Conference PaperPDF Available

Design and Evaluation of a Mobile Chat App for the Open Source Behavioral Health Intervention Platform MobileCoach


Abstract and Figures

The open source platform MobileCoach ( has been used for various behavioral health interventions in the public health context. However, so far, MobileCoach is limited to text message-based interactions. That is, participants use error-prone and laborious text-input fields and have to bear the SMS costs. Moreover, MobileCoach does not provide a dedicated chat channel for individual requests beyond the processing capabilities of its chatbot. Intervention designers are also limited to text-based self-report data. In this paper, we thus present a mobile chat app with pre-defined answer options, a dedicated chat channel for patients and health professionals and sensor data integration for the MobileCoach platform. Results of a pretest (N = 11) and preliminary findings of a randomized controlled clinical trial (N = 14) with young patients, who participate in an intervention for the treatment of obesity, are promising with respect to the utility of the chat app.
Content may be subject to copyright.
Design and Evaluation of a Mobile Chat App
for the Open Source Behavioral Health
Intervention Platform MobileCoach
Tobias Kowatsch
, Dirk Volland
, Iris Shih
, Dominik Rüegger
Florian Künzler
, Filipe Barata
, Andreas Filler
, Dirk Büchter
Björn Brogle
, Katrin Heldt
, Pauline Gindrat
Nathalie Farpour-Lambert
, and Dagmar lAllemand
Institute of Technology Management,
University of St. Gallen, St. Gallen, Switzerland
Department of Management, Technology and Economics,
ETH Zurich, Zurich, Switzerland
Energy Efcient Systems Group, University of Bamberg, Bamberg, Germany
Childrens Hospital of Eastern Switzerland, St. Gallen, Switzerland
Fondation SportSmile, Nyon, Switzerland
Department of Community Medicine, Primary Care and Emergency,
University Hospital of Geneva/University of Geneva, Geneva, Switzerland
Abstract. The open source platform MobileCoach ( has been
used for various behavioral health interventions in the public health context.
However, so far, MobileCoach is limited to text message-based interactions.
That is, participants use error-prone and laborious text-input elds and have to
bear the SMS costs. Moreover, MobileCoach does not provide a dedicated chat
channel for individual requests beyond the processing capabilities of its chatbot.
Intervention designers are also limited to text-based self-report data. In this
paper, we thus present a mobile chat app with pre-dened answer options, a
dedicated chat channel for patients and health professionals and sensor data
integration for the MobileCoach platform. Results of a pretest (N= 11) and
preliminary ndings of a randomized controlled clinical trial (N= 14) with
young patients, who participate in an intervention for the treatment of obesity,
are promising with respect to the utility of the chat app.
Keywords: Health intervention Digital coaching Chat-based interaction
1 Introduction
Non communicable diseases (NCDs) such as heart diseases, asthma, obesity, diabetes
or chronic kidney disease impose the greatest burden on global health [14]. According
to WHOs NCD global monitoring framework, many of these diseases are conse-
quences of adverse health behaviors, for example, harmful use of alcohol and tobacco
or physical inactivity [15]. However, health personnel is strongly limited [2]. Conse-
quently, scalable behavioral health interventions are required.
©Springer International Publishing AG 2017
A. Maedche et al. (Eds.): DESRIST 2017, LNCS 10243, pp. 485489, 2017.
DOI: 10.1007/978-3-319-59144-5_36
Innovative digital health interventions (DHIs) have not only the potential to
improve the efcacy of preventive or therapeutic behavioral health interventions but
also to reduce their costs [1]. With the goal to provide an open source platform that
allows health professionals to design scalable, low-cost and evidence-based DHIs,
MobileCoach ( was developed [5] and evaluated [9].
However, it uses the short message service (SMS) for delivering behavioral health
interventions, and thus comes with various shortcomings as outlined in the next
section. We therefore present in this paper the rst mobile chat app for the Mobile-
Coach platform that addresses these shortcomings and thus, complements existing
communication such as personal exchange, SMS-based, phone-based or video-based
The remainder of this paper is structured as follows. Next, we describe the design of
the chat app. Then, the apps signicance to research and practice is outlined. Finally,
we present results from an empirical study with 11 obese children who assessed the
new chat app as the rst target group.
2 Design of the Chat App
Hands-on experience with several MobileCoach-based interventions [79] has revealed
four major shortcomings related to its text messaging approach. First, participants have
to bear the SMS costs which may be an entry barrier if the caregiver does not provide a
monetary compensation. Second, participants are always requested to manually type in
text to answer even Likert-scale type questions. These answers are then parsed by the
MobileCoach, which is error-prone in case the answer does not perfectly t to the
question. Processing these answers is a time-consuming process for the caregiver, too.
Third, participant-initiated requests usually require an individual answer from a care-
giver instead of a scripted answer by a chatbot. A rule-based chatbot does therefore not
always t to the communication needs of the participants. Fourth, text-messaging is
limited to self-report data, i.e. health professionals cannot use objective sensor data
from a smartphone (e.g., accelerometer data used to measure physical activity) or
sensor data from devices connected to that smartphone (e.g., Bluetooth-enabled blood
glucose or peak ow meters) for the design of their DHIs.
