Learning User-Specific Latent Influence and Susceptibility from Information Cascades

Authors: Yongqing Wang, Huawei Shen, Shenghua Liu, Xueqi Cheng

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on synthetic dataset and a large-scale microblogging dataset demonstrate that this model outperforms the existing pair-wise models at predicting cascade dynamics, cascade size, and who will be retweeted .
Researcher Affiliation Academia Yongqing Wang , Huawei Shen , Shenghua Liu and Xueqi Cheng CAS Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China wangyongqing@software.ict.ac.cn, {shenhuawei,liushenghua,cxq}@ict.ac.cn
Pseudocode Yes Algorithm 1 Parameter estimation
Open Source Code No The paper does not provide an explicit statement or link to the open-source code for the methodology described.
Open Datasets Yes The Microblog data from Sina Weibo website is published by WISE 2012 Challenge1, spanning from January 1, 2011 to Feburary 15, 2011. http://www.wise2012.cs.ucy.ac.cy/challenge.html
Dataset Splits No The paper specifies training and testing splits (e.g., 80% for training on synthetic data, and temporal splits D1-D3 for training and T1-T3 for testing on microblog data), but does not explicitly mention a separate validation dataset split.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes We set the dimensionality of user s influence Iu and susceptibility Su as 5... with λ = 0.01. ... We introduce the length of cascade context l... The parameters of the model are learned by minimizing the negative logarithmic likelihood... using Projected Gradient (PG) method... Input: Collection of cascades observed in a given time period, the maximum epoch M, and regularization parameters γI and γS