SciLens: A Platform for Real-Time Evaluation of News Articles

Many societies suffer from scientific illiteracy, which refers to lack of knowledge about basic scientific facts and methods. Therefore, it becomes imperative for the scientific community to help foster conditions to improve the public understanding, measuring, and advancement of science. Mass media can play a significant role in improving scientific literacy. However, the main challenge is to present scientific findings in the form of news by using accessible language for a broad audience, and yet accurately representing the research findings, methods, and limitations. Often, portrayals of science fail to achieve that balance and do not communicate scientific knowledge effectively. Worse, many news articles carry misinformation or fake content.

We present SciLens, a method for evaluating the quality of scientific news articles. The framework, which bridges the gap between traditional and computational journalism, automatically extracts quality indicators about articles to evaluate them.

Our system evaluates the following parameters:

  • Content of a news article, where we introduce a method to use quotes appearing in it as quality indicators
  • Relationship of a news article with the scientific literature, where we introduce content-based and graph-based similarity methods
  • Social media reactions to the article, where we introduce a method to interpret their stance (supporting, commenting, contradicting, or questioning) as quality signals

These indicators are combined with expert reviews in a unified environment. This augmented view of news articles has helped the platform users to have a better consensus about the quality of the underlying articles. The SciLens News Platform is built in a distributed and robust fashion, handling thousands of news articles daily.

References:

[1] Panayiotis Smeros, Carlos Castillo, and Karl Aberer. 2019. SciLens: Evaluating the Quality of Scientific News Articles Using Social Media and Scientific Literature Indicators. In The World Wide Web Conference (WWW ’19). Association for Computing Machinery, New York, NY, USA, 1747–1758. DOI: http://doi.org/10.1145/3308558.3313657

[2] http://scilens.epfl.ch