Leeuwen, Floris van (2021) The Relation Between COVID-19 Related Public Addresses and Topic Development in Dutch Tweets. Bachelor's Thesis, Artificial Intelligence.
|
Text
bAI_2021_VanLeeuwenFA.pdf Download (875kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (120kB) |
Abstract
Public addresses, given by governmental officials and televised on national senders, are an important tool for COVID-19 related communication between the government and the public. This study examines the relation between public addresses and topic discussion in Dutch tweets from February to December 2020. Topic modelling is performed using the SeaNMF model and data is stripped to limit the computational resources required. The number of resultant topics is decreased by means of manually combining topics into categories. Results reveal sufficient model quality for the identification of long term changes in topic discussion and a high level of variability in shorter time spans. Analysis of the change in topic discussion surrounding public addresses is limited by the variability in topic discussion, yielding inconclusive results. Alternative topic modelling methods are proposed to decrease bias in pre-processing and topic categorization, and the computational load.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Doornkamp, J. and Spenader, J.K. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 09 Jul 2021 11:52 |
| Last Modified: | 09 Jul 2021 11:52 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/25080 |
Actions (login required)
 |
View Item |