Regarding these shortcomings and against the background of smartphone perva-
siveness [4], the following requirements have been dened: (R1) The app must not rely
on the short message service for communication purposes; (R2) the app must imple-
ment pre-dened answer sets for efcient and error-free chat interaction; (R3) the app
must implement a chat channel for individual communication needs that complements
the scalable chatbot channel; (R4) the app must be able to access sensor data from the
smartphone or smartphone-connected devices.
By considering these four requirements, we built a rst mock-up of a mobile app
and evaluated it with six behavioural health experts. As a result of that assessment, a
generic dashboard view was designed. Its purpose is to summarize key statistics of the
envisioned behavioural health interventions for self-monitoring purposes (e.g. steps
achieved per day, intervention progress or goals achieved). Based on this generic
486 T. Kowatsch et al.
mock-up, we implemented a native chat app for Android smartphones for the Mobi-
leCoach platform. Figures 1,2and 3show the graphical user interface of the chat app.
3 Signicance to Research and Practice
The mobile chat app presented in this paper allows behavioral scientists and health
professionals to enrich self-report data with objective sensor data in the everyday life of
their clients. This paves the way for a better understanding of whether psychological/
self-report data and physiological/objective data are rather complement or alternative
measures, a recent research question in the eld of NeuroIS [13].
Moreover, it is by far not clear how to design and frame chatbots for DHIs (e.g., as
an expert or a patient like me) and its interplay with a physicalcaregiver such that
they have a positive effect on the bond between caregiver and their clients and thus,
also on therapeutic outcomes [6]. In contrast to general purpose chat agents such as Siri
(Apple), Alexa (Amazon) or Cortana (Microsoft) and agents with a health focus such as
Florence (, Molly ( or Lark (, our chat app allows
full control of personal health data and a generic framework to manipulate the design
and communication style of chatbots in lab and eld settings.
Finally and consistent with the MobileCoach platform, the chat app will be made
open source under the Apache 2.0 license to enable a community-driven design such
that research teams and (business) organizations interested in chat-based digital
coaching approaches do not have to start from scratch but can re-use, revise and
improve the existing code together with the MobileCoach platform.
Fig. 1. Dashboard view, indi-
vidual caregiver chat channel
PathMate and channel with
chatbot Anna
Fig. 2. Chatbot Anna, pre-
dened answer options and
sensor integration; steps are
tracked and used in the chat
Fig. 3. Chat channel with
the caregiver; the PathMate
study team of the childrens
Mobile Chat App for the Open Source Platform MobileCoach 487
4 Evaluation of the Artifact
Based on prior work demonstrating the acceptance of chat apps by adolescents [11], the
rst test of the novel chat app was conducted in a childrens hospital in December 2016
with 11 patients (age
= 12.6 years, SD = 2.4; 8 girls), who participated in an
intervention for the treatment of obesity. The goal of this test was (1) to assess
enjoyment, ease of use, usefulness and the intention to use the app [10], and (2) to
identify and address major usability problems with the app [12] prior to a randomized
controlled trial (RCT), in which the efcacy of a chat-based six-month DHI for the
treatment of childhood obesity will be compared to a control group.
First, a chat-based DHI was collaboratively designed by computer scientists,
physicians, a psychotherapist, diet and sport experts. The patients were then asked to
select a chatbot of their liking, i.e. they could choose between a female and male
chatbot (Anna or Lukas). Then, they interacted with the bot for 10 min including
various chat-based photo, physical activity and quiz interactions. The patients were
observed during these interactions by a computer scientist and physician. Afterwards,
patients were asked to ll out a questionnaire to assess the app and to provide quali-
tative feedback on their experience with the app. Similar to prior work [10], we
assessed technology perceptions and behavioral intentions with seven-point Likert
scales anchored from strongly disagree (1) to strongly agree (7). As young patients
deserve special consideration, we used single-item measures to reduce the burden of
evaluation [3].
The descriptive statistics of the evaluation are shown in Table 1. Results indicate
that the chat app was perceived positive regarding all four constructs. A sign test
against the neutral Likert-scale median of 4 supports this observation. Finally, we
found no major usability problems based on the observations and the qualitative
First ndings of the aforementioned RCT show that new young patients assigned to
the chat-based DHI (N= 14) completed successfully approx. 61% of the daily inter-
vention tasks over the rst two months. The efcacy of this DHI will be nally
measured by the Body Mass Index after the six-month RCT. We hypothesize that the
chat-based DHI is more effective as the chatbot can provide everyday support on
therapy goals and tasks, thus increasing therapy adherence compared to patients of the
treatment-as-usual control group without everyday support.
Table 1. Descriptive statistics and results of a sign test against the neutral value 4 on a 7-point
Likert-scale (N= 11). Note: Perceived ease of use (PEU), Perceived enjoyment (PEN), Perceived
usefulness (PU) and Intention to use (IU); Signicance */**/*** p < .05 /.01 /.001
# Item Mean Median SD p-value
PEU I found the chat easy to use 6.7 7.0 0.7 ***
PEN I enjoyed chatting 6.2 7.0 1.5 **
PU Chatting with Lukas/Anna could motivate me
to accomplish my intervention tasks
5.9 6.0 1.1 *
IU I could imagine chatting daily that way 5.6 6.0 1.4 *
488 T. Kowatsch et al.
In our future work, we will test chat-based DHIs with older patient populations and
different therapies to assess the degree to which our ndings can be generalized.
Acknowledgements. We would like to thank the CSS Insurance and the Swiss National Science
Foundation for their support through grants 159289 and 162724.
