Kowalski, Radosław;
(2020)
Automated analysis of citizen feedback for inclusive public policies.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Kowalski_10106522_thesis.pdf Download (2MB) | Preview |
Abstract
Common sense is missing in large public institutions, from citizen perspective. It happens partly because of shortage of scalable tools to capture what citizens think. The study explores use of quantitative methods to turn free-text citizen comments into a resource for public policy. First, entirety of what matters to citizens was extracted from their comments. Relative importance of aspects of services experience was assessed, and it was shown how to validate insights from anonymous reviews against balanced survey data. It was found that the most comprehensive surveys of public opinion may omit variables in data collection compared to processing citizen comments. Decision-makers who rely on surveys may mis-measure policy effectiveness and formulate policies which do not solve problems or lead to negative side-effects. Second, a method for real-time performance measurement of public services using sparsely available citizen comments was developed. Prompt insights help reduce service delivery problems and help focus on currently pressing problems. Real-time performance measurement with daily updates is possible using citizen comments with over 90% of data missing. Another key finding was that public service performance is a local phenomenon. Quantitative methods may be used to cluster similar local contexts together to allow creation of more focused policies. A final element of the study focused on measuring whether individuals who use the same terms to express themselves may understand those terms differently or attach varying significance to them. The study explored ways to capture meaning, without an assumption that all citizens have fully standardised understanding of what their words mean. It was shown that meaning behind terms used in citizen feedback does drift. Allowing fluid meanings in quantitative analysis can improve reliability of insights and help bring about more inclusive policies. Distinct expressive styles of individuals or their language proficiency should find fair representation in quantitative summaries.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Automated analysis of citizen feedback for inclusive public policies |
| Event: | UCL (University College London) |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2020. Original content in this thesis is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities > Arts and Sciences (BASc) |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10106522 |
Archive Staff Only
 |
View Item |
