Leveraging Chatbots to Combat Health Misinformation for Older Adults: Participatory Design Study
Bibliographic record
Abstract
BACKGROUND: Older adults, a population particularly susceptible to misinformation, may experience attempts at health-related scams or defrauding, and they may unknowingly spread misinformation. Previous research has investigated managing misinformation through media literacy education or supporting users by fact-checking information and cautioning for potential misinformation content, yet studies focusing on older adults are limited. Chatbots have the potential to educate and support older adults in misinformation management. However, many studies focusing on designing technology for older adults use the needs-based approach and consider aging as a deficit, leading to issues in technology adoption. Instead, we adopted the asset-based approach, inviting older adults to be active collaborators in envisioning how intelligent technologies can enhance their misinformation management practices. OBJECTIVE: This study aims to understand how older adults may use chatbots' capabilities for misinformation management. METHODS: We conducted 5 participatory design workshops with a total of 17 older adult participants to ideate ways in which chatbots can help them manage misinformation. The workshops included 3 stages: developing scenarios reflecting older adults' encounters with misinformation in their lives, understanding existing chatbot platforms, and envisioning how chatbots can help intervene in the scenarios from stage 1. RESULTS: We found that issues with older adults' misinformation management arose more from interpersonal relationships than individuals' ability to detect misinformation in pieces of information. This finding underscored the importance of chatbots to act as mediators that facilitate communication and help resolve conflict. In addition, participants emphasized the importance of autonomy. They desired chatbots to teach them to navigate the information landscape and come to conclusions about misinformation on their own. Finally, we found that older adults' distrust in IT companies and governments' ability to regulate the IT industry affected their trust in chatbots. Thus, chatbot designers should consider using well-trusted sources and practicing transparency to increase older adults' trust in the chatbot-based tools. Overall, our results highlight the need for chatbot-based misinformation tools to go beyond fact checking. CONCLUSIONS: This study provides insights for how chatbots can be designed as part of technological systems for misinformation management among older adults. Our study underscores the importance of inviting older adults to be active co-designers of chatbot-based interventions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.046 | 0.036 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.008 | 0.004 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".