Effort Expectancy (0.188): Guests use it because it's easy to learn.
- Privacy Concerns (0.179): Perceived security and privacy protections are vital.
- Social Influence (0.166): Recommendations from peers and social media play a role.
All non-standardized coefficients (B) were greater than 0, indicating a statistically significant positive relationship across the board.
Limitations and Future Work
- Geographic Bias: The study was limited to guests in Guangzhou. Acceptance levels and privacy attitudes may vary significantly in different cultural or regulatory environments (e.g., the EU vs. China).
- Platform Trust: The authors suggest that using third-party platforms like WeChat or Alipay can reduce guest anxiety because these platforms already hold the users' biometric data. However, the paper does not deeply explore the long-term implications of hotels relying on these external tech giants for core security functions.
- Error Handling: The paper briefly mentions the need for "remedial measures" if a system fails (e.g., letting a guest into the wrong room), but future research could focus specifically on the "trust recovery" process after a biometric system error occurs.
Summary updated