"Do It by Myself" or Autonomy, Participation, and Assistive Devices and Technology Needs of Children and Youth With Disabilities: Text Mining Analysis of a National Survey in France.

Background: A 2019 French national online survey explored activity limitations and participation restrictions among children and youth with disabilities for which innovative solutions could help. Objective: The primary aim of this study was to use text mining analysis to complement previous human-led qualitative research and to uncover actionable additional knowledge related to difficult life situations that innovative solutions could help address and to compare the perspectives of children and youth with disabilities, relatives, and professionals. Methods: This study was part of Innovation for Participation, a cross-sectional online survey, including (1) closed questions about sociodemographic characteristics, (2) closed questions about life situations that induced difficulties, and (3) open questions to explore these situations in greater depth. This study used a text mining approach designed for French data to analyze answers to open-ended questions about difficulties and desired innovative solutions. The analysis process included (1) data cleansing; (2) computing and analyzing the word frequency in the answers and their cooccurrence; (3) clustering answers using K-means algorithms; (4) analyzing the cluster words to define a title for each one and identify answers that are consistent with cluster titles, thereafter defined as well-classified; and (5) evaluating internal consistency defined as the ratio of well-classified answers to the total number of answers. Results: In total, 1055 responses were received, and 962 (91.2%) were included, representing 2018 open-ended answers to questions about difficult life situations for which innovative solutions could be useful. Frequency analysis highlighted the desire for action and autonomy by children and youth with disabilities and their relatives ("do" in first position, closely followed by "by themselves" in third position). "Disability" was frequently used by professionals (third position) but did not figure among the 20 most frequently used terms by other respondents. Cooccurrences with "do" revealed a deep interest in "doing sports." Answers were gathered into 14 clusters, ranging in size from 9 to 681 answers; 5 underwent a second clustering step. Internal consistency ranged from 42% to 100%. Finally, 8 clusters were related to the difficulties linked to a desire for autonomy, and 4 highlighted difficulties related to actions within a group or community. Some clusters reinforced domains that emerged in the human-led analysis. Conclusions: Analysis of 2018 open-ended answers using a text mining approach designed for French data revealed that solutions are required to facilitate autonomy and the ability to "do it by myself (or themselves)," as well as integration into group and community life. Complementary to previous human-led analysis, the results reinforced the need for solutions to facilitate mobility, transport, and sports. They additionally highlighted differences in vocabulary used between the 3 respondent groups, suggesting that professionals may need to consider the language they use when communicating with individuals and relatives.