Motivated by the significant decline incitizen’s trust in governments over the past decades, thispaper explores how policy decision makers and researcherscan use social media analytics to investigate trust,specifically the relationship among trust in government,trust in state institutions, and citizens’ collectivebehavior. Analysis of these complex socio-political issuesusing online social data requires a human in the inferenceloop while also benefiting from computational methods tohandle large amounts of unstructured data and the inferenceof relevant data features. To highlight the power of amixed-initiative visual analytics-data science approach,this technical note describes the exploratory analysis workundertaken for analysis of collections of Tweets fromBrazil, and describes further work that conceives datascience methods to assist the analysis process by supportingdefinition of constructs of concepts of interest usingsocial media data, and assisting the evaluation of evidencefor hypotheses evaluation in an interactive-machine learningfashion. The outcomes of this project aim to support socialsciences inquiry using observational social media data andWorld Bank operations.