# Multi-Model Investigative Exploration of Social Media Data with boutique: A Case Study in Public Health

## TL;DR

This paper introduces boutique, a multi-model exploration system for social media data, aiding public health researchers in analyzing Twitter data related to HIV awareness through visualization and computation.

## Contribution

The paper presents the design of boutique, a novel middleware system that integrates heterogeneous data sources and computational capabilities for investigative data exploration.

## Key findings

- Successfully applied to a real-life HIV awareness case study
- Enables multi-step visualization and exploration of social media data
- Supports heterogeneous data types and integrated computation

## Abstract

We present our experience with a data science problem in Public Health, where researchers use social media (Twitter) to determine whether the public shows awareness of HIV prevention measures offered by Public Health campaigns. To help the researcher, we develop an investigative exploration system called boutique that allows a user to perform a multi-step visualization and exploration of data through a dashboard interface. Unique features of boutique includes its ability to handle heterogeneous types of data provided by a polystore, and its ability to use computation as part of the investigative exploration process. In this paper, we present the design of the boutique middleware and walk through an investigation process for a real-life problem.