Effects of Virtual Assistant Features on User Experience in Service Settings

NCT07666295 | Not Yet Recruiting

• 1 other identifier: AVIR4SERVICES-EXP-01
• Study Type: interventional
• Target: 400
• Locations: 1 country
• Sites: 1

Brief Summary

This study examines how the characteristics and performance of virtual assistants influence user experience in service settings. Approximately 400 adults will interact with virtual assistants presented as avatars, chatbots, or voice assistants in simulated tourism, cultural, retail, or financial service situations. Participants will be exposed to one or more experimental conditions that may differ in features such as communication style, language specificity, anthropomorphism, personalization, type of virtual assistant, level of immersion, or the presence of inaccurate responses or errors. After the interaction, participants will complete questionnaires about their perceptions, emotions, trust, satisfaction, acceptance of recommendations, and intention to use the virtual assistant. During the experimental session, non-invasive methods may be used to measure visual attention and psychophysiological responses. These methods include eye tracking, electrodermal activity, electroencephalography, and automated facial expression analysis. Facial recordings will be used to analyze emotional expressions and will not be used to identify participants. The study does not involve drugs, biological products, medical treatments, diagnostic procedures, or investigational medical devices. Its purpose is to improve scientific understanding of human interaction with artificial intelligence and virtual assistants in service environments.

Conditions

User Experience With Virtual Assistants in Service Settings

Keywords

Virtual Assistants; Artificial Intelligence; Human-Computer Interaction; User Experience; Consumer Behavior; Technology Acceptance; Anthropomorphism; Eye Tracking; Electrodermal Activity; Electroencephalography; Facial Expression Analysis

Outcome Measures

Primary Outcomes (1)

• Trust in the Virtual Assistant

  Trust in the virtual assistant will be assessed immediately after the interaction using a pre-specified multi-item questionnaire. Participants will rate each item on a 7-point Likert scale ranging from 1 (strongly disagree) to 7 (strongly agree). An overall trust score will be calculated as the mean of the completed items. Higher scores indicate greater trust in the virtual assistant.

  Immediately after the virtual assistant interaction, during the same experimental session

Secondary Outcomes (5)

• User Satisfaction With the Virtual Assistant

  Immediately after the virtual assistant interaction, during the same experimental session

• Intention to Use the Virtual Assistant

  Immediately after the virtual assistant interaction, during the same experimental session

• Acceptance of the Virtual Assistant Recommendation

  Immediately after the virtual assistant interaction, during the same experimental session

• Electrodermal Activity During the Virtual Assistant Interaction

  From the start to the end of the virtual assistant interaction, for up to 20 minutes.

• Visual Attention During the Virtual Assistant Interaction

  Continuously during the virtual assistant interaction, over approximately 20 minutes.

Study Arms (4)

High Anthropomorphism and Accurate Response

EXPERIMENTAL

Participants will interact with a virtual assistant displaying a high level of anthropomorphic features. The virtual assistant will provide accurate and relevant responses during the service interaction.

Behavioral: High Anthropomorphism; Behavioral: Accurate Virtual Assistant Response

High Anthropomorphism and Inaccurate Response

EXPERIMENTAL

Participants will interact with a virtual assistant displaying a high level of anthropomorphic features. During the service interaction, the virtual assistant will provide a predefined inaccurate or irrelevant response designed for the experiment.

Behavioral: High Anthropomorphism; Behavioral: Inaccurate Virtual Assistant Response

Low Anthropomorphism and Accurate Response

EXPERIMENTAL

Participants will interact with a virtual assistant displaying a low level of anthropomorphic features. The virtual assistant will provide accurate and relevant responses during the service interaction.

Behavioral: Low Anthropomorphism; Behavioral: Accurate Virtual Assistant Response

Low Anthropomorphism and Inaccurate Response

EXPERIMENTAL

Participants will interact with a virtual assistant displaying a low level of anthropomorphic features. During the service interaction, the virtual assistant will provide a predefined inaccurate or irrelevant response designed for the experiment.

Behavioral: Low Anthropomorphism; Behavioral: Inaccurate Virtual Assistant Response

Interventions

High Anthropomorphism BEHAVIORAL

The virtual assistant will display a comparatively high level of human-like visual, vocal, or conversational characteristics, as operationalized in the experimental protocol.

High Anthropomorphism and Accurate Response; High Anthropomorphism and Inaccurate Response

Low Anthropomorphism BEHAVIORAL

The virtual assistant will display a comparatively low level of human-like visual, vocal, or conversational characteristics, as operationalized in the experimental protocol.

Low Anthropomorphism and Accurate Response; Low Anthropomorphism and Inaccurate Response

Accurate Virtual Assistant Response BEHAVIORAL

The virtual assistant will provide accurate, relevant, and contextually appropriate information during the simulated service interaction.

High Anthropomorphism and Accurate Response; Low Anthropomorphism and Accurate Response

Inaccurate Virtual Assistant Response BEHAVIORAL

The virtual assistant will provide a predefined inaccurate or contextually inappropriate response during the simulated service interaction. The error will be standardized across participants assigned to this condition and will not concern medical, safety-related, or other high-risk information.

High Anthropomorphism and Inaccurate Response; Low Anthropomorphism and Inaccurate Response

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adults aged 18 years or older.
• Able to understand the study information and provide informed consent.
• Sufficient proficiency in Spanish to understand the instructions and complete the study questionnaires.
• Able to interact with a computer-based virtual assistant and complete the experimental session.
• Willing to complete the study procedures, which may include questionnaires, eye tracking, electrodermal activity recording, electroencephalography, and facial expression recording.

You may not qualify if:

• Younger than 18 years.
• Unable to understand the study information or provide valid informed consent.
• Insufficient proficiency in Spanish to understand the instructions or complete the questionnaires.
• A visual, hearing, motor, or other condition that prevents completion of the specific experimental task and cannot be accommodated by the study procedures.
• A temporary health condition, discomfort, or technical incompatibility that, according to the study procedures, prevents safe or reliable completion of the experimental session.
• Previous participation in the same experimental protocol, when prior exposure could influence the study outcomes.

Sponsors & Collaborators

• University of Malaga: lead

Study Sites (1)

Consumer Behavior Research Laboratory (LICCO), University of Malaga

Málaga, 29013, Spain

Location

MeSH Terms

Conditions

Consumer Behavior

Condition Hierarchy (Ancestors)

Behavior

Central Study Contacts

Sebastián Molinillo Jiménez - Professor of Marketing, PhD

CONTACT

+34 952131265; smolinillo@uma.es

Francisco Rejón-Guardia, Associate professor of marketing, PhD

CONTACT

+34 952 13 12 68; franrejon@uma.es

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Masking Details: Participants will not be informed of the specific experimental hypothesis or the alternative conditions. They will be informed that the study examines user interaction with virtual assistants. Investigators conducting the experimental sessions may know the assigned condition.
• Purpose: BASIC SCIENCE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate professor of Marketing and Co-Principal Investigator

Model Details: Participants will be assigned to one experimental condition involving interaction with a virtual assistant. The conditions will differ in selected virtual assistant features or interaction outcomes. Each participant will complete the experimental task and the post-interaction outcome assessment under the assigned condition.

Study Record Dates

• First Submitted: June 11, 2026
• First Posted: June 24, 2026
• Study Start (Estimated): September 1, 2026
• Primary Completion (Estimated): January 1, 2028
• Study Completion (Estimated): January 1, 2028
• Last Updated: June 24, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share

Locations

ES (1)