Dominant viewpoints emerge quickly on Twitter and soon become difficult to change, according to new study.
The results will help shape how politician run social media campaigns and will influence the way companies market goods and services.
A group of researchers asked themselves the question: How exactly does Twitter, with 241 million users tweeting 500 million messages daily, shape public opinion?
To start, they gathered about 6 million tweets over six months in 2011.
They ran these messages through computer algorithms which sorted them by topic (“iPhone 4” or “blackberry,” for example), and they analysed the underlying sentiments of the authors as they evolved over time.
The work, published today in the journal Chaos, reveals several surprises, said Fei Xiong, a lecturer at Beijing Jiaotong University who gathered and analysed the data with Professor Yun Liu.
Opinion on Twitter often evolves rapidly and levels off quickly into an ordered state in which one opinion remains dominant.
This consensus is often driven by the endorsements of larger and larger groups, which tend to have the most influence.
When dominant opinions emerge, however, they tend not to achieve complete consensus.
And when Twitter users who hold minority views are faced with overwhelming opposition, they are still not likely to change their opinions.
Since public opinion levels off and evolves into an ordered state within a short time, small advantages of one opinion in the early stages can turn into a bigger advantage during the evolution of public opinion, Xiong said.
“Once public opinion stabilises, it’s difficult to change,” he said.
The work also revealed that Twitter users overall are more likely to work to change the opinions of others than to admit to changes of their own.
Xiong says political candidates and large companies may benefit from applying this work toward developing “network applications” that would move beyond simply collecting and analysing opinions and allow them to develop and test hypotheses about what really works.
“By focusing on a network application, candidates or companies can analyse the characteristics and behaviour patterns of their supporters and protesters to explore whether the measures they take can influence public opinion and which opinion may succeed,” Xiong said.
The researchers downloaded tweets for this study using Twitter’s open API [application programming interface] to get a random sampling of all data, which was then narrowed based on topic.
The article, ‘Opinion Formation on Social Media: An Empirical Approach’, is published in Chaos: An Interdisciplinary Journal of Nonlinear Science.