Analyzing Multi-Lingual Discussions of the Standard Gauge Railway Project in Kenya Using Natural Language Processing and Social Media Analysis

Abstract

Development of infrastructure in Kenya, especially transportation infrastructure, began receiving partial financing investments by the Chinese government in 2014 as part of China’s broader Belt and Road Initiative (BRI). While there has been significant journalistic, academic, and governmental exploration of China’s new global investment strategies, less analysis has focused on local reactions to these new development relationships. In this study, we gather publicly available social media data centered around a large Kenya-Chinese infrastructure project, the Mombasa-Nairobi Standard Gauge Railway (SGR). We used automated natural language processing strategies as well as manual analysis of social media data from Twitter to understand discussion topics, attitudes, and sentiments of Kenyans toward domestic Kenya-China infrastructure projects. We advance research on multilingual digital expression through the analysis of social media data in both English and Swahili.

Keywords

Kenya Belt and Road Initiative (BRI)infrastructure twitter natural language processing topic model sentiment analysis

Get full access to this article

View all access options for this article.

References

Allcott

Braghieri

Eichmeyer

, et al. (2020) The welfare effects of social media. American Economic Review 110(3): 629–676.

Amin

Hossain

Akther

, et al. (2019) Bengali VADER: a sentiment analysis approach using modified VADER. In: 2nd international conference on electrical, computer and communication engineering (ECCE). DOI: 10.1109/ECACE.2019.8679144.

Beeson

(2018) Geoeconomics with Chinese characteristics: the BRI and China’s evolving grand strategy. Economic and Political Studies 6(3): 240–256.

Blei

Lafferty

(2007) A correlated topic model of science. The Annals of Applied Statistics 1(1): 17–35.

Blei

Jordan

(2003) Latent Dirichlet allocation. Journal of Machine Learning Research 3(4/5): 993–1022.

Business Daily Africa (2011) Will Chinese firms deliver as they gain influence in Kenya’s economic scene? 8 May. Available at: https://www.businessdailyafrica.com/bd/economy/will-chinese-firms-deliver-as-they-gain-influence-in-kenya-s-economic-scene–1983738

Cavnar

Trenkle

(1994) N-gram-based text categorization. In: Proceedings of SDAIR-94, 3rd annual symposium on document analysis and information retrieval, pp.161–175. Available at: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.53.9367 (accessed 22 February 2021).

Cheeseman

Fisher

Hassan

, et al. (2020) Social media disruption: Nigeria’s WhatsApp politics. Journal of Democracy 31(3): 145–159.

Cuenca

(2020) Kenyan Court of Appeal finds SGR construction contract illegal. International Railway Journal, 26 January. Available at: https://www.railjournal.com/africa/kenyan-court-of-appeal-finds-sgr-construction-contract-illegal/ (accessed 8 April 2021).

10.

D’Arcy

Cornell

(2016) Devolution and corruption in Kenya: everyone’s turn to eat? African Affairs 115(459): 246–273.

11.

Deibert

(2019) The road to digital unfreedom: three painful truths about social media. Journal of Democracy 30(1): 25–39.

12.

Dwyer

Molony

(eds) (2019) Social Media and Politics in Africa: Democracy, Censorship and Security. London: Zed Books Ltd.

13.

First Draft News (2019) Newsgathering and monitoring on the social web. Formerly first draft, now the information futures lab at Brown University, October 2019. Available at: https://firstdraftnews.org/long-form-article/newsgathering-and-monitoring-on-the-social-web/

14.

Githaiga

Bing

(2019) Belt and road initiative in Africa: the impact of standard gauge railway in Kenya. China Report 55(3): 219–240.

15.

Githiora

(2008) Kenya: language and the search for a coherent national identity. In: Simpson

(ed.) Language and National Identity in Africa, pp. 235–252. Oxford: Oxford University Press.

16.

Greenwood

Perrin

Duggan

(2016) Social Media Update. Washington, DC: Pew Research Center.

17.

Grimmer

Stewart

(2013) Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political Analysis 21(3): 267–297.

18.

Grün

Hornik

(2011) Topicmodels: an R package for fitting topic models. Journal of Statistical Software 40(13): 1–30.

19.

