Misinformation detection in Luganda-English code-mixed social media text

Simple item page
dc.contributor.authorNabende, Peter
dc.contributor.authorKabiito, David
dc.contributor.authorBabirye, Claire
dc.contributor.authorTusiime, Hewitt
dc.contributor.authorNakatumba-Nabende, Joyce
dc.date.accessioned2022-12-29T13:47:24Z
dc.date.available2022-12-29T13:47:24Z
dc.date.issued2021
dc.description.abstractThe increasing occurrence, forms, and negative effects of misinformation on social media platforms has necessitated more misinformation detection tools. Currently, work is being done addressing COVID-19 misinformation however, there are no misinformation detection tools for any of the 40 distinct indigenous Ugandan languages. This paper addresses this gap by presenting basic language resources and a misinformation detection data set based on code-mixed Luganda- English messages sourced from the Facebook and Twitter social media platforms. Several machine learning methods are applied on the misinformation detection data set to develop classification models for detecting whether a code-mixed Luganda-English message contains misinformation or not. A 10-fold cross validation evaluation of the classification methods in an experimental misinformation detection task shows that a Discriminative Multinomial Na¨ıve Bayes (DMNB) method achieves the highest accuracy and F-measure of 78.19% and 77.90% respectively. Also, Support Vector Machine and Bagging ensemble classification models achieve comparable results. These results are promising since the machine learning models are based on n-gram features from only the misinformation detection data set.en_US
dc.identifier.citationNabende, P., Kabiito, D., Babirye, C., Tusiime, H., & Nakatumba-Nabende, J. (2021). Misinformation detection in Luganda-English code-mixed social media text. arXiv preprint arXiv:2104.00124.en_US
dc.identifier.urihttps://arxiv.org/abs/2104.00124
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/6746
dc.language.isoenen_US
dc.publisher. arXiv preprint arXiven_US
dc.titleMisinformation detection in Luganda-English code-mixed social media texten_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Misinformation detection in Luganda-English code-mixed social media.pdf
Size:
553.14 KB
Format:
Adobe Portable Document Format
Description:
Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Engineering and Technology