1. Agarwal, R., Gao, G., DesRoches, C., et al.: The digital transformation of healthcare: current
status and the road ahead. Inf. Syst. Res. 21, 796809 (2010)
2. Aluttis, C., Bishaw, T., Frank, M.W.: The workforce for health in a globalized context
global shortages and international migration. Glob. Health Action 7(2014). https://www.
3. Bergkvist, L., Rossiter, J.R.: The predictive validity of multiple-item versus single-item
measures of the same constructs. J. Mark. Res. 44, 175184 (2007)
4. Chaffey, D.: Mobile Marketing Statistics compilation (2016).
. Accessed Feb 2017
5. Filler, A., Kowatsch, T., Haug, S., et al.: MobileCoach: a novel open source platform for the
design of evidence-based, scalable and low-cost behavioral health interventions. In: 14th
Annual Wireless Telecommunications Symposium (WTS 2015), New York (2015)
6. Flückiger, C., Del Re, A.C., Wampold, B.E., et al.: How central is the alliance in
psychotherapy? A multilevel longitudinal meta-analysis. J. Couns. Psychol. 59,1017
7. Haug, S., Kowatsch, T., Paz Castro, R., et al.: Efcacy of a web- and text messaging-based
intervention to reduce problem drinking in young people: study protocol of a
cluster-randomised controlled trial. BMC Public Health 14,18 (2014)
8. Haug, S., Paz Castro, R., Filler, A., et al.: Efcacy of an internet and SMS-based integrated
smoking cessation and alcohol intervention for smoking cessation in young people: study
protocol of a two-arm cluster randomised controlled trial. BMC Public Health 14, 1140
9. Haug, S., Paz, R., Kowatsch, T., et al.: Efcacy of a web- and text messaging-based
intervention to reduce problem drinking in adolescents: Results of a cluster-randomised
controlled trial. J. Consult. Clin. Psychol. 85, 147159 (2017)
10. Kamis, A., Koufaris, M., Stern, T.: Using an attribute-based decision support system for
user-customized products online: an experimental investigation. MIS Q. 32, 159177 (2008)
11. Lilian, S., Gregor, W., Sarah, G., et al.: MIKE - Medien, Interaktion, Kinder, Eltern. Zürcher
Hochschule für Angewandte Wissenschaften, Zürich (2015)
12. Nielsen, J., Landauer, T.K.: A mathematical model of the nding of usability problems. In:
CHI 1993 Proceedings of the INTERACT 1993 and CHI 1993 Conference on Human
Factors in Computing Systems, pp. 206213. ACM, Amsterdam (1993)
13. Tams, S., Hill, K., de Guinea, A.O., et al.: NeuroIS - alternative or complement to existing
methods? Illustrating the holistic effects of neuroscience and self-reported data in the context
of technostress research. J. Assoc. Inf. Syst. 15, Article 1 (2014)
14. WHO: Global Health and Aging. World Health Organization, Genéve, Switzerland (2011)
15. WHO: Draft comprehensive global monitoring framework and targets for the prevention and
control of noncommunicable diseases. World Health Organization, Genéve, Switzerland
Mobile Chat App for the Open Source Platform MobileCoach 489
... Once the team agreed that the sketches and wireframesreflected and appropriately translated the underpinning research and formative activities of LvL UP 1.0 (phases 1 and 2), the software development team used MobileCoach for the technical implementation. MobileCoach ( is an open-source software platform for digital biomarker and intervention research (117,118). MobileCoach has been successfully used for the development of a digital biomarker for asthma control (119)(120)(121), the delivery of digital health literacy (72), physical activity (122), personality development (123), chronic pain (68), childhood obesity (124) and holistic wellbeing during the COVID-19 pandemic (125). ...
Full-text available
Background Non-communicable diseases (NCDs) and common mental disorders (CMDs) are the leading causes of death and disability worldwide. Lifestyle interventions via mobile apps and conversational agents present themselves as low-cost, scalable solutions to prevent these conditions. This paper describes the rationale for, and development of, “LvL UP 1.0″, a smartphone-based lifestyle intervention aimed at preventing NCDs and CMDs. Materials and Methods A multidisciplinary team led the intervention design process of LvL UP 1.0, involving four phases: (i) preliminary research (stakeholder consultations, systematic market reviews), (ii) selecting intervention components and developing the conceptual model, (iii) whiteboarding and prototype design, and (iv) testing and refinement. The Multiphase Optimization Strategy and the UK Medical Research Council framework for developing and evaluating complex interventions were used to guide the intervention development. Results Preliminary research highlighted the importance of targeting holistic wellbeing (i.e., both physical and mental health). Accordingly, the first version of LvL UP features a scalable, smartphone-based, and conversational agent-delivered holistic lifestyle intervention built around three pillars: Move More (physical activity), Eat Well (nutrition and healthy eating), and Stress Less (emotional regulation and wellbeing). Intervention components include health literacy and psychoeducational coaching sessions, daily “Life Hacks” (healthy activity suggestions), breathing exercises, and journaling. In addition to the intervention components, formative research also stressed the need to introduce engagement-specific components to maximise uptake and long-term use. LvL UP includes a motivational interviewing and storytelling approach to deliver the coaching sessions, as well as progress feedback and gamification. Offline materials are also offered to allow users access to essential intervention content without needing a mobile device. Conclusions The development process of LvL UP 1.0 led to an evidence-based and user-informed smartphone-based intervention aimed at preventing NCDs and CMDs. LvL UP is designed to be a scalable, engaging, prevention-oriented, holistic intervention for adults at risk of NCDs and CMDs. A feasibility study, and subsequent optimisation and randomised-controlled trials are planned to further refine the intervention and establish effectiveness. The development process described here may prove helpful to other intervention developers.