Hillman

(2018) How big is China’s belt and road? Center for Strategic & International Studies. Available at: https://www.csis.org/analysis/how-big-chinas-belt-and-road

20.

Hong

Nadler

(2011) Does the early bird move the polls? The use of the social media tool “Twitter” by U.S. politicians and its impact on public opinion. In: Proceedings of the 12th annual international digital government research conference: digital government innovation in challenging times, pp.182–186. DOI: 10.1145/2037556.2037583.

21.

Hornik

Mair

Rauch

, et al. (2013) The textcat package for n-gram based text categorization in R. Journal of Statistical Software 52(6): 1–17.

22.

Wang

(2020) Understanding the removal of precise geotagging in tweets. Nature Human Behaviour 4(12): 1219–1221.

23.

Huang

(2016) Understanding China’s belt & road initiative: motivation, framework and assessment. China Economic Review 40: 314–321.

24.

Hutto

Gilbert

(2014) VADER: a parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings of the eighth international AAAI conference on weblogs and social media, pp.216–225. Available at: https://ojs.aaai.org/index.php/ICWSM/article/view/14550

25.

Keßler

McKenzie

(2018) A geoprivacy manifesto. Transactions in GIS 22(1): 3–19.

26.

Kenya Law (2014) Petition 58 of 2014. Available at: http://kenyalaw.org/caselaw/cases/view/103808/

27.

Khan

Swar

Lee

(2014) Social media risks and benefits: a public sector perspective. Social Science Computer Review 32(5): 606–627.

28.

Kimari

Ernstson

(2020) Imperial remains and imperial invitations: centering race within the contemporary large-scale infrastructures of east Africa. Antipode 52(3): 825–846.

29.

Kiplagat

(2018) Swazuri: Dispute over SGR Land Resolved. The Standard, 22 January. Available at: https://www.standardmedia.co.ke/business/article/2001265656/land-commission-moves-to-resolve-land-dispute

30.

Larsson

Kalsnes

(2014) ‘of course we are on Facebook’: use and non-use of social media among Swedish and Norwegian politicians. European Journal of Communication 29(6): 653–667.

31.

Lawani

Reed

Mark

, et al. (2019) Reviews and price on online platforms: evidence from sentiment analysis of Airbnb reviews in Boston. Regional Science and Urban Economics 75: 22–34.

32.

Lesutis

(2021) Infrastructural territorialisations: mega-infrastructures and the (re)making of Kenya. Political Geography 90: 102459.

33.

Liu

Dunford

Gao

(2018) A discursive construction of the Belt and Road Initiative: from neo-liberal to inclusive globalization. Journal of Geographical Sciences 28(9): 1199–1214.

34.

Liu

Teichert

Rossi

, et al. (2017) Big data for big insights: investigating language-specific drivers of hotel satisfaction with 412,784 user-generated reviews. Tourism Management 59: 554–563.

35.

Margetts

John

Hale

, et al. (2015) Political Turbulence: How Social Media Shape Collective Action. Princeton, NJ: Princeton University Press.

36.

Masua

Masasi

(2020) Enhancing text pre-processing for Swahili language: datasets for common Swahili stop-words, slangs and typos with equivalent proper words. Data in Brief 33: 106517.

37.

Mellon

Prosser

(2017) Twitter and Facebook are not representative of the general population: political attitudes and demographics of British social media users. Research & Politics 4(3): 2053168017720008.

38.

Michieka

(2005) English in Kenya: a sociolinguistic profile. World Englishes 24(2): 173–186.

39.

Miller

Bobkowski

Maliniak

, et al. (2015) Talking politics on Facebook: network centrality and political discussion practices in social media. Political Research Quarterly 68(2): 377–391.

40.

Mimno

Wallach

Talley

, et al. (2011) Optimizing semantic coherence in topic models. In: EMNLP 2011—conference on empirical methods in natural language processing, Edinburgh, 27–31 July, pp.262–272. Stroudsburg, PA: Association for Computational Linguistic.

41.

Muthoni

(2020) SGR case heads to Supreme Court. The Standard, 24 June. Available at: https://www.standardmedia.co.ke/nairobi/article/2001376223/sgr-case-heads-to-supreme-court

42.

