Sunday October 21, 2018
Home India Indian Origin...

Indian Origin scientist’s team predict outcome of tweets

0
//
139
Republish
Reprint

Arizona: A team of researchers including Indian origin scientist developed a method which will be able to predict with the accuracy of the seventy per cent the outcome of tweets. It will predict if the tweets that are part of an ongoing debate or a movement, whether they will become part of a later and even violent protest later.

The study from researchers at Arizona State University, Texas A&M University and Yahoo and funded in part by the US Military’s Office of Naval Research looked at 2,686 Twitter posts to create a system that reliably spots future online protesters.

“The ways in which protest-related events affect a person are not observable, resulting in a lack of knowledge of factors operating at that time causing his next post to be a declaration of protest,” wrote lead researchers Suhas Ranganath, Fred Morstatter and colleagues from Arizona State University.

“A user is subject to various types of influence in his past and many of them are in conflict with each other. This may lead to ambiguities on whether his posts will contain declarations of protest in the future,” they added.

The paper titled “Predicting Online Protest Participation of Social Media Users” was published as part of the proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) conference in Phoenix, Arizona, recently.

To reach this conclusion, the team observed tweets regarding the Nigerian general election in 2015, which eventually sparked widespread protests due to irregularities and militant violence.

The team employed Brownian motion theory to design the formula — a theory that is usually employed to track the movement of particles as well as model stock market fluctuations and other highly complicated systems, www.nextgov.com reported.

The findings can also be applied to scenarios when the complete spreading mechanism is not known like in the case of terror-related tweets.

“In these scenarios, we go into the history of the user and see who have tried to interact with him and the nature of the interactions. So the individual user’s response to the attempt of organizations like IS (Islamic State) to interact with him can be modelled using the proposed method,” the team told Defense One website.

The researchers, however, caution that predicting a protest tweet is different than predicting the moment of actual radicalisation

The paper is part of a $750,000 grant from the Office of Naval Research to study how crisis manifests itself in social media.(IANS)

Click here for reuse options!
Copyright 2016 NewsGram

Next Story

Microblogging Site Twitter Releases Tweets Linked to Russia, Iran

"We may also release incremental additions to existing datasets if we believe the additional information could materially impact research findings," Twitter said

0
Twitter
Twitter releases data linked to Russian, Iranian info campaigns. Pixabay

With the goal of improving understanding of how foreign influence campings operate on Twitter, the microblogging site has now released massive datasets of accounts linked to potential influence campaigns originating in Russia and Iran.

These large datasets released this week comprise 3,841 accounts affiliated with the Internet Research Agency (IRA), originating in Russia, and 770 other accounts, potentially originating in Iran.

Totalling over 360 gigabytes – including more than 10 million Tweets and more than 2 million images, GIFs, videos, and Periscope broadcasts ?the data store provides a picture of how state-sponsored agencies have used the Twitter platform, technology news website Ars Technica reported on Friday.

IRA allegedly ran information campaigns on several social media platforms to undermine the political process in the 2016 US presidential election.

TWitter
The logo for Twitter is displayed above a trading post on the floor of the New York Stock Exchange. vOA

With Twitter coming under scrutiny for its failure to stop the spread of misinformation during the election, the microblogging site, earlier this year, committed to the US Congress and the public to provide regular updates and information regarding its investigation into foreign interference in political conversations on Twitter.

Since that time, Twitter has shared examples of these types of content posted on Twitter by IRA and provided the public with a direct notice if they interacted with these accounts.

In August this year, Twitter also disclosed details of another attempted influence campaign it identified as potentially located within Iran.

The datasets released this week are aimed at enabling independent academic research and investigation into the nature of foreign influence campaigns, Twitter said.

Twitter
Twitter on a smartphone device. Pixabay

“We are committed to understanding how bad-faith actors use our services. We will continue to proactively combat nefarious attempts to undermine the integrity of Twitter, while partnering with civil society, government, our industry peers, and researchers to improve our collective understanding of coordinated attempts to interfere in the public conversation,” Twitter said.

A preliminary look at the data by Ars Technica revealed that a common tactic used by the IRA was to create “local news” accounts for major US cities, seeding them with posts linking to local news outlets.

The accounts, such as “Atlanta Online,” “Baltimore Online,” “Baton Rouge Voice,” “Chicago Daily News,” and “Dallas Top News” would also include tweet-length news headlines with no link, the report said.

Also Read- Habitability Of Surrounding Planets Affected By Super Flares Of Red Dwarfs: NASA

Twitter said if it identifies additional attempted information operations on Twitter in the future, it will release similar datasets in a timely fashion after completing its investigations.

“We may also release incremental additions to existing datasets if we believe the additional information could materially impact research findings,” Twitter said. (IANS)