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

Social data has shown important role in tracking, monitoring and risk management of disasters. Indeed, several works focused on the benets of social data analysis to the healthcare practices and curing. 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 modelling 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: rst 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 in the various languages under discussion.

Trace publics as a qualitative critical network tool: Exploring the dark matter in the #MeToo movement

The relationship between the daily practice of personal politics and digitally networked publics amplify a familiar shaping and reshaping of the social. This article expands on nascent critiques of nodocentrism as a contemporary representation of the social in new media research to begin to advance a digital methods multidisciplinary project. Trace publics as a qualitative critical network (QCN) approach considers how representations developed by big social data analysis are shaped by everyday practices. Using the #MeToo phenomenon as an analogous frame, I show how trace publics can be used as a theoretical and methodological device for deconstructing, co-constructing, and reconstructing representations in social media research. The goal of such a proposal is to encourage future critical network and data research to consider the ethical ramifications of nodocentric representations of the social and the methodological possibilities of trace publics.

Social Network Analysis

Each day, 2.5 quintillion bytes of data are generated due to our daily activity. It is due to the vast amount of use of the smart mobiles, Cloud data storage, and the Internet of Things. In earlier days, these technologies were utilized by large IT companies and the private sector, but now each person has a high-end smartphone along with the cloud and IoT for the easy storage of data and backup. The analysis of the data generated by social media is a tedious process and involves a lot of techniques. Some tools for social network analysis are: Gephi, Networkx, IGraph, Pajek, Node XL, and cytoscope. Apart from these tools there are various efficient social data analysis algorithms that are far more helpful in doing analytics. The need for and use of social network analysis is very helpful in our current problem of huge data generation. In this chapter, the need for the analysis of social data along with the tools that are needed for the analysis and the techniques that are to be implemented in the field of social data analysis are covered.