... All questionnaires were programmed using LimeSurvey (LimeSurvey Project, 2012). A study app was developed for the tablet with the open-source software MobileCoach (Filler et al., 2015;Kowatsch et al., 2017). The app PHYSICAL ACTIVITY FOLLOWING CR 3 delivered the questionnaires to the patients via a conversational agent, that is, a computer program that imitates communication with a human being (Cassell, 2000). ...
Purpose: The adoption of a healthy lifestyle is crucial for patients with established cardiac diseases. However, many patients do not engage in regular physical activity in their everyday life. Research method: The present study applied the health action process approach (HAPA) in an intensive longitudinal research design (n = 3,354 daily surveys) investigating intention towards physical activity and objectively measured physical activity in 137 cardiac patients (Mage = 62.1 years) during and after inpatient rehabilitation across 28 days. Self-reported HAPA variables were measured daily in online questionnaires at the end of each day. Theory-driven hypotheses were tested using linear multilevel models. Results: One-third of the sample did not reach the recommended physical activity levels in the first weeks after discharge from rehabilitation. Results are mostly in line with the motivational HAPA phase at both levels of analysis; outcome expectations and self-efficacy were positively associated with intentions. Results for the volitional phase were partly in line with the HAPA. Daily deviations in previous-day planning and concurrent action control were positively associated with physical activity during and after cardiac rehabilitation. Conclusion: The results of this study partly speak towards the HAPA in predicting physical activity in cardiac patients, thereby replicating prior research. The HAPA framework offers guidance for motivating and empowering cardiac patients to be more active in their everyday life. (PsycInfo Database Record (c) 2023 APA, all rights reserved).
... The chatbots were satisfying since they contain attractive multimedia; understandable content; friendly, empathetic dialogue; and utility as well as being easy to use. This is consistent with other studies showing high acceptability via chat enjoyment, bonding, creation of social and emotional relationships, ease of use, usefulness, and a desire to use [38,39]. ...
... However, successful lifestyle behavior change is often difficult to achieve and is only implemented by a fraction of those in need [16]. Furthermore, the personal everyday coaching by human healthcare professionals that often accompanies lifestyle behavior interventions is neither scalable nor financially sustainable by healthcare systems [17]. ...
Full-text available
Background: Despite an abundance of digital health interventions (DHIs) targeting the prevention and management of noncommunicable diseases (NCDs), it is unclear what specific components make a DHI effective. Purpose: This narrative umbrella review aimed to identify the most effective behavior change techniques (BCTs) in DHIs that address the prevention or management of NCDs. Methods: Five electronic databases were searched for articles published in English between January 2007 and December 2022. Studies were included if they were systematic reviews or meta-analyses of DHIs targeting the modification of one or more NCD-related risk factors in adults. BCTs were coded using the Behavior Change Technique Taxonomy v1. Study quality was assessed using AMSTAR 2. Results: Eighty-five articles, spanning 12 health domains and comprising over 865,000 individual participants, were included in the review. We found evidence that DHIs are effective in improving health outcomes for patients with cardiovascular disease, cancer, type 2 diabetes, and asthma, and health-related behaviors including physical activity, sedentary behavior, diet, weight management, medication adherence, and abstinence from substance use. There was strong evidence to suggest that credible source, social support, prompts and cues, graded tasks, goals and planning, feedback and monitoring, human coaching and personalization components increase the effectiveness of DHIs targeting the prevention and management of NCDs. Conclusions: This review identifies the most common and effective BCTs used in DHIs, which warrant prioritization for integration into future interventions. These findings are critical for the future development and upscaling of DHIs and should inform best practice guidelines.
... Each topic covers a specific class of functionalities (i.e., start anamnesis, change data, check protocol) or an interaction modality (i.e., say goodbye, feeling good dialogue, explanation modality). In [49] a chatbot solution based on predefined answer sets is proposed. The "quality in use" was also measured in this case through a 7-point Likert scale questionnaire. ...
Background Conversational agents are currently a valid alternative to humans in first-level interviews with users who need information, even in-depth, about services or products. In application domains such as health care, this technology can become pervasive only if the perceived ”quality in use” is appropriate. How to measure chatbot quality is an open question. The international standard ISO/IEC 25010 proposes a set of characteristics (effectiveness, efficiency, satisfaction, freedom from risk, and context coverage) to be considered when the ”quality in use” of a software system has to be measured. Basic procedure This study proposes a clinical chatbot comparison method based on quality. The proposed approach is based on Analytic Hierarchy Process methodology (AHP). Findings Our contribution is twofold. First, we propose a set of measures for each characteristic of ISO/IEC 25010 according to three classes of functionality: providing information, providing prescriptions and process management. Moreover a quantitative method is proposed for making homogeneous the pairwise weights when the AHP is used for the ”quality-in-use” comparison. As a case study, a comparison of two versions of a chatbot was performed. Conclusions The results show that the proposed approach provides an effective reference base for performing quality comparisons of medical chatbots compliant with the ISO/IEC 25010 standard.
