As many online publishers continue to produce this kind of content, demand is growing for ways to flag it and make it easier for online readers to access more in-depth, quality articles instead.
DataRobot has developed a highly accurate predictive model for flagging which articles might be clickbait. Their algorithm relies heavily on the detected virality of the webpage — which strongly correlates with this type of writing. Webz.io supplied DataRobot with the metadata they need to analyze online articles, extracting titles, texts, publishers, authors, sentiments, and level of virality.
Using Webz.io’s data, DataRobot has improved the predictive accuracy of its algorithm and identified certain words, phrases, and attributes (such as a high number of external links) that are more likely to drive viral news.
With these insights, DataRobot has been able to demonstrate to clients that there are alternative ways to drive viral content rather than simply using clickbait headlines.
Discover how DataRobot used Webz.io’s web data feeds to identify and help drive viral content without using clickbait headlines
“Using Webz.io’s data, DataRobot discovered that words like finance, trump, democrats, and children were more likely to be found in articles that went viral.”
DataRobot is the category creator and leading provider of automated machine learning organizations. Organizations worldwide use DataRobot to empower the teams they already have in place to rapidly build and deploy machine learning models.
Webz.io is the leading provider of machine-defined web data. It transforms the vast pool of web data from across the open and dark web into structured web data feeds, ready for machines to consume. Using Webz.io’s data, enterprises, developers, and analysts can now unlock the raw potential of web data.