no code implementations • 16 Jan 2023 • Christopher Tran, Keith Burghardt, Kristina Lerman, Elena Zheleva
In this work, we provide a survey of state-of-the-art data-driven methods for heterogeneous treatment effect estimation using machine learning, broadly categorizing them as methods that focus on counterfactual prediction and methods that directly estimate the causal effect.
1 code implementation • 31 Oct 2022 • Georgios Chochlakis, Gireesh Mahajan, Sabyasachee Baruah, Keith Burghardt, Kristina Lerman, Shrikanth Narayanan
In this work, we study how we can build a single model that can transition between these different configurations by leveraging multilingual models and Demux, a transformer-based model whose input includes the emotions of interest, enabling us to dynamically change the emotions predicted by the model.
1 code implementation • 28 Oct 2022 • Georgios Chochlakis, Gireesh Mahajan, Sabyasachee Baruah, Keith Burghardt, Kristina Lerman, Shrikanth Narayanan
First, we develop two modeling approaches to the problem in order to capture word associations of the emotion words themselves, by either including the emotions in the input, or by leveraging Masked Language Modeling (MLM).
no code implementations • 19 Sep 2022 • Matheus Schmitz, Keith Burghardt, Goran Muric
In this paper, we measure the impact of joining fringe hateful communities in terms of hate speech propagated to the rest of the social network.
1 code implementation • 19 Mar 2022 • Marcin Abram, Keith Burghardt, Greg Ver Steeg, Aram Galstyan, Remi Dingreville
The identification and classification of transitions in topological and microstructural regimes in pattern-forming processes are critical for understanding and fabricating microstructurally precise novel materials in many application domains.
1 code implementation • 18 Jan 2022 • Keith Burghardt, Kristina Lerman
In this work, we explore algorithmic confounding in collaborative filtering-based recommendation algorithms through teacher-student learning simulations.
no code implementations • 27 Oct 2021 • Yuzi He, Christopher Tran, Julie Jiang, Keith Burghardt, Emilio Ferrara, Elena Zheleva, Kristina Lerman
The popularity of online gaming has grown dramatically, driven in part by streaming and the billion-dollar e-sports industry.
1 code implementation • 21 Oct 2021 • Matheus Schmitz, Goran Murić, Keith Burghardt
The goal of this study is to better understand anti-vaccine sentiment by developing a system capable of automatically identifying the users responsible for spreading anti-vaccine narratives.
1 code implementation • 31 Aug 2021 • Nazanin Alipourfard, Keith Burghardt, Kristina Lerman
Quantitative analysis of large-scale data is often complicated by the presence of diverse subgroups, which reduce the accuracy of inferences they make on held-out data.
no code implementations • 30 Oct 2020 • Yuzi He, Keith Burghardt, Siyi Guo, Kristina Lerman
Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups.
no code implementations • 23 Oct 2020 • Keith Burghardt, Tad Hogg, Raissa M. D'Souza, Kristina Lerman, Marton Posfai
We use this data to construct a model that quantifies how judgement heuristics and option quality combine when deciding between two options.
Social and Information Networks Human-Computer Interaction
1 code implementation • 28 Oct 2019 • Yuzi He, Keith Burghardt, Kristina Lerman
To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms.
no code implementations • 24 Feb 2016 • Keith Burghardt, Emanuel F. Alsina, Michelle Girvan, William Rand, Kristina Lerman
Our results suggest that, rather than evaluate all available answers to a question, users rely on simple cognitive heuristics to choose an answer to vote for or accept.