scholarly journals Using Natural Language Processing and Sentiment Analysis to Augment Traditional User-Centered Design: Development and Usability Study (Preprint)

2019 ◽  
Author(s):  
Curtis Lee Petersen ◽  
Ryan Halter ◽  
David Kotz ◽  
Lorie Loeb ◽  
Summer Cook ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Older Adults ◽  
Natural Language Processing ◽  
Sentiment Analysis ◽  
Design Process ◽  
Language Processing ◽  
User Centered Design ◽  
The Mean ◽  
User Friendly ◽  
User Centered

BACKGROUND Sarcopenia, defined as the age-associated loss of muscle mass and strength, can be effectively mitigated through resistance-based physical activity. With compliance at approximately 40% for home-based exercise prescriptions, implementing a remote sensing system would help patients and clinicians to better understand treatment progress and increase compliance. The inclusion of end users in the development of mobile apps for remote-sensing systems can ensure that they are both user friendly and facilitate compliance. With advancements in natural language processing (NLP), there is potential for these methods to be used with data collected through the user-centered design process. OBJECTIVE This study aims to develop a mobile app for a novel device through a user-centered design process with both older adults and clinicians while exploring whether data collected through this process can be used in NLP and sentiment analysis METHODS Through a user-centered design process, we conducted semistructured interviews during the development of a geriatric-friendly Bluetooth-connected resistance exercise band app. We interviewed patients and clinicians at weeks 0, 5, and 10 of the app development. Each semistructured interview consisted of heuristic evaluations, cognitive walkthroughs, and observations. We used the Bing sentiment library for a sentiment analysis of interview transcripts and then applied NLP-based latent Dirichlet allocation (LDA) topic modeling to identify differences and similarities in patient and clinician participant interviews. Sentiment was defined as the sum of positive and negative words (each word with a +1 or −1 value). To assess utility, we used quantitative assessment questionnaires—System Usability Scale (SUS) and Usefulness, Satisfaction, and Ease of use (USE). Finally, we used multivariate linear models—adjusting for age, sex, subject group (clinician vs patient), and development—to explore the association between sentiment analysis and SUS and USE outcomes. RESULTS The mean age of the 22 participants was 68 (SD 14) years, and 17 (77%) were female. The overall mean SUS and USE scores were 66.4 (SD 13.6) and 41.3 (SD 15.2), respectively. Both patients and clinicians provided valuable insights into the needs of older adults when designing and building an app. The mean positive-negative sentiment per sentence was 0.19 (SD 0.21) and 0.47 (SD 0.21) for patient and clinician interviews, respectively. We found a positive association with positive sentiment in an interview and SUS score (ß=1.38; 95% CI 0.37 to 2.39; <i>P</i>=.01). There was no significant association between sentiment and the USE score. The LDA analysis found no overlap between patients and clinicians in the 8 identified topics. CONCLUSIONS Involving patients and clinicians allowed us to design and build an app that is user friendly for older adults while supporting compliance. This is the first analysis using NLP and usability questionnaires in the quantification of user-centered design of technology for older adults.

scholarly journals Using Natural Language Processing and Sentiment Analysis to Augment Traditional User-Centered Design: Development and Usability Study

10.2196/16862 ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. e16862
Author(s):  
Curtis Lee Petersen ◽  
Ryan Halter ◽  
David Kotz ◽  
Lorie Loeb ◽  
Summer Cook ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Older Adults ◽  
Natural Language Processing ◽  
Sentiment Analysis ◽  
Design Process ◽  
Language Processing ◽  
User Centered Design ◽  
The Mean ◽  
User Friendly ◽  
User Centered

