Making conversations with chatbots more personalized

Shumanov, Michael; Johnson, Lester W.

doi:10.1016/j.chb.2020.106627

Cited by 193 publications

(99 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While the Negative Technical Aspects theme was found in <10% of responses, it still shows that chatbots have limitations. Some users commented on chatbot misunderstandings which is consistent with past studies that have found that users expressed frustration when chatbots misunderstand questions and give irrelevant responses ( 19 ). This highlights the need to improve chatbot development including training of AI algorithms.…”

Section: Discussionsupporting

confidence: 88%

See 1 more Smart Citation

Bonding With Bot: User Feedback on a Chatbot for Social Isolation

Dosovitsky

Bunge

2021

Front. Digit. Health

View full text Add to dashboard Cite

Social isolation has affected people globally during the COVID-19 pandemic and had a major impact on older adult's well-being. Chatbot interventions may be a way to provide support to address loneliness and social isolation in older adults. The aims of the current study were to (1) understand the distribution of a chatbot's net promoter scores, (2) conduct a thematic analysis on qualitative elaborations to the net promoter scores, (3) understand the distribution of net promoter scores per theme, and (4) conduct a single word analysis to understand the frequency of words present in the qualitative feedback. A total of 7,099 adults and older adults consented to participate in a chatbot intervention on reducing social isolation and loneliness. The average net promoter score (NPS) was 8.67 out of 10. Qualitative feedback was provided by 766 (10.79%) participants which amounted to 898 total responses. Most themes were rated as positive (517), followed by neutral (311) and a minor portion as negative (70). The following five themes were found across the qualitative responses: positive outcome (277, 30.8%), user did not address question (262, 29.2%), bonding with the chatbot (240, 26.7%), negative technical aspects (70, 7.8%), and ambiguous outcome (49, 5.5%). Themes with a positive valence were found to be associated with a higher NPS. The word “help” and it's variations were found to be the most frequently used words, which is consistent with the thematic analysis. These results show that a chatbot for social isolation and loneliness was perceived positively by most participants. More specifically, users were likely to personify the chatbot (e.g., “Cause I feel like I have a new friend!”) and perceive positive personality features such as being non-judgmental, caring, and open to listen. A minor portion of the users reported dissatisfaction with chatting with a machine. Implications will be discussed.

show abstract

Section: Discussionsupporting

confidence: 88%

“…However, several studies reported concerns about negative aspects of the chatbots including the chatbot misunderstanding users which led to frustration when irrelevant comments are provided ( 19 ). Additionally, most chatbot studies present several limitations.…”

Section: Introductionmentioning

confidence: 99%

Bonding With Bot: User Feedback on a Chatbot for Social Isolation

Dosovitsky

Bunge

2021

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…The findings also indicated aspects that negatively affected the bond, such as dissatisfaction, perception of limitations of the conversational agent and perceived negative impact of the alliance with the conversational agent. The dissatisfaction and perceived ineffectiveness is consistent with extant literature which suggests that users express frustration when conversational agents misunderstand or give irrelevant responses ( 66 ). This indicates the need to further improve the AI algorithms and striking the balance in achieving human-like qualities.…”

Section: Discussionsupporting

confidence: 85%

Evaluating the Therapeutic Alliance With a Free-Text CBT Conversational Agent (Wysa): A Mixed-Methods Study

Beatty

Malik²,

Meheli

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

The present study aims to examine whether users perceive a therapeutic alliance with an AI conversational agent (Wysa) and observe changes in the t‘herapeutic alliance over a brief time period. A sample of users who screened positively on the PHQ-4 for anxiety or depression symptoms (N = 1,205) of the digital mental health application (app) Wysa were administered the WAI-SR within 5 days of installing the app and gave a second assessment on the same measure after 3 days (N = 226). The anonymised transcripts of user's conversations with Wysa were also examined through content analysis for unprompted elements of bonding between the user and Wysa (N = 950). Within 5 days of initial app use, the mean WAI-SR score was 3.64 (SD 0.81) and the mean bond subscale score was 3.98 (SD 0.94). Three days later, the mean WAI-SR score increased to 3.75 (SD 0.80) and the mean bond subscale score increased to 4.05 (SD 0.91). There was no significant difference in the alliance scores between Assessment 1 and Assessment 2.These mean bond subscale scores were found to be comparable to the scores obtained in recent literature on traditional, outpatient-individual CBT, internet CBT and group CBT. Content analysis of the transcripts of user conversations with the CA (Wysa) also revealed elements of bonding such as gratitude, self-disclosed impact, and personification. The user's therapeutic alliance scores improved over time and were comparable to ratings from previous studies on alliance in human-delivered face-to-face psychotherapy with clinical populations. This study provides critical support for the utilization of digital mental health services, based on the evidence of the establishment of an alliance.

show abstract

“…Topics that were less frequently studied in the research relate to the use of chatbots for FAQs/troubleshooting [66]- [68], recruiting [23], [24], [69], relationships with chatbots [70], [71], trust [28], [72], advertising [30], health [73], security [74], user classification [75], purchasing [50], personalisation [76] or surveys [77].…”

Section: A Research Focus and Applicationsmentioning

confidence: 99%