Evaluation of a Reusable Technique for Refining Social Media Query Criteria for Crowd-Sourced Sentiment for Decision Making

Abstract

There are three categories of users that consume social media data either for their personal use or for aggregation and presentation to others. These users rely on a preferential combination of Social Media Signals (SMS) that satisfies their information goals and aids in their decisionmaking. The research community is split on how to deal with some signals such as text originating from robotic voices; some suggest removing them while others are more interested in better identifying them. This paper statistically tests the SMS's in a dataset gathered during one of the political debates during the US Presidential Elections in 2016. It introduces a reusable technique aimed at contributing to the iterative and symbiotic user-system relationship, while improving the opportunity for arriving at empirically supported results for decision-making instances regardless of the consumer group.