Social Media Analytics for Elections

A major project I have been working on recently, is the analysis of social media conversations around national elections in Asian societies. This project comprises a series of published studies conducted in Southeast Asia for examing some of the following questions: (a) the topical, functional, and interactional strategies of political parties in their Twitter campaigns (Ahmed, Jaidka, & Cho, 2016), (b) the role of social media campaigns in mobilizing, informing, and engaging votes during general elections (Ahmed & Skoric, 2014; Jaidka, & Ahmed, 2015), (c) the role of social media campaigns in increasing the public outreach of emerging parties (Ahmed & Skoric, 2015), and in (d) creating communities and echo chambers around common ideals and social cues (Ahmed, Jaidka, & Cho, 2018). Three journal articles and 5 conference papers related to this project have been published or presented at premier venues.

My collaborators are academicians at Nanyang Technological University Singapore, University of California Davis, and the City University of Hong Kong. We aim to fill the present research gaps in political opinion mining from social media, and generate robust empirical benchmarks of the predictive utility of different computational methodologies. I am primarily responsible for planning and implementing the analyses, which will employ volumetrics, sentiment analysis based on lexicon and probabilistic models, and social network analysis to analyze over 6 million tweets related to the general elections in three Asian democracies (India, Pakistan and Malaysia) and one European democracy (UK). 

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Blog at

Up ↑

%d bloggers like this: