Abstract
Conversational agents (CAs) are increasingly ubiquitous and are now commonly used to access medical information. However, we lack systematic data about the quality of advice such agents provide. This paper evaluates CA advice for mental health (MH) questions, a pressing issue given that we are undergoing a mental health crisis. Building on prior work, we define a new method to systematically evaluate mental health responses from CAs. We develop multi-utterance conversational probes derived from two widely used mental health diagnostic surveys, the PHQ-9 (Depression) and the GAD-7 (Anxiety). We evaluate the responses of two text-based chatbots and four voice assistants to determine whether CAs provide relevant responses and treatments. Evaluations were conducted both by clinicians and immersively by trained raters, yielding consistent results across all raters. Although advice and recommendations were generally low quality, they were better for Crisis probes and for probes concerning symptoms of Anxiety rather than Depression. Responses were slightly improved for text versus speech-based agents, and when CAs had access to extended dialogue context. Design implications include suggestions for improved responses through clarification sub-dialogues. Responses may also be improved by the incorporation of empathy although this needs to be combined with effective treatments or advice.
- [1] . 2018. A tablet based embodied conversational agent to promote smoking cessation among veterans: A feasibility study. J. Epidemiol. Glob. Health 8, 3–4 (2018), 225–230.
DOI: Google ScholarCross Ref - [2] . 2020. Towards an ontology-based medication conversational agent for PrEP and PEP. Proc. Conf. Assoc. Comput. Linguist. Meet. 31–40.
DOI: Google ScholarCross Ref - [3] . 2017. Alexa, understand me. MIT Technology Review. Retrieved January 28, 2021 from https://www.technologyreview.com/2017/08/09/149815/alexa-understand-me/.Google Scholar
- [4] . 2013. How was your day? Evaluating a conversational companion. IEEE Trans. Affect. Comput. 4, 3 (2013), 299–311.
DOI: Google ScholarDigital Library - [5] . 2019. A chatbot versus physicians to provide information for patients with breast cancer: Blind, randomized controlled noninferiority trial. J. Med. Internet Res. 21, 11 (2019), e15787.
DOI: Google ScholarCross Ref - [6] . 2010. Response to a relational agent by hospital patients with depressive symptoms. Interact. Comput. 22, 4 (2010), 289–298.
DOI: Google ScholarDigital Library - [7] . 2018. Patient and consumer safety risks when using conversational assistants for medical information: An observational study of Siri, Alexa, and Google Assistant. J. Med. Internet Res. 20, 9 (2018).
DOI: Google ScholarCross Ref - [8] . 2007. How emotion is made and measured. Int. J. Hum.-Comput. Stud. 65, 4 (2007), 275–291.
DOI: Google ScholarDigital Library - [9] . 2018. Just ask Siri? A pilot study comparing smartphone digital assistants and laptop Google searches for smoking cessation advice. PLoS ONE 13, 3 (2018), e0194811.
DOI: Google ScholarCross Ref - [10] . 2020. Conversational agents in health care: Scoping review and conceptual analysis. J. Med. Internet Res. 22, 8 (2020), e17158.
DOI: Google ScholarCross Ref - [11] . 2019. When chatbots meet patients: One-year prospective study of conversations between patients with breast cancer and a chatbot. JMIR Cancer 5, 1 (2019), e12856.
DOI: Google ScholarCross Ref - [12] . 2018. Development and evaluation of a healthy coping voice interface application using the Google home for elderly patients with type 2 diabetes. In 2018 15th IEEE Annual Consumer Communications Networking Conference (CCNC). 1–5.
DOI: Google ScholarDigital Library - [13] . 2018. The state of speech in HCI: Trends, themes and challenges. (2018).
DOI: Google ScholarCross Ref - [14] . 2020. Mental health, substance use, and suicidal ideation during the COVID-19 pandemic — United States, June 24–30, 2020. MMWR Morb. Mortal. Wkly. Rep 69, (2020).
DOI: Google ScholarCross Ref - [15] . 2019. Acceptability, feasibility, and preliminary efficacy of a theory-based relational embodied conversational agent mobile phone intervention to promote HIV medication adherence in young HIV-positive African American MSM. AIDS Educ. Prev. 31, 1 (2019), 17–37.
