Media Bias, the Social Sciences, and NLP: Automating Frame Analyses to Identify Bias by Word Choice and Labeling

Abstract

Media bias can strongly impact the public perception of topics reported in the news. A difficult to detect, yet powerful form of slanted news coverage is called bias by word choice and labeling (WCL). WCL bias can occur, for example, when journalists refer to the same semantic concept by using different terms that frame the concept differently and consequently may lead to different assessments by readers, such as the terms "freedom fighters" and "terrorists," or "gun rights" and "gun control." In this research project, I aim to devise methods that identify instances of WCL bias and estimate the frames they induce, e.g., not only is "terrorists" of negative polarity but also ascribes to aggression and fear. To achieve this, I plan to research methods using natural language processing and deep learning while employing models and using analysis concepts from the social sciences, where researchers have studied media bias for decades. The first results indicate the effectiveness of this interdisciplinary research approach. My vision is to devise a system that helps news readers to become aware of the differences in media coverage caused by bias.

Newsalyze: Effective Communication of Person-Targeting Biases in News Articles

“…Shown is the three-tasks analysis workflow as it preprocesses news articles reporting on the same event, extracts and resolves phrases referring to persons involved in the event, and groups articles reporting similarly on these persons. Adapted from: [27] sentiment polarity s i in a is…”

Newsalyze: Enabling News Consumers to Understand Media Bias

“…Thus, we currently focus on targeted sentiment, which is a high-level effect of WCL bias but also a universal perception dimension. To achieve state of-the-art performance in target-dependent sentiment classification (TSC) on news articles, we use NewsTSC, a BERT-based neural model [5]. Lastly, the system visualizes the identified instances of WCL bias using two visualizations, which follow the overview first, details on demand mantra [10].…”

Towards Target-Dependent Sentiment Classification in News Articles

“…In this paper, we investigate TSC in the domain of news articles -a much less researched domain that is of critical relevance, especially in times of "fake news," echo chambers, and news owner centralization [15]. How persons and other entities are portrayed in articles on political topics is, e.g., very relevant for individual and societal opinion formation [3,14,17].…”