How people's stance on a topic can be inferred from their online activity

How people’s stance on a topic can be inferred from their online activity
Figure showing the overlap between the three network interactions. The graph demonstrates the overlap between the accounts from three networks: (1) IN@: the list of accounts the user retweet for, reply to, or mention in their Home timeline, (2) PN@ the list of accounts mentioned in the tweets the user likes, and (3) CN_FR the list of followees/friends, i.e. accounts that the user follows. Credit: Aldayel & Dr. Magdy.

As proven by some recent extreme, controversial incidents, such as the Facebook and Cambridge Analytica scandal, social media can be a real goldmine for user information. In fact, most social researchers and analytics companies perceive social media as one of the most valuable resources for understanding public opinion and how individuals react to specific events.

With this in mind, research groups worldwide have been trying to develop tools to analyze social activity and automatically gather information about people's stances on specific topics. In a recent study, a group of researchers at the University of Edinburgh has set out to unveil some of the key factors that can help to determine the stances of individuals based on their social media profiles. Their paper, pre-published on arXiv, offers interesting new insight that could lead to the development of more advanced analytics tools.

"Stance prediction on social media plays a critical role in various analytics studies aimed at gauging the public opinion about various topics," Abeer Aldayel, one of the researchers who carried out the study, told TechXplore. "Lately, research studies have proposed various methods to model stance on social media. This study examines how people's stance on specific topics can be predicted from social media data using multiple online interaction signals. One of the main messages of our paper is that there is a real concern about user privacy. We hope that this study will be used to raise the awareness of individuals about their activity online and how it can be used."

To better understand online signals that can unveil a users' viewpoint on an event or topic, the researchers carried out an in-depth study on a popular stance-detection dataset, called the SemEval stance dataset. The SemEval stance dataset contains 4000 tweets on five political, social and religious topics.

Aldayel and her colleague Dr. Magdy analyzed the possible online factors for stance prediction on social media using three key interaction factors. The first factor, called 'interaction networks,' includes the accounts and web domains that users interact with or cite in their tweets. The second, called 'preference networks,' is composed of indirect interactions with other accounts and web domains contained within posts that users have liked. The third and final factor, called the 'connection network,' includes all accounts that follow the users and that the users follow.

"It's worth noting that these network factors are independent of having users expressing their stance toward the topic of analysis, since these factors depend on the social interactions and websites the users interacted with regardless of the content of their tweets," Aldayel explained.

The results gathered by the researchers suggest that the stance of a user can be detected by analyzing multiple aspects of her online activity, including posts, accounts they interact with or follow, websites they visit, and content they like. Interestingly, when analyzing only network features, the team achieved a similar performance to that of state-of-the-art models that focus on the textual content of posts alone. In addition, when combining network features (i.e., a user's online connections) and content features (i.e., a user's posts), the researchers achieved the highest stance detection performance reported to date, with an F-measure of 72.49 percent.

"Our study demonstrates explicitly, through the use of online network features, how one can predict the unexpressed stance through the use of different network interaction signals," Aldayel said. "Most key online features can sometimes be topically unrelated to the topic of analysis and yet have a high impact on deciding the stance. For instance, the interactions with accounts such as @goodreads and @SkyNews help in detecting the stance toward feminist movement (FM) and climate change (CC), respectively."

Most previous studies focusing on stance detection did not demonstrate how each of the online 'traces' left by users can help to detect their stance on a given matter. Aldayel and her colleagues, on the other hand, gathered specific insight about the significance of each action that an individual social media user performs online, including 'silent' ones such as following accounts or liking others' posts.

"Another interesting finding of our study is that the overall similarity between accounts in each of the three networks is minuscule," Aldayel added. "This means that users tend to interact and like contents from users outside their connection network and like tweets with links generally different from the domains they link in their tweets. This is a very interesting finding, as it raises further research questions about the reason of having a similar performance for the three networks in stance detection when they are mostly different."

In the future, the observations collected by Aldayel and her colleagues could inform the development of more advanced analytics tools to detect people's stances based on their social media interactions. Their work, however, also provides important information for social media users, highlighting how much can be inferred about their views and opinions based on their actions online.

"We are now working on designing a methodological framework that could help to protect user privacy on ," Aldayel said.


Explore further

New research helps visualise sentiment and stance in social media

More information: Your stance is exposed! Analysing possible factors for stance detection on social media. arXiv:1908.03146 [cs.SI]. arxiv.org/abs/1908.03146

© 2019 Science X Network

Citation: How people's stance on a topic can be inferred from their online activity (2019, August 27) retrieved 22 September 2019 from https://techxplore.com/news/2019-08-people-stance-topic-inferred-online.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
138 shares

Feedback to editors

User comments

Aug 27, 2019
Don't worry, when you post anything on the internet your anonymity is completely safe forever, even though nothing is ever erased. :-)
Oh, and I will sell you the brooklyn bridge real cheap.
BTW Laws that protect that privacy never get broken and will be enforced forever too. :-)

Aug 27, 2019
development of more advanced analytics tools to detect people's stances based on their social media interactions.

WHY ?

