Skip to Content
Uncategorized

This Is What Controversies Look Like in the Twittersphere

A new way of analyzing disagreement on social media reveals that arguments in the Twittersphere look like fireworks.

Many a controversy has raged on social media platforms such as Twitter. Some last for weeks or months, others blow themselves in an afternoon. And yet most go unnoticed by most people. That would change if there was a reliable way of spotting controversies in the Twitterstream in real time.

That could happen thanks to the work of Kiran Garimella and pals at Aalto University in Finland. These guys have found a way to spot the characteristics of a controversy in a collection of tweets and distinguish this from a noncontroversial conversation.

Various researchers have studied controversies on Twitter but these have all focused on preidentified arguments, whereas Garimella and co want to spot them in the first place. Their key idea is that the structure of conversations that involve controversy are different from those that are benign.

And they think this structure can be spotted by studying various properties of the conversation, such as the network of connections between those involved in a topic; the structure of endorsements, who agrees with whom; and the sentiment of the discussion, whether positive and negative.

They test this idea by first studying ten conversations associated with hashtags that are known to be controversial and ten that are known to be benign. Garimella and co map out the structure of these discussion by looking at the networks of retweets, follows, keywords and combinations of these.

These networks allow further study. In particular, the retweet and follow graphs reveal clusters within the networks that might indicate a form of polarization among the users. Sure enough, the networks associated with controversial topics can be clearly partitioned into groups on either side of the debate.

These images (shown above) are beautiful representations of controversy, like fireworks in the Twittersphere. The most controversial are a, b, e, and f which are associated with #beefban, a discussion about the banning of beef in India, and with #russia_march, about protests in Russia.

The others are less controversial: c and g are associated with #sxsw, the tag for the South by South West festival of creativity, and d and h with #germanwings that involved conversations about a dramatic air crash last year but which were not generally controversial.

In all cases, the images clearly show the polarization, or lack of, in the debate.

Garimella and co developed tools for measuring the size of this polarization and hence the controversy. They go on to test these tools on a number of ground truth datasets to see how well they describe controversy.

In general, their methods spot controversy better than existing tools but are by no means perfect. So further work is clearly needed.

But who’d have guessed that controversial topics could look so striking? With tools like this, all Garimella and co have to do is watch the Twitterstream and wait for the fireworks to begin.

Ref: arxiv.org/abs/1507.05224 : Quantifying Controversy in Social Media

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.