... The DHI is implemented in a mobile app using the MobileCoach intervention platform [40,41], an open-source platform for the design and deployment of DHIs based on rule-based CA. Here, the participant chooses 1 of 4 coaches before the intervention, and the intervention information is provided as text messages, graphics, and videos or by gamification and storytelling approaches by emulating human-like interactions (Figure 1). ...
Full-text available
Background Long-term unemployed have poor nutritional and physical activity statuses, and, therefore, special health promotion needs. Particularly in rural areas, however, they often do not have access to health promotion service. Thus, new promising strategies to improve the health of long-term unemployed are needed. Hence, a digital health intervention to promote nutritional and physical health behaviors was conceived, and the effectiveness of the intervention in combination with face-to-face sessions will be evaluated in a randomized controlled trial. Objective The aim of this study is to elucidate the effectiveness of a mobile digital health intervention to promote the nutritional and physical activity behaviors of long-term unemployed in the rural areas of Germany. Methods The 9-week intervention aims to promote nutritional or physical activity behavior by improving drinking habits, increasing the consumption of fruits, vegetables, and whole grains, increasing daily step count, strengthening muscles, and improving endurance. The intervention design is based on the transtheoretical model and is implemented in a mobile app using the MobileCoach open-source platform. The effectiveness of the intervention will be elucidated by a 9-week, 2-armed, parallel-designed trial. Therefore, long-term unemployed will be recruited by employees of the German social sector institutions and randomized either to receive information brochures; the digital intervention in the form of a mobile app; and 3 face-to-face sessions regarding technical support, healthy eating, and physical activity (n=100) or to receive a control treatment consisting of solely the hand over of information brochures (n=100). The effectiveness of the intervention will be assessed using questionnaires at baseline, after 9 weeks in face-to-face appointments, and after a 3-month follow-up period by postal contact. The use of the mobile app will be monitored, and qualitative interviews or focus groups with the participants will be conducted. Incentives of €50 (US $49.7) will be paid to the participants and are tied to the completion of the questionnaires and not to the use of the mobile app or progress in the intervention. Results The effectiveness of the intervention in promoting the nutritional and physical activity behaviors of long-term unemployed participants will be elucidated. The adherence of the participants to and the acceptance and usability of the mobile device app will be evaluated. Recruitment started in March 2022, and the final publication of the results is expected in the first half of 2023. Conclusions Positive health-related changes made by the intervention would display the potency of digital health interventions to promote nutritional and physical activity behaviors among long-term unemployed in the rural areas of Germany, which would also contribute to an improved health status of the German population in general. Trial Registration German Clinical Trials Register DRKS00024805; International Registered Report Identifier (IRRID) PRR1-10.2196/40321
... The intervention for this study was delivered entirely on the web via the Benefit Move app, which the participants downloaded on their smartphones. The Benefit Move app was implemented using MobileCoach [42,43], an open-source software platform for smartphone-based and chatbot-delivered behavioral interventions (eg, study by Kowatsch et al [44]) and ecological momentary assessments (eg, study by Tinschert et al [45]). MobileCoach was developed by the Centre for Digital Health Interventions at Eidgenössische Technische Hochschule Zürich and the University of St. Gallen in Switzerland [46]. ...
Full-text available
Background Financial incentive interventions for improving physical activity have proven to be effective but costly. Deposit contracts (in which participants pledge their own money) could be an affordable alternative. In addition, deposit contracts may have superior effects by exploiting the power of loss aversion. Previous research has often operationalized deposit contracts through loss framing a financial reward (without requiring a deposit) to mimic the feelings of loss involved in a deposit contract. Objective This study aimed to disentangle the effects of incurring actual losses (through self-funding a deposit contract) and loss framing. We investigated whether incentive conditions are more effective than a no-incentive control condition, whether deposit contracts have a lower uptake than financial rewards, whether deposit contracts are more effective than financial rewards, and whether loss frames are more effective than gain frames. Methods Healthy participants (N=126) with an average age of 22.7 (SD 2.84) years participated in a 20-day physical activity intervention. They downloaded a smartphone app that provided them with a personalized physical activity goal and either required a €10 (at the time of writing: €1=US $0.98) deposit up front (which could be lost) or provided €10 as a reward, contingent on performance. Daily feedback on incentive earnings was provided and framed as either a loss or gain. We used a 2 (incentive type: deposit or reward) × 2 (feedback frame: gain or loss) between-subjects factorial design with a no-incentive control condition. Our primary outcome was the number of days participants achieved their goals. The uptake of the intervention was a secondary outcome. ResultsOverall, financial incentive conditions (mean 13.10, SD 6.33 days goal achieved) had higher effectiveness than the control condition (mean 8.00, SD 5.65 days goal achieved; P=.002; ηp2=0.147). Deposit contracts had lower uptake (29/47, 62%) than rewards (50/50, 100%; P
... The chatbots were satisfying since they contain attractive multimedia; understandable content; friendly, empathetic dialogue; and utility as well as being easy to use. This is consistent with other studies showing high acceptability via chat enjoyment, bonding, creation of social and emotional relationships, ease of use, usefulness, and a desire to use [38,39]. ...
