Chichirau, Malina (2021) Topic Modelling and Emotion Detection on Italian Tweets during the Early Covid-19 Pandemic. Bachelor's Thesis, Artificial Intelligence.
|
Text
AI_BA_2021_MALINA_CHICHIRAU.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (113kB) |
Abstract
This exploratory study attempts to identify the major topics of discussion in Italian tweets dated between February and July 2020, and the emotions associated with these topics. Topic Modelling was achieved using the SeaNMF algorithm, which exploits word contexts as a proxy for semantic similarities, while emotion detection was performed through lexicon look-up. Results revealed that the distribution of topics was imbalanced and found little evidence for a direct connection between changes in topic trends and the events selected as reference points. By examining the keywords of a given topic over the period of the study, a shift is observed in the focus of some topics. An emotion analysis of the tweets found similar patterns in terms of the intensities and fluctuations of emotions, regardless of the topics the tweets concerned. A comparison between Italian and Dutch tweets collected in the same period indicates that Italians were more preoccupied with internal affairs than their Dutch counterparts.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Spenader, J.K. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 12 Oct 2022 10:52 |
| Last Modified: | 12 Oct 2022 10:52 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/23887 |
Actions (login required)
 |
View Item |