An interventional study of Hybrid conversational companion application and Rule-based conversational companion application in Loneliness, Social Isolation and Social Isolation in Older Adults, sponsored by The University of Hong Kong. Recruiting at 1 site in Hong Kong. Open to participants aged 60 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-11-10.
Sponsored by The University of Hong Kong · Not applicable, Interventional, and Basic science
This study examines how a smartphone conversational application affects feelings of loneliness in Cantonese-speaking older adults living in Hong Kong. Seventy-two adults aged 60 or above who report at least moderate loneliness will be randomly assigned to one of two versions of the same application. Both versions look the same, offer the same three conversational companions, and provide the same set of in-app tools. The two versions differ in how the companions' replies are produced: in one version, replies are generated by a large language model, and in the other, they are assembled from pre-written templates selected by keyword and conversation state. Several features depend on the language model and are available only in the first version: (1) memory of earlier conversations; (2) replies in the tone that the participant preferred at the start of the study; (3) follow-up questions during reminiscence; (4) weekly life-story chapters drafted by the model and sent by notification when ready; (5) the option to ask the companion Tung Tung about reading material; (6) activity suggestions and action plans personalised with intake information and memory; and (7) a weekly narrative summary on the progress page written by the model. In the other version, the weekly life-story chapter is assembled at once from the participant's own answers, and the progress page shows charts and counts only. Participants use the application for four weeks and are then followed for a further four weeks with continued access. The main question is whether any difference between the two versions in emotional loneliness operates through how understood, validated and cared for participants feel during individual conversations. Participants are not told which version they are using, and the researchers who carry out the Week 0 and Week 4 assessments are also unaware of the assignment.
Loneliness in later life is associated with adverse physical and mental health outcomes. Conversational applications based on large language models have been proposed as a scalable form of support, but most published evaluations remain at the pilot feasibility stage, and few have used a comparator that holds interface richness, attention, and novelty constant. Without such a comparator, any observed benefit cannot be attributed to the language model rather than to the surrounding experience.
This trial addresses that gap using an architecturally matched comparator. Both arms deliver the identical mobile application: the same visual interface, navigation, three named conversational companions, tool layer, and in-app assessment prompts. The arms differ in the backend that generates companion responses and in the features that depend on the language model, which are available only in the Hybrid arm: (1) cross-session memory; (2) replies adjusted to the tone that the participant preferred at intake; (3) follow-up questions during reminiscence; (4) weekly life-story chapters drafted by the model and sent by notification when ready; (5) the option to ask Tung Tung about reading material; (6) activity suggestions and action plans personalised with intake information and memory; and (7) a weekly narrative summary on the progress page written by the model. In the Rule-based arm, the weekly life-story chapter is assembled at once from the participant's own answers, and the progress page shows charts and counts only. In the Hybrid arm, responses are generated by a large language model using each companion's system prompt, conversation history, and user input, and the arm exhibits language-model-distinctive conversational behaviours including anchoring on specific content, cross-session memory, explicit admission of unfamiliarity, mixed-content routing, and generative summarisation. In the Rule-based arm, responses are produced by a template system driven by keyword matching and conversational state, without cross-session memory and without those behaviours. Conversational content in this arm is not transmitted to any external service. A local safety classifier, hosted by the research team, is used in both arms.
Seventy-two community-dwelling Cantonese-speaking adults aged 60 or above who score at least 2 on the De Jong Gierveld Emotional and Social Loneliness Scale are allocated 1:1, stratified by baseline emotional loneliness using permuted blocks within stratum, with allocation concealment. Trained outcome assessors, who are unaware of allocation, explain the study, obtain written informed consent, and conduct the paper-based assessments at Week 0 and Week 4. The same assessor conducts both assessments for a participant. After the Week 0 assessment, the assessor leaves the room. The Principal Investigator then registers the participant, which triggers the allocation on the study server, and provides app onboarding. The allocation sequence is generated by a person who has no other role in the trial, and the Principal Investigator cannot read it. After the Week 4 assessment, the Principal Investigator conducts an exit interview. At Week 8, participants complete the follow-up questionnaires in the app.
