Reactions to science communication: discovering social network topics using word embeddings and semantic knowledge

Abstract

Abstract Social media platforms that disseminate scientific information to the public during the COVID-19 pandemic highlighted the importance of the topic of scientific communication. Content creators in the field, as well as researchers who study the impact of scientific information online, are interested in how people react to these information resources. This study aims to gain insights into how the public perceives scientific information, and how their behavior towards science communication (e.g. through videos or texts) during the pandemic is related to their information-seeking behavior. To analyze public reactions to scientific information, the study focused on Twitter users who are doctors, researchers, science communicators, or representatives of research institutes, and analyzed their replies for 2 years from the start of the pandemic. One large challenge consists in sifting through social media data to find comments related to a reaction towards scientific content that might prove useful feedback to a content creator. The study aimed in developing a solution powered by topic modelling enhanced by manual validation and other machine learning techniques, such as word embeddings, that is capable of filtering massive social media datasets in search of documents related to reactions to scientific communication. This architecture can be replicated for finding any documents related to niche topics in social media data.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.