Aurora: AI-Based Narrative Intervention to Support Emotional Well-Being in Clinical and Non-Clinical Populations (Aurora)

Aurora: Evaluation of an AI-Based Narrative Intervention for Emotional Well-Being, Identity Processes, and Recovery-Oriented Outcomes in Clinical and Non-Clinical Populations

Aurora is an interdisciplinary project evaluating a chatbot-mediated supportive care intervention designed to promote emotional expression, autobiographical meaning-making, identity processes, and emotional well-being through guided narrative reconstruction. The Aurora system provides a structured, person-centered storytelling process supported by generative AI and human facilitation. Under the supervision of a trained facilitator (licensed mental health professional), participants engage in guided reminiscence and storytelling sessions to co-create a personalized "life book." The chatbot is not a diagnostic or treatment tool; rather, it is intended to support emotional expression, narrative reconstruction, and recovery-oriented processes. The study includes three non-randomized arms implemented sequentially: (1) a single-session arm of healthy adults focused on acceptability, usability, and emotional safety; (2) a four-hour intervention arm of adults with DSM-5 diagnosed mental disorders in residential care; and (3) a four-hour intervention arm of healthy older adults aged 65 years and older. Quantitative outcomes assess affect, mental well-being, and recovery-related constructs. Additional measures include usability, satisfaction, and qualitative feedback. Ecological momentary assessment (EMA) is conducted in Arms 2 and 3.

Study Overview

• Status: Recruiting
• Conditions: Wellbeing; Aging; Elderly; Mental Health; Institutionalization
• Intervention / Treatment: Behavioral: chatbot-mediated supportive care intervention

Detailed Description

Pre-human development (in silico; not part of the clinical trial):

Prior to human participation, the Aurora system underwent an in-silico preparatory phase focused on content coherence and emotional safety using synthetic user profiles. Simulated interactions were reviewed by licensed mental health professionals to identify potential safety concerns and inform iterative refinements of the supportive narrative process. This preparatory work did not involve human participants and is not part of the clinical trial.

Human participants (clinical trial):

The study uses a sequential, non-randomized, three-arm interventional design with a total anticipated sample of 55 participants.

Arm 1: Healthy adults (single-session arm; n=20) Following informed consent, participants complete a single guided interaction with Aurora to generate a brief personal narrative. Outcomes include pre-session expectations, pre-post session affect (I-PANAS-SF), perceived usefulness and user experience, usability (System Usability Scale, SUS), satisfaction, and qualitative feedback.

Arm 2: Adults with DSM-5 diagnosed mental disorder in residential care (4-hour intervention arm; n=15) Following informed consent, participants complete four guided sessions over two weeks (two sessions per week, 1 hour per session). Outcomes include pre-session expectations, pre-post session affect (I-PANAS-SF) for each session, perceived usefulness and user experience, usability (SUS), satisfaction, qualitative feedback, and pre-post intervention self-report measures of mental well-being and recovery-related constructs. Ecological momentary assessment (EMA) is conducted during the 1-week pre-intervention period, the 2-week intervention period, and the 1-week post-intervention follow-up period.

Arm 3: Healthy older adults (aged 65 years and older; 4-hour intervention arm; n=20) Following informed consent, participants complete two guided sessions over two weeks (one session per week, 2 hours per session). Outcomes include pre-session expectations, pre-post session affect (I-PANAS-SF) for each session, perceived usefulness and user experience, usability (SUS), satisfaction, qualitative feedback, and pre-post intervention self-report measures of mental well-being and recovery-related constructs. Ecological momentary assessment (EMA) is conducted during the 1-week pre-intervention period, the 2-week intervention period, and the 1-week post-intervention follow-up period.

Data security and compliance:

All interactions occur in a secure professional environment. Textual data are pseudonymized during transcription and fully anonymized at the end of the project. Optional audio recordings are stored on encrypted offline devices and deleted after integration into the participant's life book. The study complies with applicable data protection and regulatory frameworks, including GDPR (EU 2016/679), LOPDGDD 3/2018, the EU AI Act (2024/1689), and institutional ethics guidelines.