The intervention period is four weeks, followed by four weeks of follow-up with continued application access and continuous usage logging. Participants are encouraged to use the application daily and at least five times per week; use is not mandatory. The primary analysis is a 2-1-2 multilevel structural equation model. Arm is the participant-level predictor. Perceived responsiveness is rated after conversations, and the model estimates each participant's latent mean. Emotional loneliness at Week 4, adjusted for baseline, is the outcome. The indirect effect is tested using a Monte Carlo confidence interval. The sample size is fixed by feasibility. In a sensitivity power analysis by simulation, sixty completers gave power of about 0.80 only when the effect of arm on perceived responsiveness was d = 0.8 and the standardised effect of perceived responsiveness on emotional loneliness was 0.4. The between-arm difference in emotional loneliness is reported as an effect estimate with a 95% confidence interval and is not tested confirmatorily. A falsifiable specification of the proposed mechanism is that an arm advantage appears on emotional loneliness but not on social loneliness.
A three-layer safety architecture operates in both arms: a Cantonese-calibrated distress detector that surfaces Hong Kong crisis resources in real time and alerts the research team; a daily 100% audit of Thought Exercise events against pre-specified scope criteria; and weekly Principal Investigator review of all flags and audits. Pre-specified pause criteria are an intervention-related serious adverse event, boundary-crossed events exceeding 10%, or distress detector recall below 0.90 on a real Cantonese corpus.
A pilot phase with six older adults preceded the randomised trial. Two pilot participants started on 15 October 2026 under a separate pilot consent form. Four further participants signed the main consent form and were registered on 19 October 2026 with an earlier allocation sequence. On that day, the Rule-based version of the app did not work correctly. The randomised analysis set was therefore restarted on 21 October 2026 with a newly generated allocation sequence, and these four participants were moved to the pilot phase. They continue to use the application and complete the scheduled assessments. Pilot-phase data are reported for feasibility and acceptability only and are excluded from all trial analyses. The randomised analysis set comprises participants enrolled from 21 October 2026 onwards; the target of 72 randomised participants, with about 60 expected to complete the trial, is unchanged.
236 studies on the registry are indexed under Social Isolation; 61 are open to participants now.
This study's planned enrollment of 72 is close to the median of 80 across 198 interventional studies indexed under Social Isolation.
Browse Social Isolation studies →The University of Hong Kong is the lead sponsor of 1,292 studies on the registry; 348 are open to participants now.
Of its 9 completed or terminated interventional studies of FDA-regulated products, 0 (0%) have results posted.
Counted across the registry records on this site, refreshed daily.
The criteria were revised on the registry on Nov 10, 2026. See what changed
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Companion responses are generated by a large language model through the official DeepSeek API, accessed via Firebase Cloud Functions. The model version is not fixed, so the model identifier returned with each response is logged. Responses are conditioned on the companion's system prompt, conversation history, cross-session memory, and the current input. In reminiscence, the model asks one follow-up question after each answer, and at the end of each week a DeepSeek model drafts a short life-story chapter that a second model checks against the conversation. Four in-app tools (Action Loop, Thought Exercise, Education, Progress). Five LLM-distinctive behaviours are tagged in logs as a cumulative within-arm exposure variable. Conversational text is sent to the model provider; participants are advised not to include identifying information. Participants are encouraged to use the app daily and at least five times per week for four weeks; use is not mandatory and is logged.
