ANU research uncovers bot influence in 2016 US Election

2016 US Presidential Election candidates Donald Trump and Hillary Clinton. (Source:
Monday 17 September 2018

New algorithms developed at The Australian National University have found bots on Twitter were on average two-and-a-half times more influential than humans during the first US Presidential debate in 2016.

The team of researchers, co-led by Dr Timothy Graham of ANU School of Sociology and ANU Research School of Computer Science, and Dr Marian-Andrei Rizoiu from ANU College of Engineering and Computer Science, analysed 6.4 million tweets generating over a period before, during, and after the debate between Donald Trump and Hillary Clinton on September 16 2016.

The team spent months collecting data to determine if the 1.5 million user accounts active during the debate were actually humans or not.

They classified four categories: Bots (and bot-like), Humans, Deleted Accounts (more likely to be bots) and Protected Accounts (more likely to be humans).

“We found only 4.8 per cent of the users were clearly bots,” said Dr Graham.

“This figure was really underwhelming given we’ve seen other reports and studies claiming 20-30 per cent of Twitter accounts were bots. We suggest those figures were inflated by biases in the methodologies, which our work exposed”.

“It startling to find those 4.8 per cent of bots were on average two-and-a-half times more influential than humans. And because of the way bots – which we found were more pro-Republican – attach themselves to influential human users, they were more successful at getting real users to retweet and engage with their content.”

Behind the success of the ANU team’s finding were several new algorithms and measures they developed, capable of analysing the Twitter cascade effect better than the current data provided by Twitter allows.

“Previous studies tend to focus on the numbers of retweets provided by Twitter data, but what we are interested in is what – or who - makes a tweet go viral via cascades of retweets, and how much influence these actors have over the retweet cascades,” said Dr Graham.

“We devised an influence measure which we could apply over all the millions and millions of possible unfoldings of these retweet diffusions, as well as a separate measure of political polarisation and engagement which we used to determine the partisanship of a tweet.

“We live in really interesting times where information warfare is now the state of play for politics nationally and internationally, so more research like this can help us understand if democracies are functioning the way we intend.

“Of course our sample is very small – just 90 minutes of Twitter activity – and much greater-sized studies are required before we could determine if the aggregate meant that bots won Trump the election, for example. However, whilst it’s a small snapshot in time, the results are robust,” said Dr Graham.

It’s expected the methods developed by the team will prove useful going forward to the broader research community, allowing them to more accurately and efficiently analyse cascades from Twitter data. The code is available online and is open source:

The study is available here:



About the ANU School of Sociology

The discipline of Sociology is one of the academic pillars on which The Australian National University was built. The ANU School of Sociology has an exciting program of research and teaching that combines the theoretical and applied dimensions of the discipline. Our research and teaching ethos is orientated to the critical analysis of social transformations; publically-engaged in its aspirations and impact, and dedicated to examining inequality in its various manifestations. The ANU is ranked 1st in Australia and 13th in the world for Sociology in the 2018 QS World Subject rankings. Follow ANU School of Sociology on Facebook and Twitter.

Search this site only

Updated:  17 September 2018/Responsible Officer:  CASS Marketing & Communications/Page Contact:  CASS Marketing & Communications