scholarly journals Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage

10.2196/17065 ◽  
2020 ◽  
Vol 4 (11) ◽  
pp. e17065
Author(s):  
Gilly Dosovitsky ◽  
Blanca S Pineda ◽  
Nicholas C Jacobson ◽  
Cyrus Chang ◽  
Milagros Escoredo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Health Interventions ◽  
Descriptive Statistics ◽  
User Engagement ◽  
Usage Pattern ◽  
Limited Information ◽  
Usage Patterns ◽  
Large Heterogeneity ◽  
Flow Through ◽  
Participant Flow

Background Chatbots could be a scalable solution that provides an interactive means of engaging users in behavioral health interventions driven by artificial intelligence. Although some chatbots have shown promising early efficacy results, there is limited information about how people use these chatbots. Understanding the usage patterns of chatbots for depression represents a crucial step toward improving chatbot design and providing information about the strengths and limitations of the chatbots. Objective This study aims to understand how users engage and are redirected through a chatbot for depression (Tess) to provide design recommendations. Methods Interactions of 354 users with the Tess depression modules were analyzed to understand chatbot usage across and within modules. Descriptive statistics were used to analyze participant flow through each depression module, including characters per message, completion rate, and time spent per module. Slide plots were also used to analyze the flow across and within modules. Results Users sent a total of 6220 messages, with a total of 86,298 characters, and, on average, they engaged with Tess depression modules for 46 days. There was large heterogeneity in user engagement across different modules, which appeared to be affected by the length, complexity, content, and style of questions within the modules and the routing between modules. Conclusions Overall, participants engaged with Tess; however, there was a heterogeneous usage pattern because of varying module designs. Major implications for future chatbot design and evaluation are discussed in the paper.

scholarly journals Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage (Preprint)

2019 ◽  
Author(s):  
Gilly Dosovitsky ◽  
Blanca S Pineda ◽  
Nicholas C Jacobson ◽  
Cyrus Chang ◽  
Eduardo L Bunge
Keyword(s):  
Artificial Intelligence ◽  
Health Interventions ◽  
Descriptive Statistics ◽  
User Engagement ◽  
Usage Pattern ◽  
Limited Information ◽  
Usage Patterns ◽  
Large Heterogeneity ◽  
Flow Through ◽  
Participant Flow

BACKGROUND Chatbots could be a scalable solution that provides an interactive means of engaging users in behavioral health interventions driven by artificial intelligence. Although some chatbots have shown promising early efficacy results, there is limited information about how people use these chatbots. Understanding the usage patterns of chatbots for depression represents a crucial step toward improving chatbot design and providing information about the strengths and limitations of the chatbots. OBJECTIVE This study aims to understand how users engage and are redirected through a chatbot for depression (Tess) to provide design recommendations. METHODS Interactions of 354 users with the Tess depression modules were analyzed to understand chatbot usage across and within modules. Descriptive statistics were used to analyze participant flow through each depression module, including characters per message, completion rate, and time spent per module. Slide plots were also used to analyze the flow across and within modules. RESULTS Users sent a total of 6220 messages, with a total of 86,298 characters, and, on average, they engaged with Tess depression modules for 46 days. There was large heterogeneity in user engagement across different modules, which appeared to be affected by the length, complexity, content, and style of questions within the modules and the routing between modules. CONCLUSIONS Overall, participants engaged with Tess; however, there was a heterogeneous usage pattern because of varying module designs. Major implications for future chatbot design and evaluation are discussed in the paper.

Smartphone usage pattern while walking: A survey on 441 young users in Korea

2020 ◽  
Vol 64 (1) ◽  
pp. 1728-1731
Author(s):  
Yujin Kwon ◽  
Seobin Choi ◽  
Eunjee Kim ◽  
Hyorim Kim ◽  
Misol Kim ◽  
...  
Keyword(s):  
Text Messaging ◽  
Traffic Accidents ◽  
Usage Pattern ◽  
Limited Information ◽  
Near Misses ◽  
Usage Rate ◽  
Phone Calls ◽  
Frequency Of Use ◽  
History Of

