The human annotation of social bots is an essential task for the training of new algorithms and bot detection techniques. How-ever, identifying bot users on social media is tricky and error-prone, even for expert annotators. Furthermore, this task is often time-consuming and the results are modest. The Bot Detection Support Tool (#BDST) is a tool developed in order to make it possible for a human annotator to better understand the behaviour of a Twitter account through intuitive visualizations of the user's activity. Re-sults show a usable and exective tool, with great potential for future research.
#BDST: Bot Detection Support Tool for human annotators of Twitter data
S Tardelli;M Tesconi
2019
Abstract
The human annotation of social bots is an essential task for the training of new algorithms and bot detection techniques. How-ever, identifying bot users on social media is tricky and error-prone, even for expert annotators. Furthermore, this task is often time-consuming and the results are modest. The Bot Detection Support Tool (#BDST) is a tool developed in order to make it possible for a human annotator to better understand the behaviour of a Twitter account through intuitive visualizations of the user's activity. Re-sults show a usable and exective tool, with great potential for future research.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