Full-text available
Background: It is recommended that caregivers receive oral health education and in-person training to improve tooth brushing for young children. To strengthen oral health education before COVID-19, the 21-Day FunDee chatbot with in-person tooth brushing training for caregivers was employed. During the pandemic, however, practical experience was difficult to implement. Therefore, the 30-Day FunDee chatbot was created to extend the coverage of chatbots from 21 to 30 days by incorporating more videos on tooth brushing demonstrations and dialogue. This was a secondary data comparison of two chatbots in similar rural areas of Pattani province, Maikan district (Study I) and Maelan district (Study II). Objective: This study aimed to evaluate the effectiveness and usability of two chatbots, 21-Day FunDee (Study I) and 30-Day FunDee (Study II), based on the protection-motivation theory (PMT). Furthermore, the study explored the feasibility of employing 30-Day FunDee chatbot to increase tooth brushing behaviors for caregivers in oral hygiene care for children aged 6-36 months without in-person training during the COVID-19 pandemic. Methods: A pre-post design was used in both studies. The effectiveness of each chatbot was evaluated among caregivers in terms of oral hygiene practices, knowledge, and oral health care perceptions based on PMT. In Study I, participants received in-person training and a 21-day chatbot course during October 2018 to February 2019. In Study II, participants received only daily chatbot programming for 30 days during December 2021 to February 2022. Data was gathered at baseline of each study and at 30 and 60 days after the start of Study I and Study II, respectively. Only Study I evaluated the plaque score. Open-ended questions in chatbot programs were used to assess the usability of chatbots at the end of their interventions. Only Study II included an in-depth interview. The two studies were compared to determine the feasibility of using the 30-Day FunDee chatbot by an alternative method of in-person training. Results: There were 71 pairs of participants in total, 37 for Study I and 34 for Study II. Both chatbots significantly improved overall knowledge (P<.001; 0.73 (SD 0.21), 0.94 (SD 0.09)) (P=.001; 0.53 (SD 0.26), 0.66 (SD 0.23)), overall oral health care perceptions based on PMT P<.001; 0.58 (SD 0.19), 0.86 (SD 0.16), P<.001; 0.53 (SD 0.26), 0.83 (SD 0.12), and tooth brushing for children by caregivers (P=.02, P=.04) in Study I and Study II, respectively. Only Study I differed statistically significant for frequency of tooth brushing at least twice a day (P=.002) and perceived vulnerability (P=.003; 0.46 (SD 0.51), 0.78 (SD 0.42)). Overall chatbot satisfactions were reported at the highest level at 9.2 (SD 0.9) and 8.6 (SD 1.2) for Study I and Study II, respectively. In Study I, plaque levels differed significantly. (P<0.001; 0.48 (SD 0.33), 0.18 (SD 0.21). Conclusions: This was the first study using a chatbot in oral health education. Two chatbot programs established their effectiveness and usability in promoting oral hygiene care of caregivers for young children. The 30-Day FunDee chatbot showed the possibility to improve tooth brushing skills without requiring in-person training.
The social psychology of eating and artificial intelligence can be integrated to develop effective online and personalized interventions to promote sustainable lifestyles that consider individual preferences and orientations. Combining the explanatory power of social psychological models with the predictive power of data-driven artificial intelligence is a promising strategy for effectively promoting sustainable and healthy dietary choices through personalized and automated message-based interventions. Artificial intelligence models can develop automatic interaction systems that adapt to the characteristics of the recipients to enable effective communication. Thanks to these automated systems, communication to promote healthy and sustainable eating habits can address a very large and diverse audience, considering the needs and resources of each individual. All this is done with full awareness of the risks, but also the benefits, that digital communication can bring. Chatbots can provide personalized and empathetic communication that adapts to the user’s motivations and resources, helping to maintain motivation over time.KeywordsArtificial intelligencePredictive powerAutomated communication strategiesChatbotRisks of digital communicationBenefits of digital communication
Full-text available
Background: Chatbots are an emerging technology that show potential for mental health care apps to enable effective and practical evidence-based therapies. As this technology is still relatively new, little is known about recently developed apps and their characteristics and effectiveness. Objective: In this study, we aimed to provide an overview of the commercially available popular mental health chatbots and how they are perceived by users. Methods: We conducted an exploratory observation of 10 apps that offer support and treatment for a variety of mental health concerns with a built-in chatbot feature and qualitatively analyzed 3621 consumer reviews from the Google Play Store and 2624 consumer reviews from the Apple App Store. Results: We found that although chatbots' personalized, humanlike interactions were positively received by users, improper responses and assumptions about the personalities of users led to a loss of interest. As chatbots are always accessible and convenient, users can become overly attached to them and prefer them over interacting with friends and family. Furthermore, a chatbot may offer crisis care whenever the user needs it because of its 24/7 availability, but even recently developed chatbots lack the understanding of properly identifying a crisis. Chatbots considered in this study fostered a judgment-free environment and helped users feel more comfortable sharing sensitive information. Conclusions: Our findings suggest that chatbots have great potential to offer social and psychological support in situations where real-world human interaction, such as connecting to friends or family members or seeking professional support, is not preferred or possible to achieve. However, there are several restrictions and limitations that these chatbots must establish according to the level of service they offer. Too much reliance on technology can pose risks, such as isolation and insufficient assistance during times of crisis. Recommendations for customization and balanced persuasion to inform the design of effective chatbots for mental health support have been outlined based on the insights of our findings.
