Scott A. Hale

TL;DR: The authors developed a machine learning classifier to infer political leaning from non-political text and, optionally, the accounts a user follows on social media, using voter advice application results shared on Twitter as their groundtruth.

TL;DR: In this paper, the first longitudinal study of how emoji semantics changes over time, applying techniques from computational linguistics to six years of Twitter data, identifying five patterns in emoji semantic development and finding evidence that the less abstract an emoji is, the more likely it is to undergo semantic change.

TL;DR: This article examined the dynamics of sharing petitions on social media in order to garner signatures and, ultimately, a government response and found that Twitter users do not exclusively share petitions on one issue nor do they share exclusively popular petitions.

TL;DR: This paper evaluated the role of semantic and multimodal context for detecting implicit and explicit hate and found that both text-and visual-enhancementioning models outperformed other models' F1 scores.

TL;DR: In this article, the authors argue that a systematic collaborative exploration and assessment of Wikipedia content and coverage is still largely missing, and they argue that collaborative visualizations have the potential to fill this gap, affording editors to collaboratively explore and analyse patterns in Wikipedia content, at different scales.