After having thoroughly reviewed existent literature about nudging, digital nudging, chatbot technology, and the hospitality sector, and having identified the research gaps, this research will investigate whether implementing nudging techniques in virtual agents enhances user experience in tourism-related tasks, in particular in planning a trip to Baton Rouge, the capital of Louisiana. The objective is to assess whether implementing nudging techniques, such as default choices and framing to a virtual agent, improves user satisfaction, engagement, and perceived usefulness compared to standard GPT chatbots. Methodologically, an experimental exploratory approach was adopted, comparing a GPT-only chatbot with a GPT-nudging chatbot. Participants were randomly assigned to interact with one of the two virtual agents and subsequently completed a questionnaire based on an evaluative model that relies on the Technology Acceptance Model (TAM), Chatbot Usability Scale (CUS), and Client Satisfaction Questionnaire (CSQ-8). Results indicate that the GPT-nudging chatbot significantly improved user engagement, but not perceived usefulness, ease of use, and satisfaction, suggesting that while nudging techniques can increase interaction frequency, they do not necessarily enhance the overall user experience or the perceived value of the chatbot in tourism-related tasks. Conclusions highlight the potential of nudging-enhanced virtual agents to optimize user decision-making in tourism services, offering valuable insight for future research and implications for businesses aiming to leverage AI-driven customer interactions.
Dopo un’attenta revisione della letteratura esistente sul nudging, sul nudging digitale, sulla tecnologia dei chatbot e sul settore dell’ospitalità, e dopo aver identificato le lacune di ricerca, questo studio si propone di indagare se l’implementazione di tecniche di nudging nei virtual agent migliori l’esperienza dell’utente in compiti legati al turismo, in particolare nella pianificazione di un viaggio a Baton Rouge, capitale della Louisiana. L’obiettivo è valutare se l’integrazione di tecniche di nudging, come le scelte predefinite e il framing, in un virtual agent, migliori la soddisfazione, il coinvolgimento e la percezione di utilità da parte dell’utente rispetto ai chatbot GPT standard. Dal punto di vista metodologico, è stato adottato un approccio esplorativo sperimentale, confrontando un chatbot GPT-only con un chatbot GPT-nudging. I partecipanti sono stati assegnati in modo casuale a uno dei due virtual agent e successivamente hanno completato un questionario basato su un modello valutativo che si fonda sul Technology Acceptance Model (TAM), sulla Chatbot Usability Scale (CUS) e sul Client Satisfaction Questionnaire (CSQ-8). I risultati indicano che il chatbot GPT-nudging ha migliorato significativamente il coinvolgimento dell’utente, ma non la percezione di utilità, la facilità d’uso o la soddisfazione, suggerendo che, sebbene le tecniche di nudging possano aumentare la frequenza dell’interazione, non migliorano necessariamente l’esperienza utente complessiva o il valore percepito del chatbot nei compiti legati al turismo. Le conclusioni evidenziano il potenziale dei nudging virtual agents nell’ottimizzare il processo decisionale degli utenti nei servizi turistici, offrendo spunti utili per ricerche future e implicazioni per le aziende che intendono sfruttare le interazioni con i clienti basate sull’intelligenza artificiale.
MIGLIORARE LA USER EXPERIENCE NEI SERVIZI TURISTICI ATTRAVERSO IL NUDGING DIGITALE: UNO STUDIO ESPLORATIVO SUI CHATBOT COSTRUITI CON TECNOLOGIA GPT.
GIGLIOTTI, STEFANO
2023/2024
Abstract
After having thoroughly reviewed existent literature about nudging, digital nudging, chatbot technology, and the hospitality sector, and having identified the research gaps, this research will investigate whether implementing nudging techniques in virtual agents enhances user experience in tourism-related tasks, in particular in planning a trip to Baton Rouge, the capital of Louisiana. The objective is to assess whether implementing nudging techniques, such as default choices and framing to a virtual agent, improves user satisfaction, engagement, and perceived usefulness compared to standard GPT chatbots. Methodologically, an experimental exploratory approach was adopted, comparing a GPT-only chatbot with a GPT-nudging chatbot. Participants were randomly assigned to interact with one of the two virtual agents and subsequently completed a questionnaire based on an evaluative model that relies on the Technology Acceptance Model (TAM), Chatbot Usability Scale (CUS), and Client Satisfaction Questionnaire (CSQ-8). Results indicate that the GPT-nudging chatbot significantly improved user engagement, but not perceived usefulness, ease of use, and satisfaction, suggesting that while nudging techniques can increase interaction frequency, they do not necessarily enhance the overall user experience or the perceived value of the chatbot in tourism-related tasks. Conclusions highlight the potential of nudging-enhanced virtual agents to optimize user decision-making in tourism services, offering valuable insight for future research and implications for businesses aiming to leverage AI-driven customer interactions.File | Dimensione | Formato | |
---|---|---|---|
ENHANCING USER EXPERIENCE IN TOURISM SERVICES THROUGH DIGITAL NUDGING - AN EXPLORATORY STUDY OF GPT-BASED VIRTUAL AGENTS - Stefano Gigliotti.pdf
accesso aperto
Dimensione
2.08 MB
Formato
Adobe PDF
|
2.08 MB | Adobe PDF | Visualizza/Apri |
È consentito all'utente scaricare e condividere i documenti disponibili a testo pieno in UNITESI UNIPV nel rispetto della licenza Creative Commons del tipo CC BY NC ND.
Per maggiori informazioni e per verifiche sull'eventuale disponibilità del file scrivere a: unitesi@unipv.it.
https://hdl.handle.net/20.500.14239/29269