Correlated Cascades: Compete or Cooperate

Authors: Ali Zarezade, Ali Khodadadi, Mehrdad Farajtabar, Hamid Rabiee, Hongyuan Zha

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on synthetic and two real datasets gathered from Twitter, URL shortening and music streaming services, illustrate the superior performance of the proposed model over the alternatives.
Researcher Affiliation Academia Sharif University of Technology, Azadi Ave, Tehran, Iran Georgia Institute of Tech., North Ave NW, Atlanta, GA 30332, United States
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Implementation codes and datasets can be found at https: //github.com/alikhodadadi/C4.
Open Datasets Yes We use the data crawled from Twitter (Hodas and Lerman 2014).
Dataset Splits No We set aside the last 20% of the data for the test set. The models are trained five times with 20% to 100% of the train data and β found by cross-validation. This describes test split and cross-validation for hyperparameter tuning, but not an explicit validation split percentage or count separate from the training data.
Hardware Specification No No specific hardware details (like GPU/CPU models or memory amounts) used for running the experiments are provided in the paper.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes The parameters of the models were drawn randomly from uniform distribution μi,p U(0, 0.1) and αi,j U(0, 0.01). Also, we set β = 1. In the correlated models, we set β = 0.1, 1, 100 to see the effect of mark function on the competitive or cooperative behavior of the proposed model. We trained 10 models, on 10% to 100% of the synthetic training data.