Udayavni Special

New AI system to help counter online hate speech


Team Udayavani, Jan 13, 2020, 2:43 PM IST

New York: Scientists have developed an artificial intelligence (AI) system that could help counter hate speech directed at disenfranchised minorities such as the Rohingya community.

The system developed by researchers from Carnegie Mellon University in the US can rapidly analyse thousands of comments on social media, and identify the fraction that defend or sympathise with voiceless groups.

Human social media moderators, who could not possibly manually sift through so many comments, would then have the option to highlight this “help speech” in comment sections, the researchers said.

“Even if there’s lots of hateful content, we can still find positive comments,” said Ashiqur R KhudaBukhsh, a post-doctoral researcher at Carnegie Mellon University’s Language Technologies Institute (LTI).

Finding and highlighting these positive comments might do as much to make the internet a safer, healthier place as would detecting and eliminating hostile content or banning the trolls responsible, the researchers said.

The Rohingyas, who began fleeing Myanamar in 2017 to avoid ethnic cleansing, are largely defenseless against online hate speech, they said.

Many of them have limited proficiency in global languages such as English, and they have little access to the internet.

Most are too busy trying to stay alive to spend much time posting their own content, KhudaBukhsh said.

To find relevant help speech, the researchers used their technique to search more than a quarter of a million comments from YouTube in what they believe is the first AI-focused analysis of the Rohingya refugee crisis.

The ability to analyse such large quantities of text for content and opinion is possible because of recent major improvements in language models, said Jaime Carbonell, LTI director and a co-author on the study.

These models learn from examples so they can predict what words are likely to occur in a given sequence, and help machines understand what speakers and writers are trying to say.

However, the researchers developed a further innovation that made it possible to apply these models to short social media texts in South Asia.

Short bits of text, often with spelling and grammar mistakes, are difficult for machines to interpret.

It’s even harder in South Asian countries, where people may speak several languages and tend to “code switch,” combining bits of different languages and even different writing systems in the same statement.

Existing machine learning methods create representations of words, or word embeddings, so that all words with a similar meaning are represented in the same way, the researchers explained.

This technique makes it possible to compute the proximity of a word to others in a comment or post.

To extend this technique to the challenging texts of South Asia, the team obtained new embeddings that revealed language groupings or clusters.

This language identification technique worked as well or better than commercially available solutions, the researchers said.

This innovation has become an enabling technology for computational analyses of social media in that region, Carbonell noted.

Samplings of the YouTube comments showed about 10 per cent of the comments were positive.

When the researchers used their method to search for help speech in the larger dataset, the results were 88 per cent positive, indicating that the method could substantially reduce the manual effort necessary to find them, KhudaBukhsh said.

The researchers presented their findings at the Association for the Advancement of Artificial Intelligence annual conference in New York City, US.

Top News

Notice was issued to Kozhikode airport in July 2019 over critical safety lapses

Yediyurappa seeks two acres land in Ayodhya from his UP counterpart for K’taka pilgrims

Rahul slams govt over ASHA workers’ strike

Indian consulate in Dubai to remain open today to share info related to Air India plane crash

Kozhikode Air Crash brings back memories of Mangaluru Air Crash: Why tabletop runways are dangerous?

61,537 new COVID cases in India, 933 deaths

Karnataka to start online liquor sales, new MSIL shops to shore up its treasury



Related Articles More

27 human genes renamed to stop Microsoft Excel from misreading them as dates

Google plans to launch foldable Pixel phone in 2021

Twitter reveals security flaw that may have exposed Android users’ direct messages

Trump signs executive orders banning TikTok, Wechat

Scientists found Saturn-like planet orbiting small, cool star

MUST WATCH

pick-up vehicle was hit by a flood and washed away in Bajatur village | Udayavani

What Happens If All The Bees Die? | Udayavani

Horticulture in 75 cents land | Success Story of Padmanabha | Udayavani

Shankar Suvarna | Interview with successful Dairy Farmer | Agriculture

Rangayya Naik | How to Nurture a Child | Udayavani

Latest Additions

Why is Karnataka the largest producer of Mulberry silk?

Dharwad: Death body of 8-year-old flash flood victim recovered

Bantwal: Overflowing Netravathi inundates low lying areas

Uppinangadi: Pick-up taken for wash swept away by floodwaters

National Handloom Day: Know about the Sarees of Karnataka that have obtained Geographical Indication (GI)

Thanks for visiting Udayavani

You seem to have an Ad Blocker on.
To continue reading, please turn it off or whitelist Udayavani.