Smartphone usage rate has been increased, and so has on the streets while walking. Concerns for traffic accidents associated with the use have been growing, but there has been limited information regarding smartphone usage pattern while walking. A survey was conducted to explore the usage pattern in terms of frequency of use while walking, and history of accidents, and apps used while walking. Of 441 students, 95.9% used smartphones ‘sometimes’ or more often while walking. 91.8% and 54.6% of 423 used their phones while waiting for a signal and while crossing the crosswalk, respectively. 57.9% experienced accidents or near misses when using smartphones while walking. Text messaging (87.7%) was the most frequently used app while walking, followed by music and phone calls. The findings indicate that using smartphones while walking is a common behavior of young users, and suggest habitual users on the streets were in greater risks for accidents.

scholarly journals Prediction Models for Public Health Containment Measures on COVID-19 Using Artificial Intelligence and Machine Learning: A Systematic Review

2021 ◽  
Vol 18 (9) ◽  
pp. 4499
Author(s):  
Anil Babu Payedimarri ◽  
Diego Concina ◽  
Luigi Portinale ◽  
Massimo Canonico ◽  
Deborah Seys ◽  
...  
Keyword(s):  
Public Health ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Systematic Review ◽  
Public Transportation ◽  
Prediction Models ◽  
Positive Impact ◽  
Health Interventions ◽  
Public Health Interventions ◽  
Commercial Activities

Artificial Intelligence (AI) and Machine Learning (ML) have expanded their utilization in different fields of medicine. During the SARS-CoV-2 outbreak, AI and ML were also applied for the evaluation and/or implementation of public health interventions aimed to flatten the epidemiological curve. This systematic review aims to evaluate the effectiveness of the use of AI and ML when applied to public health interventions to contain the spread of SARS-CoV-2. Our findings showed that quarantine should be the best strategy for containing COVID-19. Nationwide lockdown also showed positive impact, whereas social distancing should be considered to be effective only in combination with other interventions including the closure of schools and commercial activities and the limitation of public transportation. Our findings also showed that all the interventions should be initiated early in the pandemic and continued for a sustained period. Despite the study limitation, we concluded that AI and ML could be of help for policy makers to define the strategies for containing the COVID-19 pandemic.

An entropy concentration theorem: applications in artificial intelligence and descriptive statistics

1990 ◽  
Vol 27 (2) ◽  
pp. 303-313 ◽  
Author(s):  
Claudine Robert
Keyword(s):  
Artificial Intelligence ◽  
Maximum Entropy ◽  
Large Deviation ◽  
Maximum Entropy Principle ◽  
Statistical Modelling ◽  
Linear Constraints ◽  
Descriptive Statistics ◽  
Entropy Principle ◽  
Maximum Entropy Distribution ◽  
Mathematical Justification

The maximum entropy principle is used to model uncertainty by a maximum entropy distribution, subject to some appropriate linear constraints. We give an entropy concentration theorem (whose demonstration is based on large deviation techniques) which is a mathematical justification of this statistical modelling principle. Then we indicate how it can be used in artificial intelligence, and how relevant prior knowledge is provided by some classical descriptive statistical methods. It appears furthermore that the maximum entropy principle yields to a natural binding between descriptive methods and some statistical structures.

scholarly journals Recovery of new-onset kidney disease in COVID-19 patients discharged from hospital

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Nan-Hui Zhang ◽  
Yi-Chun Cheng ◽  
Ran Luo ◽  
Chun-Xiu Zhang ◽  
Shu-Wang Ge ◽  
...  
Keyword(s):  
Kidney Disease ◽  
Kidney Diseases ◽  
Descriptive Statistics ◽  
Limited Information ◽  
High Discharge ◽  
Discharged Patients ◽  
Recovery Group ◽  
Abundant Data ◽  
New Onset

