Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021;51(5):3052-3073.
doi: 10.1007/s10489-020-02033-3. Epub 2021 Feb 13.

Multilingual topic modeling for tracking COVID-19 trends based on Facebook data analysis

Amina Amara  1 , Mohamed Ali Hadj Taieb  2 , Mohamed Ben Aouicha  2
Affiliations

Multilingual topic modeling for tracking COVID-19 trends based on Facebook data analysis

Amina Amara et al. Appl Intell (Dordr). 2021.

Abstract

Social data has shown important role in tracking, monitoring and risk management of disasters. Indeed, several works focused on the benefits of social data analysis for the healthcare practices and curing domain. Similarly, these data are exploited now for tracking the COVID-19 pandemic but the majority of works exploited Twitter as source. In this paper, we choose to exploit Facebook, rarely used, for tracking the evolution of COVID-19 related trends. In fact, a multilingual dataset covering 7 languages (English (EN), Arabic (AR), Spanish (ES), Italian (IT), German (DE), French (FR) and Japanese (JP)) is extracted from Facebook public posts. The proposal is an analytics process including a data gathering step, pre-processing, LDA-based topic modeling and presentation module using graph structure. Data analysing covers the duration spanned from January 1st, 2020 to May 15, 2020 divided on three periods in cumulative way: first period January-February, second period March-April and the last one to 15 May. The results showed that the extracted topics correspond to the chronological development of what has been circulated around the pandemic and the measures that have been taken according to the various languages under discussion representing several countries.

Keywords: Covid-19; Data visualization; Facebook; Multilingual; Social media analysis; Topic modeling.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
LDA-based topic modeling process
Fig. 2
Fig. 2
Facebook-based COVID-19 tracking trends evolution system
Fig. 3
Fig. 3
Distribution of the COVID-19 related data through countries around the world
Fig. 4
Fig. 4
Distribution of the gathered Facebook public posts through the time since January 1st, 2020 to May 15, 2020
Fig. 5
Fig. 5
Correlation between percentage of COVID-19 Facebook posts during the period from January 1st, 2020 to May 15, 2020, and the percentage of users having post more than the fixed percentage
Fig. 6
Fig. 6
Facebook-based crowd-sourced COVID-19 trends covering 7 languages (EN, AR, FR, ES, IT, DE and JA) for the period January and February 2020
Fig. 7
Fig. 7
Facebook-based crowd-sourced about COVID-19 trends covering 7 languages (EN, AR, FR, ES, IT, DE and JA) for the period March (left part) and April 2020 (right part)
Fig. 7
Fig. 7
Facebook-based crowd-sourced about COVID-19 trends covering 7 languages (EN, AR, FR, ES, IT, DE and JA) for the period March (left part) and April 2020 (right part)
Fig. 8
Fig. 8
Facebook-based crowd-sourced trends about COVID-19 covering 7 languages (EN, AR, FR, ES, IT, DE and JA) for the period until May 15, 2020
Fig. 9
Fig. 9
Analysis of common topics in relation to their normalized weights in different languages
See this image and copyright information in PMC

References

    1. Sebei H, Taieb MAH, Aouicha MB. Review of social media analytics process and big data pipeline, Social Netw Analys Mining. 2018;8:30:1–30:28.
    1. Teodorescu H-N. Using analytics and social media for monitoring and mitigation of social disasters, Procedia Engineering. 2015;107:325–334. doi: 10.1016/j.proeng.2015.06.088. - DOI
    1. Joseph JK, Dev KA, Pradeepkumar A, Mohan M (2018) Big data analytics and social media in disaster management. In: Integrating Disaster Science and Management, Elsevier, pp 287–294
    1. Landwehr PM, Carley KM (2014) Social Media in Disaster Relief, Springer Berlin Heidelberg, Berlin, Heidelberg, 225–257
    1. Doan S, Vo B-KH, Collier N (2012) An analysis of twitter messages in the 2011 tohoku earthquake. In: P Kostkova, M Szomszor, D Fowler (Eds.), Electronic Healthcare, Springer Berlin Heidelberg, Berlin, Heidelberg, pp 58–66

LinkOut - more resources