Sunday, February 28, 2021
Home Lead Story Algorithm That Identifies Misogynist Content On Twitter

Algorithm That Identifies Misogynist Content On Twitter

This algorithm can detect abuse against women on Twitter

A team of researchers has developed a sophisticated algorithm to detect harmful and abusive posts against women on Twitter that cuts through the rabble of millions of tweets to identify misogynistic content. Online abuse targeting women, including threats of harm or sexual violence, has proliferated across all social media platforms.

Now, researchers from Queensland University of Technology (QUT) have developed a statistical model to help drum it out of the Twitter. The team mined a dataset of 1 million tweets then refined these by searching for those containing one of three abusive keywords – whore, slut, and rape.

The team’s model identified misogynistic content with 75 per cent accuracy, outperforming other methods that investigate similar aspects of social media language.

“At the moment, the onus is on the user to report abuse they receive. We hope our machine-learning solution can be adopted by social media platforms to automatically identify and report this content to protect women and other user groups online,” said Associate Professor Richi Nayak.

Twitter
Only 550 million people have ever sent a tweet. Unsplash

The key challenge in misogynistic tweet detection is understanding the context of a tweet. The complex and noisy nature of tweets makes it difficult.

On top of that, teaching a machine to understand natural language is one of the more complicated ends of data science as language changes and evolves constantly, and much of meaning depends on context and tone.

“So, we developed a text mining system where the algorithm learns the language as it goes, first by developing a base-level understanding then augmenting that knowledge with both tweet-specific and abusive language,” she noted.

The team implemented a deep learning algorithm called ‘Long Short-Term Memory with Transfer Learning’, which means that the machine could look back at its previous understanding of terminology and change the model as it goes, learning and developing its contextual and semantic understanding over time.”

Twitter
A day’s worth of tweets would fill a 10 million page book. Unsplash

“Take the phrase ‘get back to the kitchen’ as an example – devoid of context of structural inequality, a machine’s literal interpretation could miss the misogynistic meaning,” Nayak said.

“But seen with the understanding of what constitutes abusive or misogynistic language, it can be identified as a misogynistic tweet”. Other methods based on word distribution or occurrence patterns identify abusive or misogynistic terminology, but the presence of a word by itself doesn’t necessarily correlate with intent, said the paper, published in the journal Springer Nature.

Also Read: I Really Enjoyed Blind Items Until It Became About Me: Masaba Gupta

“Once we had refined the 1 million twitter tweets to 5,000, those tweets were then categorised as misogynistic or not based on context and intent, and were input to the machine learning classifier, which used these labelled samples to begin to build its classification model,” Nayak informed.

The team hoped the research could translate into platform-level policy that would see Twitter, for example, remove any tweets identified by the algorithm as misogynistic.

“This modelling could also be expanded upon and used in other contexts in the future, such as identifying racism, homophobia, or abuse toward people with disabilities,” Nayak said. (IANS)

STAY CONNECTED

19,120FansLike
362FollowersFollow
1,773FollowersFollow

Most Popular

With Current Climate Pledges, Global Emissions in 2030 Will Only Be 1% Lower

A United Nations Climate Change report has warned that with all current climate pledges, global emissions in 2030 will only be one per cent...

Does B-Town Link Women’s Beauty With Fair Skin? AI Analysis Reveals Truth!

For Bollywood, beautiful women have fair skin, according to an Artificial Intelligence (AI)-based computer analysis which reveals that conception of beauty has remained consistent...

Smartphones May Help To Detect Early-Warning Signs of Glaucoma

Smartphones, often blamed for eye strains and other problems, can also come to your aid as researchers have found that these devices could be...

Google To Test AI Technology For Boosting Maternal Health

Researchers from Google Research and IIT Madras have designed an AI technology that could provide an indication of women who are at risk of...

Journey of Jasprit Bumrah Towards Becoming a World-Class Pace Bowler From Scratch!

When Jasprit Bumrah started troubling young batsmen with pace generated by his quick arm action and short run-up at his school's cricket academy, a...

Are Good Bacteria Getting Viral Infections?

Researchers have developed a test to determine if bacteria are sick, similar to the one used to test humans for Covid-19. According to the...

Aerobic Exercise May Help Slow Memory Loss For Older Adults

Aerobic exercise may help slow memory loss for older adults living with Alzheimer's dementia, says new research. The findings indicate that a six-month aerobic...

Bacteria To Defeat Infections Afflicting People With Cystic Fibrosis

Researchers have discovered a slimy strategy used by bacteria to defeat antibiotics and other drugs used to combat infections afflicting people with cystic fibrosis. Cystic...

Recent Comments