Background Sarcopenia, defined as the age-associated loss of muscle mass and strength, can be effectively mitigated through resistance-based physical activity. With compliance at approximately 40% for home-based exercise prescriptions, implementing a remote sensing system would help patients and clinicians to better understand treatment progress and increase compliance. The inclusion of end users in the development of mobile apps for remote-sensing systems can ensure that they are both user friendly and facilitate compliance. With advancements in natural language processing (NLP), there is potential for these methods to be used with data collected through the user-centered design process. Objective This study aims to develop a mobile app for a novel device through a user-centered design process with both older adults and clinicians while exploring whether data collected through this process can be used in NLP and sentiment analysis Methods Through a user-centered design process, we conducted semistructured interviews during the development of a geriatric-friendly Bluetooth-connected resistance exercise band app. We interviewed patients and clinicians at weeks 0, 5, and 10 of the app development. Each semistructured interview consisted of heuristic evaluations, cognitive walkthroughs, and observations. We used the Bing sentiment library for a sentiment analysis of interview transcripts and then applied NLP-based latent Dirichlet allocation (LDA) topic modeling to identify differences and similarities in patient and clinician participant interviews. Sentiment was defined as the sum of positive and negative words (each word with a +1 or −1 value). To assess utility, we used quantitative assessment questionnaires—System Usability Scale (SUS) and Usefulness, Satisfaction, and Ease of use (USE). Finally, we used multivariate linear models—adjusting for age, sex, subject group (clinician vs patient), and development—to explore the association between sentiment analysis and SUS and USE outcomes. Results The mean age of the 22 participants was 68 (SD 14) years, and 17 (77%) were female. The overall mean SUS and USE scores were 66.4 (SD 13.6) and 41.3 (SD 15.2), respectively. Both patients and clinicians provided valuable insights into the needs of older adults when designing and building an app. The mean positive-negative sentiment per sentence was 0.19 (SD 0.21) and 0.47 (SD 0.21) for patient and clinician interviews, respectively. We found a positive association with positive sentiment in an interview and SUS score (ß=1.38; 95% CI 0.37 to 2.39; P=.01). There was no significant association between sentiment and the USE score. The LDA analysis found no overlap between patients and clinicians in the 8 identified topics. Conclusions Involving patients and clinicians allowed us to design and build an app that is user friendly for older adults while supporting compliance. This is the first analysis using NLP and usability questionnaires in the quantification of user-centered design of technology for older adults.

scholarly journals Using Ensemble Models to Classify the Sentiment Expressed in Suicide Notes

2012 ◽  
Vol 5s1 ◽  
pp. BII.S8931 ◽  
Author(s):  
James A. McCart ◽  
Dezon K. Finch ◽  
Jay Jarman ◽  
Edward Hickling ◽  
Jason D. Lind ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Text Mining ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Regular Expression ◽  
Shared Task ◽  
Suicide Notes ◽  
The Mean ◽  
The U.S

In 2007, suicide was the tenth leading cause of death in the U.S. Given the significance of this problem, suicide was the focus of the 2011 Informatics for Integrating Biology and the Bedside (i2b2) Natural Language Processing (NLP) shared task competition (track two). Specifically, the challenge concentrated on sentiment analysis, predicting the presence or absence of 15 emotions (labels) simultaneously in a collection of suicide notes spanning over 70 years. Our team explored multiple approaches combining regular expression-based rules, statistical text mining (STM), and an approach that applies weights to text while accounting for multiple labels. Our best submission used an ensemble of both rules and STM models to achieve a micro-averaged F1 score of 0.5023, slightly above the mean from the 26 teams that competed (0.4875).

scholarly journals User-Centred Design of Multidisciplinary Spatial Data Platforms for Human-History Research

2021 ◽  
Vol 10 (7) ◽  
pp. 467
Author(s):  
Meeli Roose ◽  
Tua Nylén ◽  
Harri Tolvanen ◽  
Outi Vesakoski
Keyword(s):  
Design Process ◽  
Spatial Data ◽  
User Centered Design ◽  
Human Beings ◽  
Human History ◽  
Data Types ◽  
Building Process ◽  
Development Goals ◽  
User Friendly ◽  
User Centered

The role of open spatial data is growing in human-history research. Spatiality can be utilized to bring together and seamlessly examine data describing multiple aspects of human beings and their environment. Web-based spatial data platforms can create equal opportunities to view and access these data. In this paper, we aim at advancing the development of user-friendly spatial data platforms for multidisciplinary research. We conceptualize the building process of such a platform by systematically reviewing a diverse sample of historical spatial data platforms and by piloting a user-centered design process of a multidisciplinary spatial data platform. We outline (1) the expertise needed in organizing multidisciplinary spatial data sharing, (2) data types that platforms should be able to handle, (3) the most useful platform functionalities, and (4) the design process itself. We recommend that the initiative and subject expertise should come from the end-users, i.e., scholars of human history, and all key end-user types should be involved in the design process. We also highlight the importance of geographic expertise in the process, an important link between subject, spatial and technical viewpoints, for reaching a common understanding and common terminology. Based on the analyses, we identify key development goals for spatial data platforms, including full layer management functionalities. Moreover, we identify the main roles in the user-centered design process, main user types and suggest good practices including a multimodal design workshop.

scholarly journals Smartphone App to Self-Monitor Nausea During Pediatric Chemotherapy Treatment: User-Centered Design Process

