arXiv subjects

Jessica Zhu

Publications and source records attributed to Jessica Zhu.

3 recordsLinked to original sources

arXiv2024

DocNet: Semantic Structure in Inductive Bias Detection Models

News will be biased so long as people have opinions. As social media becomes the primary entry point for news and partisan differences increase, it is increasingly important for informed citizens to be able to recognize bias. If people are aware of the biases of the news they consume, they will be able to take action to avoid polarizing echo chambers. In this paper, we explore an often overlooked aspect of bias detection in media: the semantic structure of news articles. We present DocNet, a novel, inductive, and low-resource document embedding and political bias detection model. We also demonstrate that the semantic structure of news articles from opposing political sides, as represented in document-level graph embeddings, have significant similarities. DocNet bypasses the need for pre-trained language models, reducing resource dependency while achieving comparable performance. It can be used to advance political bias detection in low-resource environments. Our code and data are made available at: https://anonymous.4open.science/r/DocNet/

cs.CL↗

arXiv2024

Nutrition Facts, Drug Facts, and Model Facts: Putting AI Ethics into Practice in Gun Violence Research

Objective: Firearm injury research necessitates using data from often-exploited vulnerable populations of Black and Brown Americans. In order to minimize distrust, this study provides a framework for establishing AI trust and transparency with the general population. Methods: We propose a Model Facts template that is easily extendable and decomposes accuracy and demographics into standardized and minimally complex values. This framework allows general users to assess the validity and biases of a model without diving into technical model documentation. Examples: We apply the Model Facts template on two previously published models, a violence risk identification model and a suicide risk prediction model. We demonstrate the ease of accessing the appropriate information when the data is structured appropriately. Discussion: The Model Facts template is limited in its current form to human based data and biases. Like nutrition facts, it also will require some educational resources for users to grasp its full utility. Human computer interaction experiments should be conducted to ensure that the interaction between user interface and model interface is as desired. Conclusion: The Model Facts label is the first framework dedicated to establishing trust with end users and general population consumers. Implementation of Model Facts into firearm injury research will provide public health practitioners and those impacted by firearm injury greater faith in the tools the research provides.

cs.AI↗

arXiv2023

Analysis of Media Writing Style Bias through Text-Embedding Networks

With the rise of phenomena like `fake news' and the growth of heavily-biased media ecosystems, there has been increased attention on understanding and evaluating media bias. Of particular note in the evaluation of media bias is writing style bias, which includes lexical bias and framing bias. We propose a novel approach to evaluating writing style bias that utilizes natural language similarity estimation and a network-based representation of the shared content between articles to perform bias characterization. Our proposed method presents a new means of evaluating writing style bias that does not rely on human experts or knowledge of a media producer's publication procedures. The results of experimentation on real-world vaccine mandate data demonstrates the utility of the technique and how the standard bias labeling procedures of only having one bias label for a media producer is insufficient to truly characterize the bias of that media producer.

cs.SI↗