An official website of the United States government
BackgroundLaypeople have easy access to health information through large language models (LLMs), such as ChatGPT, and search engines, such as Google. Search engines transformed health information access, and LLMs offer a new avenue for answering laypeople’s questions. ObjectiveWe aimed to compare the frequency of use and attitudes toward LLMs and search engines as well as their comparative relevance, usefulness, ease of use, and trustworthiness in responding to health queries. MethodsWe conducted a screening survey to compare the demographics of LLM users and nonusers seeking health information, analyzing results with logistic regression. LLM users from the screening survey were invited to a follow-up survey to report the types of health information they sought. We compared the frequency of use of LLMs and search engines using ANOVA and Tukey post hoc tests. Lastly, paired-sample Wilcoxon tests compared LLMs and search engines on perceived usefulness, ease of use, trustworthiness, feelings, bias, and anthropomorphism. ResultsIn total, 2002 US participants recruited on Prolific participated in the screening survey about the use of LLMs and search engines. Of them, 52% (n=1045) of the participants were female, with a mean age of 39 (SD 13) years. Participants were 9.7% (n=194) Asian, 12.1% (n=242) Black, 73.3% (n=1467) White, 1.1% (n=22) Hispanic, and 3.8% (n=77) were of other races and ethnicities. Further, 1913 (95.6%) used search engines to look up health queries versus 642 (32.6%) for LLMs. Men had higher odds (odds ratio [OR] 1.63, 95% CI 1.34-1.99; P<.001) of using LLMs for health questions than women. Black (OR 1.90, 95% CI 1.42-2.54; P<.001) and Asian (OR 1.66, 95% CI 1.19-2.30; P<.01) individuals had higher odds than White individuals. Those with excellent perceived health (OR 1.46, 95% CI 1.1-1.93; P=.01) were more likely to use LLMs than those with good health. Higher technical proficiency increased the likelihood of LLM use (OR 1.26, 95% CI 1.14-1.39; P<.001). In a follow-up survey of 281 LLM users for health, most participants used search engines first (n=174, 62%) to answer health questions, but the second most common first source consulted was LLMs (n=39, 14%). LLMs were perceived as less useful (P<.01) and less relevant (P=.07), but elicited fewer negative feelings (P<.001), appeared more human (LLM: n=160, vs search: n=32), and were seen as less biased (P<.001). Trust (P=.56) and ease of use (P=.27) showed no differences. ConclusionsSearch engines are the primary source of health information; yet, positive perceptions of LLMs suggest growing use. Future work could explore whether LLM trust and usefulness are enhanced by supplementing answers with external references and limiting persuasive language to curb overreliance. Collaboration with health organizations can help improve the quality of LLMs’ health output.
more »
« less
Understanding and Mitigating Bias in Online Health Search
Search engines are perceived as a reliable source for general information needs. However, finding the answer to medical questions using search engines can be challenging for an ordinary user. Content can be biased and results may present different opinions. In addition, interpreting medically related content can be difficult for users with no medical background. All of these can lead users to incorrect conclusions regarding health related questions. In this work we address this problem from two perspectives. First, to gain insight on users' ability to correctly answer medical questions using search engines, we conduct a comprehensive user study. We show that for questions regarding medical treatment effectiveness, participants struggle to find the correct answer and are prone to overestimating treatment effectiveness. We analyze participants' demographic traits according to age and education level and show that this problem persists in all demographic groups. We then propose a semi-automatic machine learning approach to find the correct answer to queries on medical treatment effectiveness as it is viewed by the medical community. The model relies on the opinions presented in medical papers related to the queries, as well as features representing their impact. We show that, compared to human behaviour, our method is less prone to bias. We compare various configurations of our inference model and a baseline method that determines treatment effectiveness based solely on the opinion of medical papers. The results bolster our confidence that our approach can pave the way to developing automatic bias-free tools that can help mediate complex health related content to users.
more »
« less
- Award ID(s):
- 1553568
- PAR ID:
- 10300521
- Date Published:
- Journal Name:
- Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21)
- Page Range / eLocation ID:
- 265 to 274
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
When interacting with information retrieval (IR) systems, users, affected by confirmation biases, tend to select search results that confirm their existing beliefs on socially significant contentious issues. To understand the judgments and attitude changes of users searching online, our study examined how cognitively biased users interact with algorithmically biased search engine result pages (SERPs). We designed three-query search sessions on debated topics under various bias conditions. We recruited 1,321 crowdsourcing participants and explored their attitude changes, search interactions, and the effects of confirmation bias. Three key findings emerged: 1) most attitude changes occur in the initial query of a search session; 2) Confirmation bias and result presentation on SERPs affect the number and depth of clicks in the current query and perceived familiarity with clicked results in subsequent queries; 3) The bias position also affects attitude changes of users with lower perceived openness to conflicting opinions. Our study goes beyond traditional simulation-based evaluation settings and simulated rational users, sheds light on the mixed effects of human biases and algorithmic biases in information retrieval tasks on debated topics, and can inform the design of bias-aware user models, human-centered bias mitigation techniques, and socially responsible intelligent IR systems.more » « less
-
Many of the questions for training AIs how to answer questions come from the queries users type into search engines (like Google's Natural Questions). Is there a cheaper---perhaps even better---way? We propose a "naturalization" technique to turn high-quality, rigorously edited trivia questions into examples that resemble Natural Questions. Training on our naturalized questions and testing on natural questions comes close to the results with using Natural Questions, and we can improve results on MMLU (a standard modern evaluation set) by using our data.more » « less
-
null (Ed.)Users often need to look through multiple search result pages or reformulate queries when they have complex information-seeking needs. Conversational search systems make it possible to improve user satisfaction by asking questions to clarify users’ search intents. This, however, can take significant effort to answer a series of questions starting with “what/why/how”. To quickly identify user intent and reduce effort during interactions, we propose an intent clarification task based on yes/no questions where the system needs to ask the correct question about intents within the fewest conversation turns. In this task, it is essential to use negative feedback about the previous questions in the conversation history. To this end, we propose a Maximum-Marginal-Relevance (MMR) based BERT model (MMR-BERT) to leverage negative feedback based on the MMR principle for the next clarifying question selection. Experiments on the Qulac dataset show that MMR-BERT outperforms state-of-the-art baselines significantly on the intent identification task and the selected questions also achieve significantly better performance in the associated document retrieval tasks.more » « less
-
Search engines are some of the most popular and profitable intelligent technologies in existence. Recent research, however, has suggested that search engines may be surprisingly dependent on user-created content like Wikipedia articles to address user information needs. In this paper, we perform a rigorous audit of the extent to which Google leverages Wikipedia and other user-generated content to respond to queries. Analyzing results for six types of important queries (e.g. most popular, trending, expensive advertising), we observe that Wikipedia appears in over 80% of results pages for some query types and is by far the most prevalent individual content source across all query types. More generally, our results provide empirical information to inform a nascent but rapidly-growing debate surrounding a highly consequential question: Do users provide enough value to intelligent technologies that they should receive more of the economic benefits from intelligent technologies?more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3404835.3462930
