The Centre Malaysia has recently launched a tracker designed to monitor hate speech on Malaysian social media, through the webpage #TrackerBenci.
The tracker is an early version of the artificial intelligence (AI) programme devised to filter through and tag Malaysian online discussions which contain hateful speech.
Speaking at the tracker’s virtual launch yesterday (14 January), the Centre’s chief executive officer, Dr Khairil Ahmad said he hopes that #TrackerBenci can help policymakers and members of the public recognise and better understand the trends and themes of online hate speech in Malaysia.
Researcher Tham Jia Vern said that #TrackerBenci is designed to help fill the gaps in current social media hate speech tracking systems, which often heavily rely on undertrained human moderators.
“The lack of investment in locally-trained and diverse panels of moderators leaves a gap in understanding what is hateful in certain cultural contexts,” she said.
She added that these moderators need to read through a massive amount of online content daily and this makes a human-only system unreliable in the long term.
She then said the #TrackerBenci will allow human moderators to more effectively detect and classify harmful online content.
According to its website, #TrackerBenci V1.0 is still in early stages of development and has its limitations. The tracker can only process Twitter’s tweets at the moment and is also not yet able to fully comprehend all forms of hate speech. This is largely due to time and manpower limit researchers had to train the AI.
Nonetheless, The Centre hopes to improve #TrackerBenci’s performance over time and has also allowed users to further improve the AI by informing it when users find the AI to be wrong about what is hateful.
Tham said training the AI involved showing it some 20,000 tweets, and then teaching it to differentiate between the tweets as either “hateful”, “a snarky reply towards hateful sentiments”, or “not hateful or irrelevant to the Malaysian context”.
These tweets were chosen by a team of six researchers, led by Tham and Nelleita Omar, who went through the social media site for posts they curated as relevant to Malaysian society.
Following this, the AI will be trained to determine the intensity of the “hateful” tweets, by identifying them as either an “insult” or “threat to marginalisation”.
Apart from that, it is also thought how to distinguish hateful tweets by categories and themes such as “violent threat”, “increases intergroup tension”, “sexism”, “related to one’s religion or religious beliefs”, and “perpetuates a negative stereotype”.
What do you think about this initiative? Share your thoughts!