Election Prediction on Twitter: A Systematic Mapping Study

Table 1

Description of research and demographic questions (RQs and DQs).

Questions	Description
RQ1	Approaches (sentiment analysis, volumetric, social network analysis, or hybrid) used in the selected papers.
RQ1(a)	Identify the learning techniques of the approaches used in the selected papers: Machine Learning (supervised, unsupervised, hybrid, deep learning), lexicon-based approach, and no machine learning (volumetric, online tool).
RQ1(b)	Identify tools, libraries, and dictionaries along with the primary studies.
RQ1(c)	List the techniques used for collecting tweets.
RQ2	Identify and list the studies that manually/automatically labelled the data to assist their experiments (training, testing data).
RQ3	List of the countries whose elections are analyzed on Twitter in the selected papers.
RQ4	List of tweet languages analyzed in the selected papers.
RQ5	Identify the most frequent topics automatically using LDA in the selected papers.
DQ1, DQ2, DQ3	Based on the number of publications, the minimum contribution level is two papers.