Abstract Background Coronavirus disease 2019 (COVID-19) has emerged as a major global health threat with a great number of deaths worldwide. Despite abundant data on that many COVID-19 patients also displayed kidney disease, there is limited information available about the recovery of kidney disease after discharge. Methods Retrospective and prospective cohort study to patients with new-onset kidney disease during the COVID-19 hospitalization, admitted between January 28 to February 26, 2020. The median follow-up was 4 months after discharge. The follow-up patients were divided into the recovery group and non-recovery group. Descriptive statistics and between-groups comparison were used. Results In total, 143 discharged patients with new-onset kidney disease during the COVID-19 hospitalization were included. Patients had a median age was 64 (IQR, 51–70) years, and 59.4% of patients were men. During 4-months median follow-up, 91% (130 of 143) patients recovered from kidney disease, and 9% (13 of 143) patients haven’t recovered. The median age of patients in the non-recovery group was 72 years, which was significantly higher than the median age of 62 years in the recovery group. Discharge serum creatinine was significantly higher in the non-recovery group than in the recovery group. Conclusions Most of the new-onset kidney diseases during hospitalization of COVID-19 patients recovered 4 months after discharge. We recommend that COVID-19 patients with new-onset kidney disease be followed after discharge to assess kidney recovery, especially elderly patients or patients with high discharge creatinine.

Investigating when, which and why users stop using an e- and m-health intervention to promote an active lifestyle: A focus on HAPA-based psychosocial determinants. (Preprint)

2021 ◽  
Author(s):  
Helene Schroé ◽  
Geert Crombez ◽  
Ilse De Bourdeaudhuij ◽  
Delfien Van Dyck
Keyword(s):  
Behaviour Change ◽  
Demographic Variables ◽  
Health Intervention ◽  
Health Interventions ◽  
Descriptive Statistics ◽  
Drop Out ◽  
Attrition Rates ◽  
Technical Problems ◽  
Psychosocial Determinants ◽  
In The Beginning

BACKGROUND E- and m-health interventions have gained momentum to change health behaviours such as physical activity (PA) and sedentary behaviour (SB). Although these interventions show promising results in terms of behaviour change, they still suffer from high attrition rates, resulting in a lower potential and reachability. In order to reduce attrition rates in the future, there is a need to investigate the reasons why individuals stop using e- and m-health interventions. Certain demographic variables have already been related to attrition in e- and m-health interventions, however the role of psychosocial determinants of behaviour change as predictors of attrition has not yet been fully explored. OBJECTIVE The aim of this study was to examine when, which and why users stop using an e- and m-health intervention. In particular, we aimed to investigate whether psychosocial determinants of behaviour change were predictors for attrition. METHODS The sample consisted of 473 healthy adults who participated in the e-and m-health intervention ‘MyPlan 2.0’ to promote PA or reduce SB. The intervention was developed using the Health Action Process Approach (HAPA) model, which describes psychosocial determinants that guide individuals in changing their behaviour. If participants stopped with the intervention, a questionnaire with eight question concerning attrition was sent by email. To analyze when users stopped using the intervention, descriptive statistics were used per part of the intervention (including pre- and post-test measurements, and 5 website sessions). To analyze which users stopped using the intervention, demographic variables, behavioural status and HAPA-based psychosocial determinants at pre-test measurement were investigated as potential predictors of attrition using logistic regression models. To analyze why users stopped using the intervention, descriptive statistics of answers to the attrition related questionnaire were used. RESULTS The study demonstrated that 227 of the 473 (47,9%) participants stopped using the intervention, and drop out occurred mainly in the beginning of the intervention. The results seem to indicate that gender and participants’ scores on the psychosocial determinants action planning, coping planning and self-monitoring were predictors of first session, third session and/or whole intervention completion. The most endorsed reasons to stop with the intervention were the time-consuming nature of questionnaires, not having time, dissatisfaction with the content of the intervention, technical problems, already meeting the guidelines for PA/SB, and to a lesser extent the experience of medical/emotional problems. CONCLUSIONS This study provides some directions for future studies. To decrease attrition, it will be important to personalise interventions on different levels, questionnaires (either for research purposes or tailoring) should be kept to a minimum especially in the beginning of interventions by for example using objective monitoring devices, and technical aspects of e-and m-health interventions should be thoroughly tested in advance.

scholarly journals Mobile Apps as Audience-Centered Health Communication Platforms (Preprint)

2020 ◽  
Author(s):  
Michael Mackert ◽  
Dorothy Mandell ◽  
Erin Donovan ◽  
Lorraine Walker ◽  
Mike Garcia ◽  
...  
Keyword(s):  
Health Communication ◽  
Mobile Phones ◽  
Mobile Apps ◽  
Mobile App ◽  
Health Interventions ◽  
User Engagement ◽  
Health Campaigns ◽  
Efficient Tool ◽  
Limited Budget ◽  
Expectant Fathers

