Abstract
In the age of freedom of speech, users of the various social media platforms post millions of unverified messages, resulting in misinformation. Despite these platforms’ set policies against misinformation, there is an alarming rise in misleading news dissemination. On political matters, misinformation online can result in defamation and in extreme cases, violence offline. Misinformation classification involves classifying text as fake or fact. Most of the existing studies address misinformation classification for posts in a single language only. Among most bilingual or multilingual social media users, code-switching such as Swahili-English, is common practice. This poses a threat to code-switching being used to spread misinformation. There is need for more research in low-resource languages such as Swahili, especially their use to spread misinformation. This study curated the PolitiKweli (dataset: https://github.com/jayneamol/kweli) dataset, a Swahili-English code-switched misinformation classification dataset, containing 6,345 Swahili-English code-switched texts, 22,954 English texts and 211 Swahili texts. The texts are labeled as fake, fact or neutral as compared to fact-checked Twitter dataset also created as part of this study. The paper discusses the dataset curation process including data collection, data processing and data annotation. It also highlights the challenges during the annotation. The study develops a benchmark classification model based on pretrained language model BERT that achieves an F-score of 0.62. The results of the experiment show promising results on the usefulness of the Swahili-English code-switched misinformation classification models. When applied, the classification model can be able to flag instances of misinformation on social media platforms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The aspect of slag is not discussed in this study and left for future work.
- 2.
As part of the larger project, we plan to expand the dataset to include code-switched texts for other local languages.
References
Adelani, D.I., et al.: Masakhaner: named entity recognition for African languages. Trans. Assoc. Comput. Linguist. 9, 1116–1131 (2021)
Ahmed, W., Bath, P.A., Demartini, G.: Using twitter as a data source: an overview of ethical, legal, and methodological challenges. Ethics Online Res. 2, 79–107 (2017)
Altay, S., Berriche, M., Heuer, H., Farkas, J., Rathje, S.: A survey of expert views on misinformation: definitions, determinants, solutions, and future of the field. Harvard Kennedy School Misinformation Rev. 4(4), 1–34 (2023)
Amer, E., Kwak, K.S., El-Sappagh, S.: Context-based fake news detection model relying on deep learning models. Electronics 11(8), 1255 (2022)
Balaton-Chrimes, S.: Who are Kenya’s 42 (+) tribes? The census and the political utility of magical uncertainty. J. Eastern Afr. Stud. 15(1), 43–62 (2021)
Barnett, R., et al.: The lides coding manual: a document for preparing and analyzing language interaction data version 1.1–july 1999. Int. J. Bilingualism 4(2), 131–271 (2000)
Candra, L.K., Qodriani, L.U.: An analysis of code switching in leila s. chudori’s for nadira. Teknosastik 16(1), 9–14 (2019)
Casero-Ripollés, A.: Influencers in the political conversation on twitter: identifying digital authority with big data. Sustainability 13(5), 2851 (2021)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. ar**v preprint ar**v:1810.04805 (2018)
Guzmán, G.A., Ricard, J., Serigos, J., Bullock, B.E., Toribio, A.J.: Metrics for modeling code-switching across corpora. In: Interspeech, pp. 67–71 (2017)
Hoffmann, C.: In introduction to bilingualism, ed. Logman, Newyork (1991)
Jerit, J., Zhao, Y.: Political misinformation. Annu. Rev. Polit. Sci. 23, 77–94 (2020)
Köchler, H.: Idea and politics of communication in the global age. In: Digital Transformation in Journalism and News Media: Media Management, Media Convergence and Globalization, pp. 7–15 (2017)
Kresse, K., Vierke, C.: Swahili language and literature as resources for Indian ocean studies. Hist. Compass 20(7), e12725 (2022)
Landis, J.R., Koch, G.G.: An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers. Biometrics 363–374 (1977)
Magueresse, A., Carles, V., Heetderks, E.: Low-resource languages: a review of past work and future challenges. ar**v preprint ar**v:2006.07264 (2020)
Martin, G., Mswahili, M.E., Jeong, Y.S., Woo, J.: Swahbert: language model of swahili. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 303–313 (2022)
Michail, D., Kanakaris, N., Varlamis, I.: Detection of fake news campaigns using graph convolutional networks. Int. J. Inf. Manag. Data Insights 2(2), 100104 (2022)
