Constructing an Artworld Influencers Network by Mining Social Media
arXiv:2611.02657 · doi:10.1162/leon_a_02094
Abstract
The author shows a methodology for constructing a network map of the artworld. The tweets posted by a manually comprised set of exemplar artworld actors and Natural Language Processing (NLP) methods are used to identify significant artworld actors, including those that do not own a Twitter account. Identified artworld actors form communities detected with the Louvain method, and their authority is evaluated with the HITS centrality method. The resulting artworld network exhibits the ability, starting with a small set of exemplar actors, to identify new artworld actors and provides a wealth of data that would be very hard to collect otherwise.
arXiv commentAuthor's accepted manuscript. Published in Leonardo 55(1), 24-29 (2022), MIT Press. (c) 2022 ISAST. Supplemental material and tweet IDs: https://doi.org/10.5281/zenodo.23586408