• Study Type: Interventional
• Enrollment (Estimated): 55
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Albert Feliu-Soler Associate Professor Serra Húnter Fellow, PhD; Phone Number: +34935812778; Email: albert.feliu@uab.cat
• Study Contact Backup: Name: Jaime Navarrete Postdoctoral Researcher, PhD; Phone Number: 12734 +34 936 615 208; Email: jaime.navarrete@sjd.es

Study Locations

• Spain
  • Barcelona
    • Barcelona, Barcelona, Spain, 08012
      • Not yet recruiting
      • Llar Residència Gràcia(Grup ATRA)
      • Contact: Meritxell Alcaraz, MSc; Phone Number: +34 93 461 57 62; Email: dir.llargracia@smgracia.org
    • Cerdanyola del Vallès, Barcelona, Spain, 08193
      • Recruiting
      • Department of Clinical and Health Psychology; Universitat Autònoma de Barcelona
      • Contact: Albert Feliu-Soler Associate Professor Serra Húnter Fellow, PhD; Phone Number: +34 93 581 2778; Email: albert.feliu@uab.cat

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria

Arm 1: Healthy Adults (Single-Session Intervention)

Age 18 years or older at screening.

Sufficient ability to read and understand Spanish to follow study instructions and complete questionnaires.

Ability to engage in a brief guided interaction and complete self-report measures.

Able and willing to provide written informed consent.

---

Arm 2: Adults with DSM-5 Diagnosed Mental Disorder in Residential Care (4-hour Intervention)

Age 18 years or older at screening.

Currently residing in a participating long-term mental health residential care facility and expected to remain there for the duration of the intervention and post-assessment period.

Documented diagnosis of a mental disorder according to DSM-5 criteria, confirmed by the treating clinician.

Minimal clinical stability at baseline, defined as all of the following:

Clinically stable in the judgment of the treating clinician.

No requirement for acute psychiatric hospitalization or crisis intervention in the previous 4 weeks.

Clinical Global Impression - Improvement (CGI-I) score between 3 and 5 inclusive during the 4 weeks prior to enrollment, indicating relative clinical stability.

Sufficient ability to understand spoken and written Spanish to participate in study procedures.

Ability to engage in guided interaction and provide feedback.

Able and willing to provide informed consent; when applicable, provision of legal guardian consent plus participant assent.

Willingness to participate in all study procedures.

---

Arm 3: Healthy Older Adults (≥65 Years; 4-hour Intervention)

Age 65 years or older at screening.

No self-reported diagnosis of a serious mental disorder (for example, psychotic disorder or bipolar disorder).

Sufficient ability to read and understand Spanish to participate in study procedures.

Adequate cognitive and communication abilities to engage in guided interaction and complete questionnaires.

Able and willing to provide written informed consent.

---

Exclusion Criteria

Arm 1: Healthy Adults

Current acute medical or psychiatric condition that would compromise safe participation or data validity.

Moderate or high acute suicide or self-harm risk at screening.

Significant cognitive, communication, or comprehension impairment that would interfere with participation.

Explicit refusal to participate.

---

Arm 2: Adults with DSM-5 Diagnosed Mental Disorder in Residential Care

Current acute psychiatric decompensation requiring crisis-level care.

Moderate or high acute suicide or self-harm risk at screening or baseline.

High risk of clinically significant emotional harm from autobiographical life review, defined as treating clinician judgment that narrative or reminiscence work is contraindicated due to one or more of the following:

Severe clinical destabilization within the past 3 months.

Trauma-related re-experiencing symptoms.

Marked dissociative symptoms.

Inability to provide informed consent, with no legal representative available when required, or lack of participant assent when applicable.

Significant cognitive, communication, or comprehension impairment without available supports.

Explicit refusal to participate.

Imminent discharge or transfer that would prevent completion of the intervention or post-assessment.

---

Arm 3: Healthy Older Adults

Self-reported diagnosis of a serious mental disorder (for example, psychotic disorder or bipolar disorder).

Moderate or high acute suicide or self-harm risk at screening.

Current acute medical or psychiatric condition that would compromise safe participation.

Significant cognitive, communication, or comprehension impairment that would interfere with participation.

