Predicting Online Protest Participation of Social Media Users

Authors: Suhas Ranganath, Fred Morstatter, Xia Hu, Jiliang Tang, Suhang Wang, Huan Liu

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the framework using data from the social media platform Twitter on protests during the recent Nigerian elections and demonstrate that it can effectively predict whether the next post of a user is a declaration of protest. Experiments We evaluate the framework using a real world dataset presented in Table 1 by answering the following questions: How does the framework perform in determining whether the next post of the user is a declaration of protest? What is the effect of the varying proportions of the interaction network information on the performance of the framework? How does the framework perform for different proportions of training data?
Researcher Affiliation Collaboration Suhas Ranganath srangan8@asu.edu Arizona State University Fred Morstatter Fred.Morstatter@asu.edu Arizona State University Xia Hu hu@cse.tamu.edu Texas A&M University Jiliang Tang jlt@yahoo-inc.com Yahoo Labs Suhang Wang swang187@asu.edu Arizona State University Huan Liu Huan.Liu@asu.edu Arizona State University
Pseudocode Yes Algorithm 1: Predicting Online Protest Participation
Open Source Code No The paper does not contain any explicit statement about releasing the source code for the methodology, nor does it provide a link to a code repository.
Open Datasets No The paper describes its data collection process from the Twitter Streaming API and labeling using Amazon Mechanical Turk, but it does not provide a link, DOI, or formal citation for public access to the collected dataset.
Dataset Splits No The paper specifies a train-test split ("earliest 50% of the candidate posts for training and the rest for testing"), but it does not explicitly mention a separate validation split or how it was handled.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU/CPU models, memory, or cluster specifications.
Software Dependencies No The paper does not mention any specific software dependencies or libraries with their version numbers that would be required to reproduce the experiments.
Experiment Setup Yes In this experiment, we set the value of information network parameter at wreg = 0.1 and the number of latent dimensions I = 50.