From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context
Not on the map. Why?
Abstract (arXiv)
Reading and understanding the stories in the news is increasingly difficult. Reporting on stories evolves rapidly, politicized news venues offer different perspectives (and sometimes different facts), and misinformation is rampant. However, existing solutions merely aggregate an overwhelming amount of information from heterogenous sources, such as different news outlets, social media, and news bias rating agencies. We present NEWSSENSE, a novel sensemaking tool and reading interface designed to collect and integrate information from multiple news articles on a central topic, using a form of reference-free fact verification. NEWSSENSE augments a central, grounding article of the user's choice by linking it to related articles from different sources, providing inline highlights on how specific claims in the chosen article are either supported or contradicted by information from other articles. Using NEWSSENSE, users can seamlessly digest and cross-check multiple information sources without disturbing their natural reading flow. Our pilot study shows that NEWSSENSE has the potential to help users identify key information, verify the credibility of news articles, and explore different perspectives.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 44 references that are in the map. First posted on arXiv 6 Oct 2023.
Builds on
17 of 44 references.
References · 17
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
- 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
- 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
- 2023The science of fake newscited by 94
- 2022Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusterscited by 44
- 2021FRUIT: Faithfully Reflecting Updated Information in Textcited by 39
- 2020Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbolscited by 36
- 2022PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognitioncited by 29
5 more
- 2022Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literaturecited by 21
- 2021Media Cloud: Massive Open Source Collection of Global News on the Open Webcited by 20
- 2022NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challengecited by 20
- 2023The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfacescited by 9
- 2023LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interactioncited by 7
Built on by
Citing papers per year: 2023: 1.
1 paper.