Full-text available
Recent research has made a strong case for the importance of NeuroIS methods for IS research. It has suggested that NeuroIS contributes to an improved explanation and prediction of IS phenomena. Yet, such research is unclear on the source of this improvement; while some studies indicate that NeuroIS constitutes an alternative to psychometrics, implying that the two methods assess the same dimension of an underlying IS construct, other studies indicate that NeuroIS constitutes a complement to psychometrics, implying that the two methods assess different dimensions of an IS construct. To clarify the role of NeuroIS in IS research and its contribution to IS research, in this study, we examine whether NeuroIS and psychometrics/psychological methods constitute alternatives or complements. We conduct this examination in the context of technostress, an emerging IS phenomenon to which both methods are relevant. We use the triangulation approach to explore the relationship between physiological and psychological/self-reported data. Using this approach, we argue that both kinds of data tap into different aspects of technostress and that, together, they can yield a more complete or holistic understanding of the impact of technostress on a theoretically-related outcome, rendering them complements. Then, we test this proposition empirically by probing the correlation between a psychological and a physiological measure of technostress in combination with an examination of their incremental validity in explaining performance on a computer-based task. The results show that the physiological stress measure (salivary alpha-amylase) explains and predicts variance in performance on the computer-based task over and above the prediction afforded by the self-reported stress measure. We conclude that NeuroIS is a critical complement to IS research. © 2014, Association for Information Systems. All rights reserved.
Full-text available
BACKGROUND: Tobacco smoking prevalence continues to be high, particularly among adolescents and young adults with lower educational levels, and is therefore a serious public health problem. Tobacco smoking and problem drinking often co-occur and relapses after successful smoking cessation are often associated with alcohol use. This study aims at testing the efficacy of an integrated smoking cessation and alcohol intervention by comparing it to a smoking cessation only intervention for young people, delivered via the Internet and mobile phone.
Full-text available
Background Problem drinking, particularly risky single-occasion drinking is widespread among adolescents and young adults in most Western countries. Mobile phone text messaging allows a proactive and cost-effective delivery of short messages at any time and place and allows the delivery of individualised information at times when young people typically drink alcohol. The main objective of the planned study is to test the efficacy of a combined web- and text messaging-based intervention to reduce problem drinking in young people with heterogeneous educational level. Methods/Design A two-arm cluster-randomised controlled trial with one follow-up assessment after 6 months will be conducted to test the efficacy of the intervention in comparison to assessment only. The fully-automated intervention program will provide an online feedback based on the social norms approach as well as individually tailored mobile phone text messages to stimulate (1) positive outcome expectations to drink within low-risk limits, (2) self-efficacy to resist alcohol and (3) planning processes to translate intentions to resist alcohol into action. Program participants will receive up to two weekly text messages over a time period of 3 months. Study participants will be 934 students from approximately 93 upper secondary and vocational schools in Switzerland. Main outcome criterion will be risky single-occasion drinking in the past 30 days preceding the follow-up assessment. Discussion This is the first study testing the efficacy of a combined web- and text messaging-based intervention to reduce problem drinking in young people. Given that this intervention approach proves to be effective, it could be easily implemented in various settings, and it could reach large numbers of young people in a cost-effective way. Trial registration Current Controlled Trials ISRCTN59944705.
Full-text available
The 'crisis in human resources' in the health sector has been described as one of the most pressing global health issues of our time. The World Health Organization (WHO) estimates that the world faces a global shortage of almost 4.3 million doctors, midwives, nurses, and other healthcare professionals. A global undersupply of these threatens the quality and sustainability of health systems worldwide. This undersupply is concurrent with globalization and the resulting liberalization of markets, which allow health workers to offer their services in countries other than those of their origin. The opportunities of health workers to seek employment abroad has led to a complex migration pattern, characterized by a flow of health professionals from low- to high-income countries. This global migration pattern has sparked a broad international debate about the consequences for health systems worldwide, including questions about sustainability, justice, and global social accountabilities. This article provides a review of this phenomenon and gives an overview of the current scope of health workforce migration patterns. It further focuses on the scientific discourse regarding health workforce migration and its effects on both high- and low-income countries in an interdependent world. The article also reviews the internal and external factors that fuel health worker migration and illustrates how health workforce migration is a classic global health issue of our time. Accordingly, it elaborates on the international community's approach to solving the workforce crisis, focusing in particular on the WHO Code of Practice, established in 2010.
Full-text available
Significant variation exists in published Aboriginal mortality and life expectancy (LE) estimates due to differing and evolving methodologies required to correct for inadequate recording of Aboriginality in death data, under-counting of Aboriginal people in population censuses, and unexplained growth in the Aboriginal population attributed to changes in the propensity of individuals to identify as Aboriginal at population censuses. The objective of this paper is to analyse variation in reported Australian Aboriginal mortality in terms of LE and infant mortality rates (IMR), compared with all Australians. Published data for Aboriginal LE and IMR were obtained and analysed for data quality and method of estimation. Trends in reported LE and IMR estimates were assessed and compared with those in the entire Australian population. LE estimates derived from different methodologies vary by as much as 7.2 years for the same comparison period. Indirect methods for estimating Aboriginal LE have produced LE estimates sensitive to small changes in underlying assumptions, some of which are subject to circular reasoning. Most indirect methods appear to under-estimate Aboriginal LE. Estimated LE gaps between Aboriginal people and the overall Australian population have varied between 11 and 20 years. Latest mortality estimates, based on linking census and death data, are likely to over-estimate Aboriginal LE. Temporal LE changes by each methodology indicate that Aboriginal LE has improved at rates similar to the Australian population overall. Consequently the gap in LE between Aboriginal people and the total Australian population appears to be unchanged since the early 1980s, and at the end of the first decade of the 21st century remains at least 11¿12 years. In contrast, focussing on the 1990¿2010 period Aboriginal IMR declined steeply over 2001¿08, from more than 12 to around 8 deaths per 1,000 live births, the same level as Australia overall in 1993¿95. The IMR gap between Aboriginal people and the total Australian population, while still unacceptable, has declined considerably, from over 8 before 2000 to around 4 per 1,000 live births by 2008. Regardless of estimation method used, mortality and LE gaps between Aboriginal and non-Aboriginal people are substantial, but remain difficult to estimate accurately.