Aug 27, 2019
Because marketing wants to know everything about it's targets. Political organizations too.

Aug 27, 2019
I am making a good MONEY (500$ to 700$ / hr )online on my Ipad .Last month my pay check of nearly 30 k$.This online work is like draw straight-arrow and earn money.Do not go to office.I do not claim to be others,I just work.You will call yourself after doing this JOB,It's a REAL job.Will be very lucky to refer to this WEBSITE.Ihope,you can find something,Simply go to the below SITE.GOOD LUCK★★★★COPY THIS WEBSITE★★★★ .http://www.98steps.com


Here is an example of stupidity and arrogance. He WILL be tracked down and prosecuted once universal super quantum computers are developed and used to track people. There will be NO anonymity and this con artist will be found and prosecuted.

Aug 27, 2019
It's interesting how we grow wary of the surveillance that pervades our daily actions, but, we freely expose, for whatever surreptitious analysis , that which can most effectively be used to ruin us; our minds.

Aug 27, 2019
I think @antiALgoracle needs to have his brain reprogrammed. A climate denier deserves to have the con-artists BS side of his brain flushed and stuffed with rainbows, butterflies and unicorns and then exposed to real science on and facts on Anthropogenic Global Warming.

Aug 27, 2019
effectively be used to ruin us; our minds.


In what way will this ruin us and our minds? Unless we are criminals.

Aug 28, 2019
As stated, they are using our online interactions, including "silent" ones to develop a profile of our mindset. Are you truly that naive to think they do so, to target criminals? When there are billions to be picked from the ignorant.

Aug 28, 2019
I essentially started about a month and a 1/2 agone and i have gotten a couple of test for a whole of $2,200...this is the bestcall I made amidst pretty some time! "grateful to you for giving Maine this incredible possibility to profit from home. This similarly cash has changed my existence in such an excellent measure of courses, to the point that, bypass on you!".......GOOD LUCK Click this Below connect here...http://www.98steps.com

Here is an example of stupidity and arrogance. He WILL be tracked down and prosecuted once universal super quantum computers are developed and used to track people. There will be NO anonymity and this con artist will be found and prosecuted.

Aug 28, 2019
Here is an example of stupidity and arrogance. He WILL be tracked down and prosecuted once universal super quantum computers are developed and used to track people. There will be NO anonymity and this con artist will be found and prosecuted.

Why are you flaming about these posts? It isn't illegal to post ads and spam on forums. Chill dude

Aug 28, 2019
Here is an example of stupidity and arrogance. He WILL be tracked down and prosecuted once universal super quantum computers are developed and used to track people. There will be NO anonymity and this con artist will be found and prosecuted.


Why are you flaming about these posts? It isn't illegal to post ads and spam on forums. Chill dude


As far as I know free speech is not illegal. But, if you make statements that you know are blatantly false in order to trick someone out of their valuables that is illegal.
Plus I am not flaming or spamming, I am stating the facts.
We lose a little more of our privacy everyday, eventually it will all be gone. When that point comes there will be no hiding for the criminals and con artists. They are just not smart enough to realize what the consequences of their actions today will be in the near future.

Aug 28, 2019
Don't worry, when you post anything on the internet your anonymity is completely safe forever, even though nothing is ever erased. :-)


Except that is wrong, you can by law erase your data nowadays.

Aug 28, 2019
Don't worry, when you post anything on the internet your anonymity is completely safe forever, even though nothing is ever erased. :-)


Except that is wrong, you can by law erase your data nowadays.


How can you erase the data I or somebody else collected about you and I have stored on my multi terabyte drives at home?

Aug 30, 2019
How can you erase the data I or somebody else collected about you and I have stored on my multi terabyte drives at home?

And what kind of useful data could you have? Some random writings, maybe even an IP-address. Nothing that you can trace to the actual person behind the computer.

I think you have some misconceptions about data storage and how you trace people in the internet. Like if these add-spammers on this site are using public computers or prepaid mobile connection, there's actually close to zero possibility to trace them even if you had all the computing power in the universe in the future.

Aug 30, 2019
All I can say is quote "Advanced technology will seem like magic to us."
I am just guessing of course but your writing style is pretty much unique to you, therefore can be attributed to you. That includes how you emotionally feel about different subjects and even words. Once again just guessing but perhaps even a specific computer leaves a (for the present) unknown mark on anything it touches,. At one time typewriters were like that but it was quickly learned how to tell one from each other.

Aug 30, 2019
Even if you tracked all my post from this site and you could somehow magically connect these posts to a certain pc with IP-address, you still could not connect them to a single person.

I'm, for example, usually writing here during boring hours of work. So you could possibly pin point my working place but getting the information of exact pc through all these firewalls and security stuff should be difficult. Then getting the information who actually used this pc for work during certain period of time should be impossible.

Aug 30, 2019
should be impossible.

Of course it is impossible. Here are some of the few times I can remember hearing that word.
Fire
The Great Pyramid
Flying
Breaking Sound Barrier.
Black Holes
And one of the most enigmatic of all 'Spooky' Quantum Entanglement
etc.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more