10.2196/18564 ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. e18564
Author(s):  
Astrid Eliasen ◽  
Mikkel Kramme Abildtoft ◽  
Niels Steen Krogh ◽  
Catherine Rechnitzer ◽  
Jesper Sune Brok ◽  
...  
Keyword(s):  
Design Process ◽  
Response Rates ◽  
Nausea And Vomiting ◽  
Smartphone App ◽  
User Centered Design ◽  
Pediatric Cancer Patients ◽  
Patient Reported ◽  
User Friendly ◽  
Nausea Severity ◽  
User Centered

Background Nausea and vomiting are common and distressing side effects for children receiving chemotherapy. Limited evidence is available to guide antiemetic recommendations; therefore, prospective and reliable evaluation of antiemetic efficacy is needed. Smartphone apps can be used to effortlessly and precisely collect patient-reported outcomes in real time. Objective Our objective was to develop a smartphone app to monitor nausea and vomiting episodes in pediatric cancer patients aged 0 to 18 years and to test its usability and adherence to its use. Methods We used a user-centered design process and the evolutionary prototype model to develop and evaluate the app. Multidisciplinary group discussions and several rounds of patient feedback and modification were conducted. We translated the validated Pediatric Nausea Assessment Tool to assess nausea severity in children aged 4 to 18 years. The child’s own term for nausea was interactively incorporated in the nausea severity question, with response options expressed as 4 illustrative faces. Parent-reported outcomes were used for children aged 0 to 3 years. Reminders were sent using push notifications in order to ensure high response rates. Children aged 0 to 18 years who were undergoing chemotherapy were recruited from the Department of Pediatric Oncology at Copenhagen University Hospital Rigshospitalet to evaluate the app. Results The app’s most important function was to record nausea severity in children. After assistance from a researcher, children aged 4 to 18 years were able to report their symptoms in the app, and parents were able to report symptoms for their children aged 0 to 3 years. Children (n=20, aged 2.0-17.5 years) and their parents evaluated the app prospectively during a collective total of 60 chemotherapy cycles. They expressed that the app was user-friendly, intuitive, and that the time spent on data entry was fair. The response rates were on average 92%, 93%, and 80% for the day before, the first day of, and the next 3 days after chemotherapy, respectively. Researchers and clinicians were able to obtain an overview of the patient’s chemotherapy dates and responses through a secure and encrypted web-based administrative portal. Data could be downloaded for further analysis. Conclusions The user-friendly app could be used to facilitate future pediatric antiemetic trials and to refine antiemetic treatment during chemotherapy.

Design of an mHealth app to promote day-long physical activity in older adults with chronic pain: Phase 1 of the MORPH study (Preprint)

2020 ◽  
Author(s):  
Jason Fanning ◽  
Amber Brooks ◽  
Edward Ip ◽  
Barbara Nicklas ◽  
W. Jack Rejeski
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
Design Process ◽  
Underserved Populations ◽  
Activity Monitor ◽  
Perceived Usefulness ◽  
Technology Selection ◽  
Large Trial ◽  
User Centered Design ◽  
User Centered

BACKGROUND Participating in physical activity and minimizing time spent sitting is an effective strategy for managing pain in older adults. Theory-based mHealth tools are integral to effective day-long physical activity interventions, but it is vital that mHealth tools undergo an iterative development process alongside members of the target population to ensure their uptake and use. OBJECTIVE We subjected a preliminary social cognitive smartphone application (Companion App) designed to promote day-long movement to a user centered design process with the assistance of low-active older adults with chronic multisite pain. The Companion App integrates ecological momentary assessments of pain, Fitbit activity monitor data, and smart weight scale data to provide real-time feedback on the relationships between movement, sitting, and pain and to facilitate goal setting and achievement. METHODS We recruited participants (N=5; 71.8 5.54 years old) sequentially to participate in a three-phase iterative design study. First, each participant received a brief orientation to physical activity, was exposed to the application, and engaged in a Think Aloud protocol. Use and usability issues were noted by study staff. The participant then used the app for one week in their daily lives, and then returned to provide feedback. Issues were identified from participant feedback, discussed with the study team, and modified before the next participant began the study. RESULTS Participant interviews yielded feedback in areas related to technology selection and operation, app design/form, and intervention clarity. Regarding technology, the use of the Fitbit activity monitor revealed no issues, but there were barriers to the use of the Fitbit Aria 2 scale, including incompatibility with a widely used home internet router. Switching to a cellular enabled scale alleviated this issue. With regard to form, modifications were made to several key interface elements in response to participant feedback to aid in clarity. Finally, initial participant experiences revealed the need to separate the intervention orientation from the technology orientation to minimize informational load. CONCLUSIONS Our brief user-centered design process produced key changes in our intervention orientation, the form and function of the Companion App, and the technologies that support the app. These are vital elements that are likely to hamper the perceived usefulness and utility of the Companion App in the context of a large trial and eventual public use. We recommend the conduct of such a process any time mHealth is used in research or medicine to account for changing populations and preferences. Moreover, publication of lessons learned can help to establish a foundation of knowledge for designing apps for underserved populations such as older adults. CLINICALTRIAL ClinicalTrials.gov Identifier: NCT03377634