Mohammad, S.: A practical guide to sentiment annotation: challenges and solutions. In: Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pp. 174–179 (2016)
Moons, F., Vandervieren, E.: Measuring agreement among several raters classifying subjects into one-or-more (hierarchical) nominal categories. a generalisation of fleiss’ kappa. ar**v preprint ar**v:2303.12502 (2023)
Mozilla: New research: In Kenya, disinformation campaigns seek to discredit pandora papers (2021). https://foundation.mozilla.org/en/blog/new-research-in-kenya-disinformation-campaigns-seek-to-discredit-pandora-papers/
Muhammad, S.H., et al.: Afrisenti: a twitter sentiment analysis benchmark for African languages. ar**v preprint ar**v:2302.08956 (2023)
Mukhongo, L.L.: Participatory media cultures: virality, humour, and online political contestations in Kenya. Afr. Spectr. 55(2), 148–169 (2020)
Nabende, P., Kabiito, D., Babirye, C., Tusiime, H., Nakatumba-Nabende, J.: Misinformation detection in luganda-english code-mixed social media text. ar**v preprint ar**v:2104.00124 (2021)
Ogola, G.: # whatwouldmagufulido? Kenya’s digital “practices” and “individuation” as a (non) political act. J. East. Afr. Stud. 13(1), 124–139 (2019)
Okoth, G.B.W.: How Kenyans on twitter use visuals as a form of political protest. J. Kommunikation. Medien 1–27 (2020)
Ombui, E., Muchemi, L., Wagacha, P.: Hate speech detection in code-switched text messages. In: 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), pp. 1–6. IEEE (2019)
Paullada, A., Raji, I.D., Bender, E.M., Denton, E., Hanna, A.: Data and its (dis) contents: a survey of dataset development and use in machine learning research. Patterns 2(11) (2021)
X developer platform documentation (2023). https://developer.twitter.com/en/docs
Qureshi, M.A., et al.: A novel auto-annotation technique for aspect level sentiment analysis. Comput. Mater. Contin. 70(3), 4987–5004 (2022)
Rajput, K., Kapoor, R., Rai, K., Kaur, P.: Hate me not: detecting hate inducing memes in code switched languages. ar**v preprint ar**v:2204.11356 (2022)
Randolph, J.J.: Free-marginal multirater kappa (multirater k [free]): an alternative to fleiss’ fixed-marginal multirater kappa. Online submission (2005)
Rijhwani, S., Sequiera, R., Choudhury, M., Bali, K., Maddila, C.S.: Estimating code-switching on twitter with a novel generalized word-level language detection technique. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1971–1982 (2017)
Sakketou, F., Plepi, J., Cervero, R., Geiss, H.J., Rosso, P., Flek, L.: Factoid: a new dataset for identifying misinformation spreaders and political bias. ar**v preprint ar**v:2205.06181 (2022)
Shahi, G.K., Dirkson, A., Majchrzak, T.A.: An exploratory study of covid-19 misinformation on twitter. Online Soc. Netw. Media 22, 100104 (2021)
Shu, K., Mahudeswaran, D., Wang, S., Lee, D., Liu, H.: Fakenewsnet: a data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big Data 8(3), 171–188 (2020)
Sitaram, S., Chandu, K.R., Rallabandi, S.K., Black, A.W.: A survey of code-switched speech and language processing. ar**v preprint ar**v:1904.00784 (2019)
Wanjawa, B., Wanzare, L., Indede, F., McOnyango, O., Ombui, E., Muchemi, L.: Kencorpus: a Kenyan language corpus of swahili, dholuo and luhya for natural language processing tasks. ar**v preprint ar**v:2208.12081 (2022)
X: How we address misinformation on x (2023). https://help.twitter.com/en/resources/addressing-misleading-info
Zampieri, M., et al.: Semeval-2020 task 12: multilingual offensive language identification in social media (offenseval 2020). ar**v preprint ar**v:2006.07235 (2020)
Acknowledgements
We acknowledge the contributions of Shamsuddeen Hassan who assisted with the data collection from Twitter, Martin Okech, Edwin Onkoba and the Maseno University School of Computing and Informatics staff and students. We thank Mary Gitaari, Ezekiel Maina, Nelson Odhiambo, Stephen Otieno, Monicah Odipo, Harrison Kioko, Elphas Otieno, Bowa Marita, Peter Gathuita and Samwel Okonda for their contribution in data annotation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Amol, C., Wanzare, L., Obuhuma, J. (2024). PolitiKweli: A Swahili-English Code-Switched Twitter Political Misinformation Classification Dataset. In: Chakravarthi, B.R., et al. Speech and Language Technologies for Low-Resource Languages. SPELLL 2023. Communications in Computer and Information Science, vol 2046. Springer, Cham. https://doi.org/10.1007/978-3-031-58495-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-58495-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-58494-7
Online ISBN: 978-3-031-58495-4
eBook Packages: Computer ScienceComputer Science (R0)