Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Division
Browse By Session Type
Search Tips
Personal Schedule
Sign In
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.
Carlos Arcila Calderon, Universidad de Salamanca
Miguel Vicente-Marino, U of Valladolid
Felix Ortega, U of Salamanca