Applying Word Embeddings to Measure Valence in Information Operations Targeting Journalists in Brazil

TL;DR

This paper explores how word embeddings can measure the overall valence of targeted actors in information operations, revealing subtle biases and campaign impacts on Twitter discourse, especially against journalists in Brazil.

Contribution

It introduces a novel approach using word embeddings to assess the collective valence of actors affected by information operations, beyond content-level detection.

Findings

Campaigns target female journalists more than males.

Detectable traces of targeted campaigns are present in Twitter discourse.

Preliminary results indicate shifts in overall discourse valence.

Abstract

Among the goals of information operations are to change the overall information environment vis-\'a-vis specific actors. For example, "trolling campaigns" seek to undermine the credibility of specific public figures, leading others to distrust them and intimidating these figures into silence. To accomplish these aims, information operations frequently make use of "trolls" -- malicious online actors who target verbal abuse at these figures. In Brazil, in particular, allies of Brazil's current president have been accused of operating a "hate cabinet" -- a trolling operation that targets journalists who have alleged corruption by this politician and other members of his regime. Leading approaches to detecting harmful speech, such as Google's Perspective API, seek to identify specific messages with harmful content. While this approach is helpful in identifying content to downrank, flag, or remove, it is known to be brittle, and may miss attempts to introduce more subtle biases into the discourse. Here, we aim to develop a measure that might be used to assess how targeted information operations seek to change the overall valence, or appraisal, of specific actors. Preliminary results suggest known campaigns target female journalists more so than male journalists, and that these campaigns may leave detectable traces in overall Twitter discourse.