Behavioral: Hybrid conversational companion application
Identical interface, navigation, companion names and personae, tool layer, notification schedule, and in-app assessment prompts. Replies are assembled from pre-written templates by keyword matching and conversational state; no language model is used. In free conversation, Siu Yan's replies are drawn in rotation from a pool of pre-written sentences. The daily check-in is a short conversation with fixed questions, followed by a pre-written response chosen by the participant's answer. In reminiscence, both arms use the same open questions; in this arm each answer is followed by a fixed acknowledgement, and the participant's own answers are arranged, unchanged, into a weekly life-story chapter. No cross-session memory. Conversational content is not sent to any external service; a local safety classifier, hosted by the research team, is used in both arms. Attention- and interface-matched active comparator. Recommended use, expected daily duration, and logging are identical to the experimen
Behavioral: Rule-based conversational companion application
Companion responses are generated by a large language model through the official DeepSeek API, accessed via Firebase Cloud Functions. The model version is not fixed, so the model identifier returned with each response is logged. Responses are conditioned on the companion's system prompt, conversation history, cross-session memory, and the current input. In reminiscence, the model asks one follow-up question after each answer, and at the end of each week a DeepSeek model drafts a short life-story chapter that a second model checks against the conversation. Four in-app tools (Action Loop, Thought Exercise, Education, Progress). Five LLM-distinctive behaviours are tagged in logs as a cumulative within-arm exposure variable. Conversational text is sent to the model provider; participants are advised not to include identifying information. Participants are encouraged to use the app daily and at least five times per week for four weeks; use is not mandatory and is logged.
Identical interface, navigation, companion names and personae, tool layer, notification schedule, and in-app assessment prompts. Replies are assembled from pre-written templates by keyword matching and conversational state; no language model is used. In free conversation, Siu Yan's replies are drawn in rotation from a pool of pre-written sentences. The daily check-in is a short conversation with fixed questions, followed by a pre-written response chosen by the participant's answer. In reminiscence, both arms use the same open questions; in this arm each answer is followed by a fixed acknowledgement, and the participant's own answers are arranged, unchanged, into a weekly life-story chapter. No cross-session memory. Conversational content is not sent to any external service; a local safety classifier, hosted by the research team, is used in both arms. Attention- and interface-matched active comparator. Recommended use, expected daily duration, and logging are identical to the experiment
Session-level perceived responsiveness (primary mediator)
Brief perceived-responsiveness measure administered in the app after valid conversation sessions. Four single items, each rated from 1 to 7, cover Understanding, Validation, Caring, and Insensitivity (reverse-scored). A free-conversation session is valid when the participant sends at least three messages and receives replies; a check-in or reminiscence session is valid when the participant completes the module. In the pre-specified primary mediation model, each participant's latent mean of these ratings is the mediator; this is not an efficacy endpoint.
Time frame: After valid conversation sessions, at most once per companion per day, Weeks 1 through 4
Change in emotional loneliness (De Jong Gierveld emotional subscale)
3 items, 0-3. Change from baseline to Week 4. Outcome in the primary mediation model. Assessed on paper at Weeks 0 and 4 by a trained outcome assessor who is unaware of allocation; in principle, the same assessor conducts both assessments for a participant. Power for the indirect effect was examined in a sensitivity simulation; the trial is not powered for confirmatory testing of the between-arm difference, which is reported as an effect estimate with a 95% CI.
Time frame: Baseline (Week 0) and Week 4
Emotional loneliness at Week 8
De Jong Gierveld emotional subscale, 3 items, 0-3, self-administered in the app at Week 8 (the questionnaire opens on Day 56 and closes on Day 63).
Time frame: Baseline (Week 0) and Week 8
Social loneliness at Week 4
De Jong Gierveld social subscale, 3 items, 0-3. Tests the prediction that any difference between arms appears in emotional but not in social loneliness.
Time frame: Baseline (Week 0) and Week 4
Dimensions of session-level perceived responsiveness
Understanding, Validation, Caring, and Insensitivity (reverse-scored), each rated from 1 to 7. Each dimension is examined as a mediator in a secondary analysis without correction for multiple comparisons.
Time frame: After valid conversation sessions, Weeks 1 through 4
Social network size (LSNS-6)
Lubben Social Network Scale, 6-item version, completed on paper at Weeks 0 and 4 and in the app at Week 8. It is used to examine whether participants' social networks become smaller while they use the app. Within each arm, the Week 4 and Week 8 scores are compared with Week 0; no direction is predicted for the difference between arms.
