What makes people click? Researchers analyze online news preferences

Jun 18, 2013

A new study has analysed tens of thousands of articles available to readers of online news and created a model to find out 'what makes people click'.

The researchers developed a model of "news appeal" based on the words contained in an article's title and text intro, which is what a reader uses when they choose to click on a story.

The study by academics at the University of Bristol's Intelligent Systems Laboratory is published in a series of publications.

The aim of the study was to model the reading preferences for the audiences of 14 online news outlets using machine learning techniques. The models, describing the appeal of an article to each , were developed by linear functions of word frequencies. The models compared articles that became "most popular" on a given day in a given outlet with articles that did not.

The research, led by Nello Cristianini, Professor of , identified the most attractive keywords, as well as the least attractive ones, and explained the choices readers made.

The team created a model for each user group they had data on, including the 's online news, and Australian newspapers.

After scoring articles by reader preferences, the researchers then ranked the articles by their appeal, and studied what might explain the choices made by online readers.

Professor Cristianini, speaking about the research, said: "We found significant inverse correlations between the appeal to users and the amount of attention devoted to public affairs.

This video is not supported by your browser at this time.

"People are put off by public affairs and attracted by entertainment, crime, and other non-public affairs topics."

The researchers examined millions of article pairs, collected over nearly eighteen months. The models analysed user choices, choices were then used to compare both the audiences and the contents of various outlets.

The researchers found that there is a significant between the demographic profiles of audiences and their preferences. They also found that content appeal is related both to writing style - with more sentimentally charged language being preferred, and to content with "" topics, such as "finance" and "politics", being less preferred.

Explore further: Engineer leads effort to develop computer systems that can see better than humans

More information: Paper: Modelling and Explaining Online News Preferences, Elena Hensinger, Ilias Flaounas, Nello Cristianini, In Collection: Pattern Recognition - Applications and Methods, Springer Berlin Heidelberg.

mediapatterns.enm.bris.ac.uk/WhatReadersWant
www.see-a-pattern.org/sites/de… 0Media%20Content.pdf

add to favorites email to friend print save as pdf

Related Stories

Scientists analyze millions of news articles

Nov 26, 2012

Researchers in the UK have used artificial intelligence algorithms to analyze 2.5 million articles from 498 different English-language online news outlets over ten months.

Researchers examine the rise of liveblogging

Nov 26, 2012

Dr Neil Thurman and Anna Walters, from City University London's Journalism School, have just published a study into liveblogging, which is becoming the default format for covering major breaking news stories, sports events, ...

Scientists map what factors influence the news agenda

Dec 08, 2010

Computer scientists have analysed over a million news articles in 22 languages to pinpoint what factors, such as the Eurovision song contest, influence and shape the news agenda in 27 EU countries. This is the first large-scale ...

Foreign Affairs goes online

Mar 12, 2009

Foreign Affairs, the magazine which has hosted articles about international affairs by US foreign policy luminaries for decades, is going online.

Recommended for you

Hacking Gmail with 92 percent success

7 hours ago

(Phys.org) —A team of researchers, including an assistant professor at the University of California, Riverside Bourns College of Engineering, have identified a weakness believed to exist in Android, Windows ...

User comments : 0