An official website of the United States government
News media is expected to uphold unbiased reporting. Yet they may still affect public opinion by selectively including or omitting events that support or contradict their ideological positions. Prior work in NLP has only studied media bias via linguistic style and word usage. In this paper, we study to which degree media balances news reporting and affects consumers through event inclusion or omission. We first introduce the task of detecting both partisan and counter- partisan events: events that support or oppose the author’s political ideology. To conduct our study, we annotate a high-quality dataset, PAC, containing 8 , 511 (counter-)partisan event annotations in 304 news articles from ideologically diverse media outlets. We benchmark PAC to highlight the challenges of this task. Our findings highlight both the ways in which the news subtly shapes opinion and the need for large language models that better understand events within a broader context. Our dataset can be found at https://github.com/ launchnlp/Partisan-Event-Dataset.
more »
« less
Predicting Personal Opinion on Future Events with Fingerprints
Predicting users’ opinions in their response to social events has important real-world applications, many of which political and social impacts. Existing approaches derive a population’s opinion on a going event from large scores of user generated content. In certain scenarios, we may not be able to acquire such content and thus cannot infer an unbiased opinion on those emerging events. To address this problem, we propose to explore opinion on unseen articles based on one’s fingerprinting: the prior reading and commenting history. This work presents a focused study on modeling and leveraging fingerprinting techniques to predict a user’s future opinion. We introduce a recurrent neural network based model that integrates fingerprinting. We collect a large dataset that consists of event-comment pairs from six news websites. We evaluate the proposed model on this dataset. The results show substantial performance gains demonstrating the effectiveness of our approach.
more »
« less
- Award ID(s):
- 1838145
- PAR ID:
- 10292536
- Date Published:
- Journal Name:
- Proceedings of COLING
- ISSN:
- 1525-2477
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
It is critical in social network analysis to understand the underlying mechanisms of online information diffusion. Although there has been much progress on the influential factors that lead to online viral diffusion, little is known about the impact by public opinion. In this paper, we examine the relations between the public opinion among information propagators and the virality of online diffusion based on a large-scale real-world dataset. We propose a set of new metrics for public opinion in online diffusion to reveal their correlation with diffusion structural virality, and further apply our understanding to predict diffusion virality based on public opinion. The experimental results show the effectiveness of the proposed analysis in the prediction of viral diffusion events.more » « less
-
Influence operations are large-scale efforts to manipulate public opinion. The rapid detection and disruption of these operations is critical for healthy public discourse. Emergent AI technologies may enable novel operations that evade detection and influence public discourse on social media with greater scale, reach, and specificity. New methods of detection with inductive learning capacity will be needed to identify novel operations before they indelibly alter public opinion and events. To this end, we develop an inductive learning framework that: (1) determines content- and graph-based indicators that are not specific to any operation; (2) uses graph learning to encode abstract signatures of coordinated manipulation; and (3) evaluates generalization capacity by training and testing models across operations originating from Russia, China, and Iran. We find that this framework enables strong cross-operation generalization while also revealing salient indicators-illustrating a generic approach which directly complements transductive methodologies, thereby enhancing detection coverage.more » « less
-
One of the challenging problems in large scale cyber-argumentation platforms is that users often engage and focus only on a few issues and leave other issues under-discussed and under-acknowledged. This kind of non-uniform participation obstructs the argumentation analysis models to retrieve collective intelligence from the underlying discussion. To resolve this problem, we developed an innovative opinion prediction model for a multi-issue cyber-argumentation environment. Our model predicts users’ opinions on the non-participated issues from similar users’ opinions on related issues using intelligent argumentation techniques and a collaborative filtering method. Based on our detailed experimental results on an empirical dataset collected using our cyber-argumentation platform, our model is 21.7% more accurate, handles data sparsity better than other popular opinion prediction methods. Our model can also predict opinions on multiple issues simultaneously with reasonable accuracy. Contrary to existing opinion prediction models, which only predict whether a user agrees on an issue, our model predicts how much a user agrees on the issue. To our knowledge, this is the first research to attempt multi-issue opinion prediction with the partial agreement in the cyber-argumentation platform. With additional data on non-participated issues, our opinion prediction model can help the collective intelligence analysis models to analyze social phenomena more effectively and accurately in the cyber argumentation platform.more » « less
-
The widespread use of social media has led to a surge in popularity for automated methods of analyzing public opinion. Supervised methods are adept at text categorization, yet the dynamic nature of social media discussions poses a continual challenge for these techniques due to the constant shifting of the focus. On the other hand, traditional unsupervised methods for extracting themes from public discourse, such as topic modeling, often reveal overarching patterns that might not capture specific nuances. Consequently, a significant portion of research into social media discourse still depends on labor-intensive manual coding techniques and a human-in-the-loop approach, which are both time-consuming and costly. In this work, we study the problem of discovering arguments associated with a specific theme. We propose a generic **LLMs-in-the-Loop** strategy that leverages the advanced capabilities of Large Language Models (LLMs) to extract latent arguments from social media messaging. To demonstrate our approach, we apply our framework to contentious topics. We use two publicly available datasets: (1) the climate campaigns dataset of 14k Facebook ads with 25 themes and (2) the COVID-19 vaccine campaigns dataset of 9k Facebook ads with 14 themes. Additionally, we design a downstream task as stance prediction by leveraging talking points in climate debates. Furthermore, we analyze demographic targeting and the adaptation of messaging based on real-world events.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