Time frame: Baseline (Week 0), Week 4, and Week 8
Weekly emotional loneliness
De Jong Gierveld emotional subscale, 3 items, 0-3, completed in the app at Weeks 1 to 3. Together with Weeks 0 and 4, it is used to describe the trajectory of emotional loneliness with a mixed model that includes the interaction between arm and time, and to examine its within-person lagged association with weekly perceived responsiveness (exploratory).
Time frame: Weeks 0 through 4
Weekly perceived responsiveness
Weekly perceived responsiveness questionnaire, 12 items, completed in the app.
Time frame: Weeks 1 through 4
Patient Global Impression of Change in loneliness
One item asking how loneliness has changed compared with before the participant started using the app, with 7 options from much better to much worse, completed in the app.
Time frame: Weeks 1 through 8
Weekly social contact
Two items completed in the app, on the number of days with in-person contact and the number of days with remote contact in the past 7 days. Used to examine whether participants use the app in place of contact with other people (exploratory).
Time frame: Weeks 1 through 4
Loneliness (UCLA-3)
Three-item UCLA Loneliness Scale.
Time frame: Weeks 0, 4, and 8
Depressive symptoms (PHQ-9)
Time frame: Weeks 0 and 4
Anxiety symptoms (GAD-7)
Time frame: Weeks 0 and 4
Number of valid sessions
Number of valid conversation sessions logged by the app, using the same definition of a valid session as Primary Outcome 1.
Time frame: Weeks 1 through 4
Manipulation-check ratings
Ratings of the companions' responses in three randomly sampled valid sessions per participant, on understanding, validation, caring, and insensitivity. The Principal Investigator codes all sampled sessions; a second coder who is not told the arm codes about 20% of them.
Time frame: Weeks 1 through 4
Safety events
Safety events reported separately by source (participant input, scans of the AI reply, questionnaires, and assessor entries).
Time frame: Weeks 1 through 8
Attitudes toward AI in mental health (AIMHS)
Time frame: Weeks 0, 4, and 8 (optional at Week 8)
App quality and acceptability (uMARS)
Time frame: Week 4
Concerns about AI
4 study-specific items.
Time frame: Week 4
Continuance intention
3 items.
Time frame: Weeks 4 and 8
Retrospective pre-test of attitudes toward AI in mental health
AIMHS answered at Week 4 about how the participant felt before using the app (then-test).
Time frame: Week 4
Ratings of the weekly life-story chapter
Three study-specific items, each rated from 1 to 7 after each weekly chapter is shown, on whether the chapter matches what the participant said, satisfaction with the chapter, and willingness to show it to family or friends.
Time frame: Weeks 1 through 4
Daily mood
One optional item with five faces, which can be answered more than once a day; each answer is time-stamped.
Time frame: Weeks 1 through 8
Acceptability of the app (Theoretical Framework of Acceptability questionnaire)
Generic acceptability questionnaire based on the Theoretical Framework of Acceptability (Sekhon, Cartwright and Francis, 2022), 9 items each scored from 1 to 5, covering affective attitude, burden, ethicality (2 items), intervention coherence, perceived effectiveness, self-efficacy, opportunity costs, and general acceptability. Items are reported separately by arm; no total score is formed. Completed on paper at Week 4; Cantonese translation by the research team.
Time frame: Week 4
Plan to share: Yes — After publication, de-identified questionnaire and rating data will be provided through the Open Science Framework on reasonable request, subject to privacy review. Conversation text will not be shared.
Supporting information: Study protocol, Statistical analysis plan, Analytic code
Time frame: The data will be available after publication of the primary results, for as long as the de-identified data are kept under the data retention policy of The University of Hong Kong.
Access criteria: Researchers can request the data by contacting the Principal Investigator through the study's Open Science Framework project page and describing the intended analysis. Data are shared after a privacy review. Applicants must sign a data use agreement before they receive the data. Conversation text is not shared.
No publications or documents are linked to this record.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.