Individual Submission Summary
Share...

Direct link:

Distributed Sentiment Analysis of Real-Time Political Tweets

Sat, May 27, 8:00 to 9:15, Hilton San Diego Bayfront, Floor: 3, Aqua 313

Abstract

There is a growing interest in surveying political opinions using large-scale data produced by social media. This paper describes and assess the creation of machine learning models to predict sentiments in real-time political tweets and explains how this process can be scaled using commercial distributed computing when personal computers do not support computations and storage. We explain how communication scholars can locally analyze the tone of political tweets in real time using freely available resources such as Python and the Application Program Interface (API) of Twitter. We also explain how this procedure is scalable using commercial tools (AWS, Azure, IBM, etc.), instead of academic grids. The described procedure to monitor political tweets in streaming might help testing traditional and emerging theoretical approaches in communication research that require longitudinal data and might also contribute to experimental studies, which need real-time inputs to create or adapt stimuli.

Authors