Mining voter sentiments from Twitter data for the 2016 Uganda Presidential elections

Abstract

Micro-bogging platforms like Twitter have proved to be fertile ground for political campaigns. In several applications, Twitter data has been mined to understand sentiments of the population, to determine trends and to understand the informal communication amongst people. A key challenge with the Twitter platform is that it produces immense quantities of noisy unstructured user-generated data across multiple social relations. The uniqueness of social media data calls for novel data mining techniques that can effectively handle user-generated content with rich social relations in order to build descriptive and predictive models of social interactions. We analyse Twitter data for the #UgandaDecides hash tag for Uganda Presidential elections 2016, during the period of January to February. We derive inferences from the data and show that in some cases Twitter can be informative on actual events happening on ground. In the analysis we use a word-emotion lexicon to determine the nature of sentiments in the tweets and semantic orientation, to determine the ties conversations within the tweets have with positive and negative contexts, this is based on the pointwise mutual information technique. We find that twitter data analytics using both intensity-based measures and sentiment analysis can be useful to reflect the current offline political sentiment and we make a number of observations related to the task of monitoring public sentiments during an election campaign, including examining a variety of sample sizes, time parameters as well as methods for quantitatively and qualitatively exploring the underlying content.