Tracking Political Elections on Social Media: Applications and Experience

Authors: Danish Contractor, Bhupesh Chawda, Sameep Mehta, L Venkata Subramaniam, Tanveer Afzal Faruquie

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Using data from the 2012 US presidential elections and the 2013 Philippines General elections, we provide detailed experiments on our methods that use granger causality to identify topics that were most causal for public opinion and which in turn, give an interpretable insight into elections topics that were most important.
Researcher Affiliation Industry Danish Contractor IBM Research New Delhi dcontrac@in.ibm.com Bhupesh Chawda IBM Research New Delhi bhchawda@in.ibm.com Sameep Mehta IBM Research New Delhi sameepmehta@in.ibm.com L. Venkata Subramaniam IBM Research New Delhi lvsubram@in.ibm.com Tanveer A. Faruquie IBM T.J. Watson Research Center Yorktown Heights, New York tafaruqu@us.ibm.com
Pseudocode Yes Algorithm 1 Build prediction model using n-grams occurring in the data
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described.
Open Datasets No The paper describes using Gallup poll data, Twitter data collected via twitter4j API, and Pulse Asia electoral surveys. However, it does not provide concrete access information (e.g., specific links, DOIs, or formal citations with authors and year for a directly usable dataset) for these datasets as publicly available in the specific form they collected/used.
Dataset Splits No The paper mentions training models using 'data from the last seven days' to predict on the 'eighth day' or 'election day', which implies a temporal split for training and testing. However, it does not specify explicit percentages or sample counts for training, validation, or test sets, nor does it mention a separate validation set.
Hardware Specification No The paper mentions using 'a multi-node Hadoop cluster' but does not provide specific hardware details such as CPU/GPU models, memory specifications, or cloud instance types.
Software Dependencies Yes We made use of Lasso Granger regression implementation provided by Matlab5 for our experiments.
Experiment Setup No The paper describes the data collection and processing, but it does not provide specific details on experimental setup, such as hyperparameters (e.g., learning rate, batch size, number of epochs) or specific optimizer settings used for training the models.