Explicit refusal to participate.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: Non-Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Single-session - Healthy adults; Healthy adults complete one Aurora session (single exposure) for platform refinement and usability assessment.	Behavioral: chatbot-mediated supportive care intervention; Aurora is a guided narrative reconstruction chatbot combining structured storytelling and reminiscence with an AI-based conversational system and support from a trained facilitator. Participants co-create a personalized life narrative ("life book") with written content and optional audio contributions (with explicit consent). Sessions occur in a secure professional environment and are supervised by licensed mental health professionals to ensure emotional safety. Aurora is not a diagnostic tool and is intended to promote emotional expression, recovery-oriented processes, and emotional well-being. The intervention is delivered in structured guided sessions. Arm 1 receives a single-session version for refinement and usability assessment, whereas Arms 2 and 3 receive a 4-hour intervention delivered over two weeks. The total intervention dose is equivalent across Arms 2 and 3. Session structure differs to accommodate participant characteristics.; Other Names: Aurora; Aurora AI-Assisted Narrative Reconstruction Chatbot
Experimental: Four-hour program - Adults with DSM-5 diagnosed mental disorder in residential care; Adults (aged ≥18 years) with a DSM-5 diagnosed mental disorder, residing in long-term mental health residential care facilities, complete a four-session guided narrative program over two weeks (two sessions per week, 1 hour per session) with facilitation by a licensed mental health professional.	Behavioral: chatbot-mediated supportive care intervention; Aurora is a guided narrative reconstruction chatbot combining structured storytelling and reminiscence with an AI-based conversational system and support from a trained facilitator. Participants co-create a personalized life narrative ("life book") with written content and optional audio contributions (with explicit consent). Sessions occur in a secure professional environment and are supervised by licensed mental health professionals to ensure emotional safety. Aurora is not a diagnostic tool and is intended to promote emotional expression, recovery-oriented processes, and emotional well-being. The intervention is delivered in structured guided sessions. Arm 1 receives a single-session version for refinement and usability assessment, whereas Arms 2 and 3 receive a 4-hour intervention delivered over two weeks. The total intervention dose is equivalent across Arms 2 and 3. Session structure differs to accommodate participant characteristics.; Other Names: Aurora; Aurora AI-Assisted Narrative Reconstruction Chatbot
Experimental: Four-hour program - Healthy older adults (≥65 years); Healthy older adults (aged ≥65 years), with no self-reported diagnosis of a serious mental disorder, complete a two-session guided narrative program over two weeks (one session per week, 2 hours per session) with facilitation by a licensed mental health professional.	Behavioral: chatbot-mediated supportive care intervention; Aurora is a guided narrative reconstruction chatbot combining structured storytelling and reminiscence with an AI-based conversational system and support from a trained facilitator. Participants co-create a personalized life narrative ("life book") with written content and optional audio contributions (with explicit consent). Sessions occur in a secure professional environment and are supervised by licensed mental health professionals to ensure emotional safety. Aurora is not a diagnostic tool and is intended to promote emotional expression, recovery-oriented processes, and emotional well-being. The intervention is delivered in structured guided sessions. Arm 1 receives a single-session version for refinement and usability assessment, whereas Arms 2 and 3 receive a 4-hour intervention delivered over two weeks. The total intervention dose is equivalent across Arms 2 and 3. Session structure differs to accommodate participant characteristics.; Other Names: Aurora; Aurora AI-Assisted Narrative Reconstruction Chatbot

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Positive Affect (I-PANAS-SF - Positive Affect subscale-pre-post session change)	Positive affect will be assessed using the Positive Affect (PA) subscale of the International Positive and Negative Affect Schedule - Short Form (I-PANAS-SF). Participants will rate their affect "right now." The endpoint is the change in PA from immediately before to immediately after each session across all treatment arms. Higher scores indicate higher positive affect.	Change from immediately before to immediately after each session, up to 2 weeks.
Negative Affect (I-PANAS-SF - Negative Affect subscale - pre-post session change)	Negative affect will be assessed using the Negative Affect (NA) subscale of the International Positive and Negative Affect Schedule - Short Form (I-PANAS-SF). Participants will rate their affect "right now." The endpoint is the change in NA from immediately before to immediately after each session across all treatment arms. Higher scores indicate higher negative affect.	Change from immediately before to immediately after each session, up to 2 weeks.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Positive Affect (I-PANAS-SF - Positive Affect subscale - baseline to 1-week follow-up change)	Positive affect will be assessed using the Positive Affect (PA) subscale of the I-PANAS-SF. Participants will rate their affect "over the past week." The endpoint is the change in PA from baseline to immediately post-intervention in Arms 2 and 3. Higher scores indicate higher positive affect.	Change from baseline at 1 week after end of intervention.
Negative Affect (I-PANAS-SF - baseline to 1-week follow-up change)	Negative affect will be assessed using the Negative Affect (NA) subscale of the I-PANAS-SF, adapted to assess affect over the past week. The endpoint is the change in NA from baseline (pre-intervention) to 1-week follow-up after completion of the intervention in Arms 2 and 3. Higher scores indicate higher negative affect.	Change from baseline at 1 week after end of intervention.
Mental well-being (WEMWBS)	Mental well-being will be assessed using the Warwick-Edinburgh Mental Well-being Scale (WEMWBS; total score). Higher scores indicate greater mental well-being. The endpoint is change from baseline at 1 week after end of intervention in Arms 2 and 3.	Change from baseline at 1 week after end of intervention.
Recovery-related outcomes aligned with CHIME framework	Recovery-related outcomes will be assessed using an ad hoc self-report measure aligned with the CHIME framework. The measure includes six constructs (3 items each): social connectedness, hope, self-concept clarity, valued living, general self-efficacy, and self-esteem. A total composite score will be computed. Higher scores indicate more favorable recovery-related outcomes. The endpoint is the change from baseline (pre-intervention) to 1-week follow-up after completion of the intervention in Arms 2 and 3.	Change from baseline at 1 week after end of intervention.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Usability (System Usability Scale, SUS)	Usability will be assessed using the System Usability Scale (SUS). The SUS is a 10-item self-report measure of perceived usability. Total scores range from 0 to 100, with higher scores indicating better perceived usability. In Arm 1, the SUS will be administered immediately after the single session. In Arms 2 and 3, the SUS will be administered at follow-up, 1 week after the end of the intervention.	Immediately after session (Arm 1); 1 week after end of intervention (Arms 2 and 3)
User experience and satisfaction	User experience and satisfaction will be assessed using study-specific self-report items covering expectations, perceived usefulness, and satisfaction/opinion. In Arm 1, this measure will be administered immediately after the single session. In Arms 2 and 3, it will be administered at follow-up, 1 week after the end of the intervention.	Immediately after session (Arm 1); 1 week after end of intervention (Arms 2 and 3)
Ecological Momentary Assessment (EMA)	Ecological momentary assessment (EMA) will be conducted in Arms 2 and 3. Participants will complete brief assessments twice daily across three predefined periods: (1) a 1-week pre-intervention baseline period, (2) the 2-week intervention period, and (3) a 1-week post-intervention follow-up period. EMA will include brief momentary items assessing affect, valued action, self-efficacy/empowerment, connectedness/hope, and psychological flexibility, capturing real-time (momentary) experiences.	Twice daily from 1 week before intervention to 1 week after end of intervention.

Collaborators and Investigators

• Sponsor: Universitat Autonoma de Barcelona
• Collaborators: Parc Sanitari Sant Joan de Déu; Universitat Oberta de Catalunya; AGAUR; Grup ATRA; Institut Municipal de Persones amb Discapacitat

Study record dates

Study Major Dates

• Study Start (Actual): February 12, 2026
• Primary Completion (Estimated): April 1, 2026
• Study Completion (Estimated): April 1, 2026

Study Registration Dates

• First Submitted: December 18, 2025
• First Submitted That Met QC Criteria: March 19, 2026
• First Posted (Actual): March 27, 2026

Study Record Updates

• Last Update Posted (Actual): March 27, 2026
• Last Update Submitted That Met QC Criteria: March 19, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: older adults; recovery; mental health; artificial intelligence; storytelling; digital mental health; wellbeing; human-computer interaction; reminiscence; identity; residential care; autobiographical narrative; life story; chatbot intervention
• Additional Relevant MeSH Terms: Behavior; Personal Satisfaction; Psychological Well-Being
• Other Study ID Numbers: 2025LLAV00080 (Other Identifier: AGAUR; Convocatòria d'Indústria del Coneixement, 2025, Modalitat A, Llavor)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared due to the sensitive nature of the data, which include mental health information and autobiographical narrative content from a vulnerable population. Data use is restricted to the approved study objectives under the conditions of the ethics committee approval and applicable data protection regulations (GDPR).

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No