The largest ever study into online abuse against women has found that one in 10 tweets mentioning black women politicians and journalists were abusive or problematic.

They were part of a sample analysed by Amnesty International as part of a study into abuse against women on Twitter conducted with Element AI, a global artificial intelligence software product company.

More than 6,500 volunteers from 150 countries signed up to take part in the crowdsourcing project, designed to process large-scale data about online abuse.

Volunteers sorted through 228,000 tweets sent to 778 women politicians and journalists in the UK and USA in 2017.

Element AI calculated that 1.1 million abusive or problematic tweets were sent to the women in the study across the year - or one every 30 seconds on average.

Black women were disproportionately targeted, being 84% more likely than white women to be mentioned in abusive or problematic tweets.

Some 7.1% of tweets sent to the women in the study were problematic or abusive.

Women of colour, (black, Asian, Latinx and mixed-race women) were 34% more likely to be mentioned in abusive or problematic tweets than white women.

Online abuse against women also cuts across the political spectrum.

Politicians and journalists faced similar levels of online abuse and it was observed both liberals and conservatives alike, as well as left and right leaning media organisations, were affected.

File photo

Milena Marin is senior advisor for tactical research at Amnesty International.

"With the help of technical experts and thousands of volunteers, we have built the world's largest crowdsourced dataset about online abuse against women.

"Troll Patrol means we have the data to back up what women have long been telling us - that Twitter is a place where racism, misogyny and homophobia are allowed to flourish basically unchecked.

"We found that, although abuse is targeted at women across the political spectrum, women of colour were much more likely to be impacted, and black women are disproportionately targeted.

"Twitter's failure to crack down on this problem means it is contributing to the silencing of already marginalised voices."

Element AI used the data gathered to develop a machine learning model of an app, which attempts to automatically detect abusive tweets.

It is making its model available to try out for three weeks, to demonstrate the potential and current limitations of AI technology in this field.

Politicians included in the sample were from across the US and UK political spectrums.

The journalists included were from a range of publications including The Daily Mail, The New York Times, Guardian, The Sun, GalDem, Pink News and Breitbart.

Troll Patrol volunteers collectively dedicated an incredible 2,500 hours analysing tweets: the equivalent of someone working full-time for 1.5 years.