Mwangi

(2008) Political corruption, party financing and democracy in Kenya. The Journal of Modern African Studies 46(2): 267–285.

43.

Mwiti

(2018) SGR Makes Sh10 Billion Loss in First Year. The Standard, 18 July. Available at: https://www.standardmedia.co.ke/business/business/article/2001288487/sgr-makes-sh10-billion-loss-in-first-year

44.

Nardi

Schiano

Gumbrecht

, et al. (2004) Why we blog. Communications of the ACM 47(12): 41–46.

45.

OECD (2018) China’s belt and road initiative in the global trade, investment and finance landscape. In: OECD Business and Finance Outlook. Paris: OECD Publishing.

46.

Pei

Sun

(2019) Slang detection and identification. In: Proceedings of the 23rd conference on computational natural language learning (CoNLL), Hong Kong, China, 3–4 November, pp.881–889. Association for Computational Linguistics.

47.

Pew Research Center (2019) Global Attitudes Survey Methodology—Kenya. Washington, DC: Pew Research Center.

48.

Poushter

Bishop

Chwe

(2018) Social Media Use Continues to Rise in Developing Countries but Plateaus Across Developed Ones. Washington, DC: Pew Research Center.

49.

Ross

Fountaine

Comrie

(2015) Facing up to Facebook: politicians, publics and the social media(ted) turn in New Zealand. Media Culture & Society 37(2): 251–269.

50.

Sadler

(2018) Narrative and interpretation on Twitter: Reading tweets by telling stories. New Media & Society 20(9): 3266–3282.

51.

Sarker

MNI

Hossin

Yin

, et al. (2018) One belt one road initiative of China: implication for future of global development. Modern Economy 9(4): 623–638.

52.

Shepard

(2020) How China is losing support for its belt and road initiative. Forbes, 28 February. Available at: https://www.forbes.com/sites/wadeshepard/2020/02/28/how-beijing-is-losing-support-for-its-belt-and-road-initiative/

53.

Shikali

Mokhosi

(2020) Enhancing African low-resource languages: Swahili data for language modelling. Data in Brief 31: 105951.

54.

Sloan

Morgan

Housley

, et al. (2013) Knowing the tweeters: deriving sociologically relevant demographics from Twitter. Sociological Research Online 18(3): 7.

55.

Steinert-Threlkeld

(2017) Spontaneous collective action: peripheral mobilization during the Arab spring. The American Political Science Review 111(2): 379–403.

56.

Sunstein

(2017) #Republic. Princeton, NJ: Princeton University Press.

57.

Theocharis

Barberã

Fazekas

, et al. (2020) The dynamics of political incivility on twitter. SAGE Open 10(2): 215824402091944.

58.

The World Bank (2021) Individuals using the Internet. Available at: https://data.worldbank.org/indicator/IT.NET.USER.ZS?end=2019&locations=KE&start=1990

59.

Twitter Development Team (2018) Do More with Twitter Data — Do more with Twitter data 0.1 documentation. Twitter API Documentation. Available at: https://twitterdev.github.io/do_more_with_twitter_data/finding_the_right_data.h

60.

Tymann

Lutz

Palsbröker

, et al. (2019) GerVADER: a German adaptation of the VADER sentiment analysis tool for social media texts. In: Proceedings of the Conference on “Lernen, Wissen, Daten, Analysen” (LWDA), Berlin, Germany. September 30-October 2, pp.178–189. CEUR Workshop Proceedings.

61.

Wasserman

(2015) South Africa and China as BRICS partners: media perspectives on geopolitical shifts. Journal of Asian and African Studies 50(1): 109–123.

62.

Woolley

Howard

(eds) (2019) Computational Propaganda: Political Parties, Politicians, and Political Manipulation on Social Media (Oxford Studies in Digital Politics). Oxford: Oxford University Press.

63.

(2017) Full text of President Xi’s speech at opening of Belt and Road forum. Xinhua News, 14 May. Available at: http://www.xinhuanet.com/english/2017-05/14/c_136282982.htm (accessed 16 July 2021).

64.

Zola

Cortez

Carpita

(2019) Twitter user geolocation using web country noun searches. Decision Support Systems 120: 50–59.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.01 MB