Search Results for author: Aron Culotta

Found 14 papers, 5 papers with code

Inferring the Origin Locations of Tweets with Quantitative Confidence

no code implementations16 May 2013 Reid Priedhorsky, Aron Culotta, Sara Y. Del Valle

Social Internet content plays an increasingly critical role in many domains, including public health, disaster management, and politics.

Management

Controlling for Unobserved Confounds in Classification Using Correlational Constraints

no code implementations5 Mar 2017 Virgile Landeiro, Aron Culotta

In response, we propose a method to properly control for the influence of $z$ by first estimating its relationship with the class variable $y$, then updating predictions for $z$ to match that estimated relationship.

Classification General Classification

Co-training for Demographic Classification Using Deep Learning from Label Proportions

no code implementations13 Sep 2017 Ehsan Mohammady Ardehaly, Aron Culotta

To further support domains in which the data consist of two conditionally independent feature views (e. g. image and text), we propose a co-training algorithm that iteratively generates pseudo bags and refits the deep LLP model to improve classification accuracy.

Attribute General Classification +3

Forecasting the presence and intensity of hostility on Instagram using linguistic and social features

1 code implementation18 Apr 2018 Ping Liu, Joshua Guberman, Libby Hemphill, Aron Culotta

Online antisocial behavior, such as cyberbullying, harassment, and trolling, is a widespread problem that threatens free discussion and has negative physical and mental health consequences for victims and communities.

Task 2

When do Words Matter? Understanding the Impact of Lexical Choice on Audience Perception using Individual Treatment Effect Estimation

no code implementations12 Nov 2018 Zhao Wang, Aron Culotta

However, we lack general methods for estimating the causal effect of lexical choice on the perception of a specific sentence.

Sentence

Are Words Commensurate with Actions? Quantifying Commitment to a Cause from Online Public Messaging

no code implementations6 Oct 2020 Zhao Wang, Jennifer Cutler, Aron Culotta

Often, this public messaging is aimed at aligning the entity with a particular cause or issue, such as the environment or public health.

text-classification Text Classification

Identifying Spurious Correlations for Robust Text Classification

1 code implementation Findings of the Association for Computational Linguistics 2020 Zhao Wang, Aron Culotta

The predictions of text classifiers are often driven by spurious correlations -- e. g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment.

feature selection General Classification +5

Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals

1 code implementation18 Dec 2020 Zhao Wang, Aron Culotta

However, the classifier trained on the combined data is more robust and performs well on both the original test data and the counterfactual test data (e. g., 12%-25% increase in accuracy compared with the traditional classifier).

counterfactual General Classification +2

Enhancing Model Robustness and Fairness with Causality: A Regularization Approach

1 code implementation EMNLP (CINLP) 2021 Zhao Wang, Kai Shu, Aron Culotta

In this paper, we propose a simple and intuitive regularization approach to integrate causal knowledge during model training and build a robust and fair model by emphasizing causal features and de-emphasizing spurious features.

Causal Inference counterfactual +1

Leaders or Followers? A Temporal Analysis of Tweets from IRA Trolls

no code implementations4 Apr 2022 Siva K. Balasubramanian, Mustafa Bilgic, Aron Culotta, Libby Hemphill, Anita Nikolich, Matthew A. Shapiro

The Internet Research Agency (IRA) influences online political conversations in the United States, exacerbating existing partisan divides and sowing discord.

Cannot find the paper you are looking for? You can Submit a new open access paper.