UNSTRUCTURED Health communication campaigns often suffer from the shortcomings of a limited budget and limited reach, resulting in a limited impact. This paper suggests a shift to audience-centered communication platforms – particularly apps on mobile phones. By using a common platform, multiple interventions and campaigns can combine resources and increase user engagement, resulting in a larger impact on health behavior. Given the widespread use of mobile phones, mobile apps can be an effective and efficient tool to provide health interventions. One such platform is Father’s Playbook, a mobile app designed for men to be more involved during their partner’s pregnancy. Health campaigns and interventions looking to reach expectant fathers can use Father’s Playbook as a vehicle for their messages.

Non-Player Characters and Artificial Intelligence

Gamification ◽  
2015 ◽  
pp. 488-514
Author(s):  
Gonçalo Pereira ◽  
António Brisson ◽  
João Dias ◽  
André Carvalho ◽  
Joana Dimas ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Computational Models ◽  
Research Topic ◽  
Interactive Systems ◽  
Learning Activity ◽  
Willingness To Accept ◽  
User Engagement ◽  
Efficient Communication ◽  
Game Environment ◽  
Computational Systems

Serious Games rely on interactive systems to provide an efficient communication medium between the tutor and the user. Designing and implementing such medium is a multi-disciplinary task that aims at an environment that engages the user in a learning activity. User engagement is significantly related to the users' sense of immersion or his willingness to accept the reality proposed by a game environment. This is a very relevant research topic for Artificial Intelligence (AI), since it requires computational systems to generate believable behaviors that can promote the users' willingness to enter and engage in the game environment. In order to do this, AI research has been relying on social sciences, in particular psychology and sociology models, to ground the creation of computational models for non-player characters that behave according to the users' expectations. In this chapter, the authors present some of the most relevant NPC research contributions following this approach.

Smartphone Data Protection Using Mobile Usage Pattern Matching

2011 ◽  
pp. 23-39
Author(s):  
Wen-Chen Hu ◽  
Naima Kaabouch ◽  
S. Hossein Mousavinezhad ◽  
Hung-Jen Yang
Keyword(s):  
Pattern Matching ◽  
Data Protection ◽  
Finite Automata ◽  
String Matching ◽  
Handheld Devices ◽  
Approximate String Matching ◽  
Usage Pattern ◽  
Usage Patterns ◽  
Novel Approaches

Handheld devices like smartphones must include rigorous and convenient handheld data protection in case the devices are lost or stolen. This research proposes a set of novel approaches to protecting handheld data by using mobile usage pattern matching, which compares the current handheld usage pattern to the stored usage patterns. If they are drastic different, a security action such as requiring a password entry is activated. Various algorithms of pattern matching can be used in this research. Two of them are discussed in this chapter: (i) approximate usage string matching and (ii) usage finite automata. The first method uses approximate string matching to check device usage and the second method converts the usage tree into a deterministic finite automaton (DFA). Experimental results show this method is effective and convenient for handheld data protection, but the accuracy may need to be improved.

The Labour Market Under Consideration of the Technical Changes

2021 ◽  
Vol 11 (1) ◽  
pp. 1-14
Author(s):  
Tom Sander ◽  
Phoey Lee Teh ◽  
Anabela Mesquita
Keyword(s):  
Artificial Intelligence ◽  
Labour Market ◽  
Human Activities ◽  
T Test ◽  
Descriptive Statistics ◽  
Spearman Correlation ◽  
Daily Lives ◽  
Men And Women

Implementing artificial intelligence (AI) into our daily lives has created new occupations and businesses. It has changed human activities and affected individual's behaviour, influencing our decisions. This study explores the opinions of individuals about the influences of implementing AI into the labour market, especially the issue of how AI could affect human employment. There are 144 participants who responded to this survey, and the data was analysed using descriptive statistics, the t-test to identify significant differences between men and women, as well as the Spearman correlation. The results provide interesting insights and only relevant statistics and significant results are presented.

Sign in / Sign up

Export Citation Format

Share Document