June 14, 2013
Rich Don’t Get Richer In Terms Of Internet Traffic, Study Finds
Lee Rannals for redOrbit.com — Your Universe Online
Chinese scientists from City University of Hong Kong and the School of Management at Beijing Normal University performed a study to determine the impact of a website based on the interaction between its users with the entire Web. Their findings could provide helpful insights to advertisers.
Past studies analyzed hyperlinks and individual browsing records, but they have failed to look into information on more internet-wide collective browsing behaviors. In order to understand these complex interactions between websites, researchers needed to analyze the transportation of traffic between websites, or clickstreams.
Scientists in the current study analyzed the clickstream networks for 1,000 of the most popular websites. They used models of clickstream networks based on "Markov matrices." This is a matrix in mathematics used to describe the transitions of a Markov chain, which is a system that undergoes transitions from one state to another. The researchers also validated their findings through network flow analysis by tracking users' movements on the Web.
"To construct clickstream networks we prepared three lists of seed site[s]. For convenience we simply called these lists 'list1,' 'list2,' and 'list3,' and the constructed networks 'w1,' 'w2,' and 'w3'," the researchers wrote in the journal. "By analyzing the circulation of the collective attention we discover the scaling relationship between the impact of sites and their traffic," the authors added.
The team found the accessibility of websites in the clickstream networks increases slower than the level of traffic for the sites studied. They revealed the Web is not solely dominated by a few hubs. Instead, relatively small websites have a greater chance of acquiring popularity than larger ones.
According to the findings, clickstreams do not follow a "rich-get-richer" paradigm in which the larger a site gets, the more it becomes a magnet for traffic, taking away users from smaller sites. The researchers actually say user navigation increases the inequality of traffic among websites.
Marketers could use this study because it offers a more precise calculation of the impact of sites for determining advertising rates based on the circulation of clickstreams, instead of just traffic.