DOI: Google ScholarCross Ref - [16] . 2020. Evaluating smart assistant responses for accuracy and misinformation regarding human papillomavirus vaccination: Content analysis study. J. Med. Internet Res. 22, 8 (2020), e19018.
DOI: Google ScholarCross Ref - [17] . 2017. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (Woebot): A randomized controlled trial. JMIR Ment. Health 4, 2 (2017), e19.
DOI: Google ScholarCross Ref - [18] . 2018. Using psychological artificial intelligence (Tess) to relieve symptoms of depression and anxiety: Randomized controlled trial. JMIR Ment. Health 5, 4 (2018), e64.
DOI: Google ScholarCross Ref - [19] . 2018. An empathy-driven, conversational artificial intelligence agent (Wysa) for digital mental well-being: Real-world data evaluation mixed-methods study. JMIR MHealth UHealth 6, 11 (2018), e12106.
DOI: Google ScholarCross Ref - [20] . 2019. Microsoft releases voice assistant usage report, finds Apple Siri and Google Assistant tied at 36%, and 41% of respondents have privacy concerns. Voicebot.ai. Retrieved January 28, 2021 from https://voicebot.ai/2019/04/28/microsoft-releases-voice-assistant-usage-report-finds-apple-siri-and-google-assistant-tied-at-36-and-41-of-respondents-have-privacy-concerns/.Google Scholar
- [21] . 2019. Psychological artificial intelligence service, Tess: Delivering on-demand support to patients and their caregivers: Technical report. Cureus 11, 1 (2019), e3972.
DOI: Google ScholarCross Ref - [22] . 2019. kBot: Knowledge-enabled personalized chatbot for asthma self-management. In 2019 IEEE International Conference on Smart Computing (SMARTCOMP). 138–143.
DOI: Google ScholarCross Ref - [23] . 2019. More than half of consumers want to use voice assistants for healthcare - new report from Voicebot and Orbita - voicebot.ai. Voicebot.ai. Retrieved January 22, 2021 from https://voicebot.ai/2019/10/29/more-than-half-of-consumers-want-to-use-voice-assistants-for-healthcare-new-report-from-voicebot-and-orbita/.Google Scholar
- [24] . 2020. Nearly 90 million U.S. adults have smart speakers, adoption now exceeds one-third of consumers - voicebot.ai. Voicebot.ai. Retrieved January 22, 2021 from https://voicebot.ai/2020/04/28/nearly-90-million-u-s-adults-have-smart-speakers-adoption-now-exceeds-one-third-of-consumers/.Google Scholar
- [25] . 2020. Responses of conversational agents to health and lifestyle prompts: Investigation of appropriateness and presentation structures. J. Med. Internet Res. 22, 2 (2020), e15823.
DOI: Google ScholarCross Ref - [26] . 2020. HarborBot: A chatbot for social needs screening. AMIA. Annu. Symp. Proc. 2019, (2020), 552–561.Google Scholar
- [27] . 2010. The patient health questionnaire somatic, anxiety, and depressive symptom scales: A systematic review. Gen. Hosp. Psychiatry 32, 4 (2010), 345–359.
DOI: Google ScholarCross Ref - [28] . 2018. Conversational agents in healthcare: A systematic review. J. Am. Med. Inform. Assoc. JAMIA 25, 9 (2018), 1248–1258.
DOI: Google ScholarCross Ref - [29] . 2018. Should machines express sympathy and empathy? Experiments with a health advice chatbot. Cyberpsychology Behav. Soc. Netw. 21, 10 (2018), 625–636.
DOI: Google ScholarCross Ref - [30] . 2017. A fully automated conversational agent for promoting mental well-being: A pilot RCT using mixed methods. Internet Interv. 10, (2017), 39–46.
DOI: Google ScholarCross Ref - [31] . 2016. Smartphone-based conversational agents and responses to questions about mental health, interpersonal violence, and physical health. JAMA Intern. Med. 176, 5 (2016), 619–625.
DOI: Google ScholarCross Ref - [32] , Anastas Philalithis, and Sofia Koukouli. 2020. The role of empathy in health and social care professionals. Healthcare 8, 1 (2020).