scholarly journals Smartphone App to Self-Monitor Nausea During Pediatric Chemotherapy Treatment: User-Centered Design Process (Preprint)

2020 ◽  
Author(s):  
Astrid Eliasen ◽  
Mikkel Kramme Abildtoft ◽  
Niels Steen Krogh ◽  
Catherine Rechnitzer ◽  
Jesper Sune Brok ◽  
...  
Keyword(s):  
Design Process ◽  
Response Rates ◽  
Nausea And Vomiting ◽  
Smartphone App ◽  
User Centered Design ◽  
Pediatric Cancer Patients ◽  
Patient Reported ◽  
User Friendly ◽  
Nausea Severity ◽  
User Centered

BACKGROUND Nausea and vomiting are common and distressing side effects for children receiving chemotherapy. Limited evidence is available to guide antiemetic recommendations; therefore, prospective and reliable evaluation of antiemetic efficacy is needed. Smartphone apps can be used to effortlessly and precisely collect patient-reported outcomes in real time. OBJECTIVE Our objective was to develop a smartphone app to monitor nausea and vomiting episodes in pediatric cancer patients aged 0 to 18 years and to test its usability and adherence to its use. METHODS We used a user-centered design process and the evolutionary prototype model to develop and evaluate the app. Multidisciplinary group discussions and several rounds of patient feedback and modification were conducted. We translated the validated Pediatric Nausea Assessment Tool to assess nausea severity in children aged 4 to 18 years. The child’s own term for nausea was interactively incorporated in the nausea severity question, with response options expressed as 4 illustrative faces. Parent-reported outcomes were used for children aged 0 to 3 years. Reminders were sent using push notifications in order to ensure high response rates. Children aged 0 to 18 years who were undergoing chemotherapy were recruited from the Department of Pediatric Oncology at Copenhagen University Hospital Rigshospitalet to evaluate the app. RESULTS The app’s most important function was to record nausea severity in children. After assistance from a researcher, children aged 4 to 18 years were able to report their symptoms in the app, and parents were able to report symptoms for their children aged 0 to 3 years. Children (n=20, aged 2.0-17.5 years) and their parents evaluated the app prospectively during a collective total of 60 chemotherapy cycles. They expressed that the app was user-friendly, intuitive, and that the time spent on data entry was fair. The response rates were on average 92%, 93%, and 80% for the day before, the first day of, and the next 3 days after chemotherapy, respectively. Researchers and clinicians were able to obtain an overview of the patient’s chemotherapy dates and responses through a secure and encrypted web-based administrative portal. Data could be downloaded for further analysis. CONCLUSIONS The user-friendly app could be used to facilitate future pediatric antiemetic trials and to refine antiemetic treatment during chemotherapy.

Ergonomics as Mediator within the Product Design Process

2000 ◽  
Vol 44 (8) ◽  
pp. 20-23 ◽  
Author(s):  
Ralph Bruder
Keyword(s):  
Product Development ◽  
Product Design ◽  
Design Process ◽  
User Centered Design ◽  
Human Centered Design ◽  
Mediating Role ◽  
Product Design Process ◽  
User Friendly ◽  
User Centered

As a consequence of an increasing complexity of products using procedures a human-centered-design process is more and more important. This thesis can be based on the success of user friendly products on market but also by looking at new regulations concerning human-centered design (e.g. pr EN-ISO 13407). Within an user-centered design process there is a need for a continuos balancing between interests of users and producers. This mediating role can be fulfilled by persons with an ergonomic background. The potentiality of ergonomic for the initialization, accompaniment and evaluation of an user-centered design process was demonstrated within the product development of a new electronic pipette.

Sign in / Sign up

Export Citation Format

Share Document