Algorithm identifies top ten technology news trend setters

July 5, 2012
trend_business_insider

Top panel: Canonical trends during the first three weeks of October 2011. Steve Jobs’ death marks a strong peak in the first week of October. Bottom panel: The prediction obtained from the news feed http://businessinsider.com showed the highest prediction accuracy of this trend. (Credit: Felix Biessmann, Jens-Michalis Papaioannou, Mikio Braun, Andreas Harth)

Berlin Institute of Technology researchers studied the problem of trend-setting among news sites to determine which websites lead the news coverage and which ones merely follow, Technology Review Physics arXiv Blog reports.

They took a snapshot of the words generated by 96 technology news websites at any instant in time and compared them to the words generated by one of these websites at an earlier time.

This allowed them to calculate whether the content of this single website is a good predictor of future content on other websites and ranked them according to this metric.

One problem with this approach: it fails to differentiate between news generated by current events vs. original reporting. The difference: a big earthquake would get significant media coverage whether or not a particular website covered it, whereas a journalistic expose only gets coverage because of the legwork performed by a particular website.

This is related to another problem. One possibility is that the real trend setters may lie outside the group of 96 websites that these guys have monitored. For example, wires services such as Associated press and Reuters have a huge impact on the spread of news, and many of the bigger websites will have subscriptions to these services.

In this case, the trend setters are simply the ones who post the wires stories first or who post so many of them that they are first often enough to seem like trend setters.

Felix Biessmann, Jens-Michalis Papaioannou, Mikio Braun, Andreas Harth, Canonical Trends: Detecting Trend Setters in Web Data, arxiv.org/abs/1206.6388