Highlighting disputed claims on the web

Abstract

We describe Dispute Finder, a browser extension that alerts a user when information they read online is disputed by a source that they might trust. Dispute Finder examines the text on the page that the user is browsing and highlights any phrases that resemble known disputed claims. If a user clicks on a highlighted phrase then Dispute Finder shows them a list of articles that support other points of view.Dispute Finder builds a database of known disputed claims by crawling web sites that already maintain lists of disputed claims, and by allowing users to enter claims that they believe are disputed. Dispute Finder identifies snippets that make known disputed claims by running a simple textual entailment algorithm inside the browser extension, referring to a cached local copy of the claim database.In this paper, we explain the design of Dispute Finder, and the trade-offs between the various design decisions that we explored.

Integrating on-demand fact-checking with public dialogue

“…Systems like Dispute Finder [12] and Hypothes.is annotate claims at a sentence-by-sentence granularity at the point of consumption as users browse the web. This line of system building focuses on helping individuals be more responsible consumers of information they encounter, rather than grounding an ongoing discussion.…”

Fact checking and analyzing the web

“…However, the complexity of knowledge found in open data sources requires powerful, flexible ways for users to retrieve, analyze and understand the data, as well as produce and share complex annotations on the analyzed documents. Existing tools let users annotate Web pages directly from their browser, e.g., Dispute Finder [6] helps distributed users annotate pages to uncover disputed content or use it as supporting evidence for other claims. Closer to our work, DocumentCloud [7] provides an online service for newsrooms, where users create collections of documents, analyze and annotate them, share annotations, etc.…”

The economy of attention in the age of (mis)information

“…Since unsubstantiated claims are proliferating over the Internet, what could happen if they were used as the basis for policy making? Nonetheless, several tools have been recently designed to help users disambiguate misinformation and false news [36,37]. On the other hand, basic questions remain on how the quality of (mis)information affects the economy of attention processes, concerning, for example, the virality of information, its lifespan and the consumption patterns.…”