An introduction to agent‐based models as an accessible surrogate to field‐based research and teaching
There are many barriers to fieldwork including cost, time, and physical ability. Unfortunately,
these barriers disproportionately affect minority communities and create a disparity in access …
these barriers disproportionately affect minority communities and create a disparity in access …
Vam: an end-to-end simulator for time series regression and temporal link prediction in social media networks
F Mubang, LO Hall - IEEE transactions on computational social …, 2022 - ieeexplore.ieee.org
We present a machine-learning-driven end-to-end simulator, called the Volume-Audience-
Match (VAM) simulator. VAM's purpose is to simulate future phenomena related to various …
Match (VAM) simulator. VAM's purpose is to simulate future phenomena related to various …
Deep agent: Studying the dynamics of information spread and evolution in social networks
This paper explains the design of a social network analysis framework, developed under
DARPA's SocialSim program, with novel architecture that models human emotional …
DARPA's SocialSim program, with novel architecture that models human emotional …
Analyzing the productivity of GitHub teams based on formation phase activity
Our goal is to understand the characteristics of high-performing teams on GitHub. Towards
this end, we collect data from software repositories and evaluate teams by examining …
this end, we collect data from software repositories and evaluate teams by examining …
Simulating New and Old Twitter User Activity with XGBoost and Probabilistic Hybrid Models
F Mubang, L Hall - 2022 21st IEEE International Conference on …, 2022 - ieeexplore.ieee.org
The Volume Audience Match Simulator is an end-to-end approach for predicting user-to-
user interactions on a given social media platform. It is comprised of 2 components: firstly, an …
user interactions on a given social media platform. It is comprised of 2 components: firstly, an …
Simulating User-Level Twitter Activity with XGBoost and Probabilistic Hybrid Models
F Mubang, L Hall - arXiv preprint arXiv:2202.08964, 2022 - arxiv.org
The Volume-Audience-Match simulator, or VAM was applied to predict future activity on
Twitter related to international economic affairs. VAM was applied to do timeseries …
Twitter related to international economic affairs. VAM was applied to do timeseries …
Explaining differences in classes of discrete sequences
S Saadat, G Sukthankar - 2020 IEEE/WIC/ACM International …, 2020 - ieeexplore.ieee.org
While there are many machine learning methods to classify and cluster sequences, they fail
to explain what are the differences in groups of sequences that make them distinguishable …
to explain what are the differences in groups of sequences that make them distinguishable …
A popularity-based model of the diffusion of innovation on GitHub
A Al-Rubaye, G Sukthankar - Proceedings of the 2018 Conference of the …, 2020 - Springer
Open source software development platforms are natural laboratories for studying the
diffusion of innovation across human populations, enabling us to better understand what …
diffusion of innovation across human populations, enabling us to better understand what …
Negative influence gradients lead to lowered information processing capacity on social networks
Communication networks are known to exhibit asymmetric influence structures, constructed
of a spectrum from highly influential individuals to highly influenced individuals. Information …
of a spectrum from highly influential individuals to highly influenced individuals. Information …
Social Media Time Series Forecasting and User-Level Activity Prediction with Gradient Boosting, Deep Learning, and Data Augmentation
F Mubang - 2022 - search.proquest.com
In the overall history of technological innovations, social media has only existed for a brief
time, however its influence is undeniable. Researchers have found that it can be used to …
time, however its influence is undeniable. Researchers have found that it can be used to …