DOI: Google ScholarCross Ref - [33] . 1994. Computers are social actors. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI’94), Association for Computing Machinery, New York, NY, USA, 72–78.
DOI: Google ScholarDigital Library - [34] Pew Research Center. 2017. Nearly half of Americans use digital voice assistants, mostly on their smartphones. Pew Research Center. Retrieved January 22, 2021 from https://www.pewresearch.org/fact-tank/2017/12/12/nearly-half-of-americans-use-digital-voice-assistants-mostly-on-their-smartphones/.Google Scholar
- [35] . 2017. Virtual human as a new diagnostic tool, a proof of concept study in the field of major depressive disorders. Sci. Rep. 7, (2017), 42656.
DOI: Google ScholarCross Ref - [36] . 1996. The Media Equation: How People Treat Computers, Television, and New Media Like Real People and Places. Cambridge University Press, New York, NY, USA.Google ScholarDigital Library
- [37] . 2014. Mobile phone-based asthma self-management aid for adolescents (mASMAA): A feasibility study. Patient Prefer. Adherence 8, (2014), 63–72.
DOI: Google ScholarCross Ref - [38] . 2020. Readiness for voice assistants to support healthcare delivery during a health crisis and pandemic. npj Digit. Med. 3, 1 (2020), 1–4.
DOI: Google ScholarCross Ref - [39] . 2006. A brief measure for assessing generalized anxiety disorder: The GAD-7. Arch. Intern. Med. 166, 10 (2006), 1092.
DOI: Google ScholarCross Ref - [40] . 2019. Age, period, and cohort trends in mood disorder indicators and suicide-related outcomes in a nationally representative dataset, 2005-2017. J. Abnorm. Psychol. 128, 3 (2019), 185–199.
DOI: Google ScholarCross Ref - [41] . 2019. Chatbots and conversational agents in mental health: A review of the psychiatric landscape. Can. J. Psychiatry (2019), 070674371982897.
DOI: Google ScholarCross Ref - [42] . 1997. PARADISE: A framework for evaluating spoken dialogue agents. In 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, Madrid, Spain, 271–280.
DOI: Google ScholarDigital Library - [43] . 2018. Social media–based conversational agents for health management and interventions. Computer 51, 8 (2018), 26–33.
DOI: Google ScholarDigital Library - [44] . 1966. ELIZA—a computer program for the study of natural language communication between man and machine. Commun. ACM 9, 1 (1966), 36–45.
DOI: Google ScholarDigital Library - [45] WHO. Depression Fact Sheet. Retrieved January 21, 2021 from https://www.who.int/news-room/fact-sheets/detail/Depression.Google Scholar
- [46] . 2020. Impact of COVID-19 pandemic on mental health in the general population: A systematic review. J. Affect. Disord. 277, (2020), 55–64.
DOI: Google ScholarCross Ref
Index Terms
- “I don’t know what you mean by `I am anxious'”: A New Method for Evaluating Conversational Agent Responses to Standardized Mental Health Inputs for Anxiety and Depression
Recommendations
Exploring how politeness impacts the user experience of chatbots for mental health support
AbstractPoliteness is important in human–human interaction when asking people to engage in sensitive conversations. If politeness manifests similarly in human–chatbot interaction, it may play an important role in the design of sensitive chatbot ...
Highlights- Politeness can both positively and negatively impact the chatbot user experience.
- The Personal politeness chatbot was experienced as caring and encouraging.
- The Passive politeness chatbot was experienced as too apologetic and ...
The Effect of Emojis when interacting with Conversational Interface Assisted Health Coaching System
PervasiveHealth '18: Proceedings of the 12th EAI International Conference on Pervasive Computing Technologies for HealthcareThe recent rise of conversational interfaces have made it possible to integrate this technology into various domains, among which is health. Dialogue systems and conversational agents can bring a lot into healthcare to reduce cost, increase efficiency ...
Can Chatbots Help Support a Person’s Mental Health? Perceptions and Views from Mental Healthcare Professionals and Experts
Survey PaperThe objective of this study was to understand the attitudes of professionals who work in mental health regarding the use of conversational user interfaces, or chatbots, to support people’s mental health and wellbeing. This study involves an online ...
Comments