Full-text available
In the decision support systems literature, most studies have concentrated on the direct effects of DSS use and design on decision outcomes and user performance in the workplace. Fewer DSS studies have integrated decision process variables, such as user beliefs and attitudes, in their models. In this paper, we examine the mediating role of decision process variables in the use of an online customer DSS. We do so through an experimental study of an alternative-based and an attribute-based DSS for product customization by online customers. Using cognitive fit and flow theories, we develop a theoretical model with four mediating decision process variables (perceived usefulness, perceived ease of use, perceived enjoyment, and perceived control) and two of their antecedents: interface design (attribute-based versus alternative-based) and task complexity (choice set size). Our results show that the impact of DSS interface design on behavioral intentions is fully mediated by perceived usefulness and perceived enjoyment, although not by perceived control. Specifically, we verify that users of an attribute-based DSS express higher perceived usefulness and perceived enjoyment than users of an alternative-based one. In addition, we find that task complexity has an interesting relationship with usefulness and enjoyment, both of which follow an inverted U-shaped curve as choice set size increases. Finally, we find that for users of the alternative-based DSS, perceived ease of use and perceived control decrease as task complexity increases. However, the attribute-based DSS alleviates that decline for both variables. Among other contributions, our results indicate the importance of including decision process variables when studying DSS as well as the complex effect of task complexity on those variables. Our study also provides some important guidelines for online companies that provide customer DSS on their websites, especially the danger of providing too many product choice options that can overwhelm customers and harm their shopping experience.
Objective: To test the efficacy of a combined web- and text messaging-based intervention to reduce problem drinking in young people compared to assessment only. Method: Two-arm, parallel-group, cluster-randomized controlled trial with assessments at baseline and 6-month follow up. The automated intervention included online feedback, based on the social norms approach, and individually tailored text messages addressing social norms, outcome expectations, motivation, self-efficacy, and planning processes, provided over 3 months. The main outcome criterion was the prevalence of risky single-occasion drinking (RSOD, defined as drinking at least 5 standard drinks on a single occasion in men and 4 in women) in the past 30 days. Irrespective of alcohol consumption, 1,355 students from 80 Swiss vocational and upper secondary school classes, all of whom owned a mobile phone, were invited to participate in the study. Of these, 1,041 (76.8%) students participated in the study. Results: Based on intention-to-treat analyses, RSOD prevalence decreased by 5.9% in the intervention group and increased by 2.6% in the control group, relative to that of baseline assessment (odds ratio [OR] = 0.62, 95% confidence interval [CI] = 0.44-0.87). No significant group differences were observed for the following secondary outcomes: RSOD frequency, quantity of alcohol consumed, estimated peak blood alcohol concentration, and overestimation of peer drinking norms. Conclusions: The intervention program reduced RSOD, which is a major indicator of problem drinking in young people, effectively. (PsycINFO Database Record
Effective and efficient behavioral interventions are important and of high interest today. Due to shortcomings of related approaches, we introduce MobileCoach ( as novel open source behavioral intervention platform. With its modular architecture, its rule-based engine that monitors behavioral states and triggers state transitions, we assume MobileCoach to lay a fruitful ground for evidence-based, scalable and low-cost behavioral interventions in various application domains. The code basis is made open source and thus, MobileCoach can be used and revised not only by interdisciplinary research teams but also by public bodies or business organizations without any legal constraints. Technical details of the platform are presented as well as preliminary empirical findings regarding the acceptance of one particular intervention in the public health context. Future work will integrate Internet of Things services that sense and process data streams in a way that MobileCoach interventions can be further tailored to the needs and characteristics of individual participants.
As the United States expends extraordinary efforts toward the digitization of its health-care system, and as policy makers across the globe look to information technology (IT) as a means of making health-care systems safer, more affordable, and more accessible, a rare and remarkable opportunity has emerged for the information systems research community to leverage its in-depth knowledge to both advance theory and influence practice and policy. Although health IT (HIT) has tremendous potential to improve quality and reduce costs in healthcare, significant challenges need to be overcome to fully realize this potential. In this commentary, we survey the landscape of existing studies on HIT to provide an overview of the current status of HIT research. We then identify three major areas that warrant further research: (1) HIT design, implementation, and meaningful use; (2) measurement and quantification of HIT payoff and impact; and (3) extending the traditional realm of HIT. We discuss specific research questions in each domain and suggest appropriate methods to approach them. We encourage information systems scholars to become active participants in the global discourse on health-care transformation through IT.