Automated Classification of User Support Tickets (ACOUSTICS)

The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) is a leading data center that provides earth science data, information, and services to users all around the world. In order to further improve the GES DISC data services, user data and service analytics have been collected over the past year. In this project, we are analyzing the categorizing user support tickets through GES DISC’s tracking tool system. In particular, we experimented with machine learning and natural language processing practices to classify a ticket as one of four categories: findability, accessibility, interoperability, or reusability (i.e., F.A.I.R). This entails pre-processing the textual data, extracting features, and evaluating classification algorithms. The goal of this work is to use this model to classify historical tickets to gain a broader understanding of the GES DISC user needs. This poster was presented at the 2021 Earth Science Information Partners (ESIP) Summer Meeting held virtually in July 2021.