Category Archives: Methodology

News and articles about social research methodology, digital research, computational social science, R coding, data and text mining

CooRTweet: an R package to detect coordinated behavior on Twitter

I have just release the beta version of CooRTweet, an R package that I developed to help detecting coordinated networks on Twitter.

The CooRTweet package builds on the existing literature on coordinated behavior and the experience of previous software, particularly CooRnet, to provide R users with an easy-to-use tool for coordinated action detection.

Coordinated behavior is a relevant social media strategy employed for political astroturfing (Keller et al., 2020), the spread of inappropriate content online (Giglietto et al., 2020), and activism. Software for academic research and investigative journalism has been developed in the last few years to detect coordinated behavior, such as the CooRnet R package (Giglietto, Righetti, Rossi, 2020), which detects Coordinated Link Sharing Behavior (CLSB) and Coordinated Image Sharing on Facebook and Instagram (CooRnet website), and the Coordination Network Toolkit by Timothy Graham (Graham, QUT Digital Observatory, 2020), a command line tool for studying coordination networks in Twitter and other social media data. CooRTweet adds to this set of tools with an easy app for R users.

Further details and the instruction for installing and using the package are available on GitHub: https://github.com/nicolarighetti/CooRTweet

A online handbook to learn R and Time Series Analysis

I have recently started to teach a course in data analysis with R at the University of Vienna, and I am creating a free online book where I explain fundamental R functions and data analysis operations, with a specific focus on time series analysis.

I’ll update the online book as the course goes on, but some chapters are already online. You can read the book at this link: Time Series Analysis With R

CooRnet: an R package for detecting coordinated behavior on social media

Today we have released CooRnet, an R package developed for detecting coordinated link sharing behavior on Facebook and Instagram.

Given a list of URLs, the package queries the CrowdTangle API link endpoint and retrieves the Facebook shares performed by public pages, groups and verified accounts, identifying the networks involved in coordinated activity.

The basic functions of CooRnet are augmented with other useful functions that create, for instance, the graph of the coordinated networks (to do additional network analysis) or the dataset of the most shared URLs.

CooRnet implements the methods we applied and detailed in our research on coordinated link sharing behavior on Facebook, as described in the report Understanding Coordinated and Inauthentic Link Sharing Behavior on Facebook in the Run-up to 2018 General Election and 2019 European Election in Italy – where we found, for instance, that URLs shared in a coordinated way gained more engagement than those shared in a non-coordinated way – and in the paper It takes a village to manipulate the media: coordinated link sharing behavior during 2018 and 2019 Italian elections.

Engagement by coordinated and non-coordinated activity on Facebook. Understanding Coordinated and Inauthentic Link Sharing Behavior on Facebook in the Run-up to 2018 General Election and 2019 European Election in Italy

In these works we found that networks involved in coordinated link sharing behavior are consistently associated with the spread of misinformation on Facebook. In the two figures below you can see the proportion of blacklisted domains shared by coordinated and non-coordinated entities, and the proportion of problematic entities (signaled by Avaaz) included in the coordinated and non-coordinated entities, as emerged in our studies on the Italian elections.

A more detailed description of CooRnet can be found on the dedicated website.

Proportion of problematic domains shared by coordinated and non-coordinated entities. The panel on the right displays the risk ratio (RR) values, all statistically significant. (It takes a village to manipulate the media)

Proportion of problematic entities included in the coordinated and non-coordinated entities. The panel on the right displays the risk ratio (RR) values, all statistically significant. (It takes a village to manipulate the media)

Using Twitter Data to Estimate Partisan Attention in a Multi-Party Media System

It has just been published “Multi-Party Media Partisanship Attention Score. Estimating Partisan Attention of News Media Sources Using Twitter Data in the Lead-up to 2018 Italian Election”.

Extending the computational method first introduced by Benkler, Faris, Roberts and others (see here and here), the paper makes use of Twitter data to measure partisan attention to news media sources in a multi-party political system.

To validate the method we compared our results with those obtained through a survey (ITANES), finding remarkable similarity (see figure below).

Furthermore, we analyzed the degree of polarization of the Italian online news media system we observed in the lead-up to the 2018 Italian election, finding a moderate level of polarization.

We also find that populist parties’ online communities relied on news sources characterized by an higher level of insularity (i.e. mainly shared on Twitter by their partisan community only) than non-populist ones.

Replication data and R code used in the study can be found here, while the paper can be read here.