[ Back to EurekAlert! ] Public release date: 3-Jul-2013
[ | E-mail Share Share ]

Contact: Jyoti Madhusoodanan
jmadhusoodanan@plos.org
415-568-4545
Public Library of Science

Tweet timing tells bots, people and companies apart

Regardless of tweet content, tweet times can distinguish 3 kinds of tweeters

Tweet timing can differentiate individual, corporate and bot-controlled Twitter accounts independent of the language or content of a tweet, according to research published July 3 in the open access journal PLOS ONE by Aldo Faisal and Gabriela Tavares from Imperial College London, UK.

The researchers studied over 160,000 tweets from personal accounts held by individuals, 'managed' accounts belonging to large, well-known corporations and 'bot-controlled' accounts chosen from online lists of Twitter bots. Periods of high or low Twitter activity and the time between successive tweets could distinguish the three kinds of accounts from one another with approximately 83% accuracy. Based on the time since the last tweet, the researchers also developed a method to predict when a new tweet would be posted. For individual tweeters, predictions of a next tweet were equally accurate whether the method accounted for working hours or night-time in different time zones and when it did not account for different time-zones.

Perhaps not surprisingly, the study also found corporate-managed accounts tweeted more during work hours, personal accounts were more active in the afternoons and evenings, and bot-controlled accounts either tweeted at regular, constant intervals through the day, or had sudden bursts of activity at one or a few specific hours. Senior author Faisal concludes, "The identification and classification of specific types of users on Twitter can be useful for a variety of purposes, from the computational social sciences, focusing advertisement and political campaigns, to filtering spam, identity theft and malicious accounts."

###

Citation: Tavares G, Faisal A (2013) Scaling-Laws of Human Broadcast Communication Enable Distinction between Human, Corporate and Robot Twitter Users. PLOS ONE 8(6): e65774. doi:10.1371/journal.pone.0065774

Financial Disclosure: AAF acknowledges the support of the Human Frontiers in Science Program (grant number HFSP RGP0022/2012). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Competing Interest Statement: The authors have declared that no competing interests exist.

PLEASE LINK TO THE SCIENTIFIC ARTICLE IN ONLINE VERSIONS OF YOUR REPORT (URL goes live after the embargo ends): http://dx.plos.org/10.1371/journal.pone.0065774

Disclaimer: This press release refers to upcoming articles in PLOS ONE. The releases have been provided by the article authors and/or journal staff. Any opinions expressed in these are the personal views of the contributors, and do not necessarily represent the views or policies of PLOS. PLOS expressly disclaims any and all warranties and liability in connection with the information found in the release and article and your use of such information.

About PLOS ONE: PLOS ONE is the first journal of primary research from all areas of science to employ a combination of peer review and post-publication rating and commenting, to maximize the impact of every report it publishes. PLOS ONE is published by the Public Library of Science (PLOS), the open-access publisher whose goal is to make the world's scientific and medical literature a public resource.

All works published in PLOS ONE are Open Access. Everything is immediately available—to read, download, redistribute, include in databases and otherwise use—without cost to anyone, anywhere, subject only to the condition that the original authors and source are properly attributed. For more information about PLOS ONE relevant to journalists, bloggers and press officers, including details of our press release process and our embargo policy, see the everyONE blog at http://everyone.plos.org/media.



[ Back to EurekAlert! ] [ | E-mail Share Share ]

 


AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert! system.