Towards a Service-Oriented Architecture for Pre-Processing Crowd-Sourced Sentiment from Twitter
Julian Jarrett, Kimberley Hemmings-Jarrett, M. Brian Blake · 2019
Online social media platforms like Twitter, provide opinion rich repositories for conducting sentiment analysis. Users engage in open discussions on a variety of topics across a wide cross-section of problem domains. Commercial, government, educational, non-profit and other types of agencies are increasingly relying on extracting conversations on Twitter to determine the general sentiment of the public on particular topics, products, services and issues. Despite being readily available and in abundance, it is also laced with nuances which can disrupt, skew and potentially lead to inaccurate analysis if not handled properly. In this paper, we propose an SOA framework to enable the pre-processing of data origination on Twitter, and configurable components that allow data consumers to filter the data using useful social media signals.