BAITRADAR – A clickbait detection for YouTube
19 May 2022
We've all been tricked into clicking on a sensational headline, only to realise that there was nothing there to begin with. Some of us end up wasting precious time waiting to see the content we had hoped to see. Misleading headlines are a huge problem these days. Their only aim is to attract clicks which will encourage traffic.
The rising popularity of YouTube has led to the clickbait problem, which provokes users to click on videos by publishing attractive titles and thumbnails. It is a waste of time, but the impact is also more severe when it exposes minors to age-inappropriate or ill-intended content. So, it cannot guarantee a safe surfing environment, especially for kids.
To detect whether the video is clickbait or not
A team of researchers from the School of Information Technology, Monash University Malaysia, have created a system that detects when a video is clickbait and alerts users in real-time — BaitRadar.
"Our research uses a multi-modal Deep Learning architecture as a back-end artificial intelligence (AI) engine to analyse the title, tags, thumbnail, comments, audio transcript and statistics. We have packaged the model into a browser extension for Chromium-based browsers (Google chrome, edge, brave and others). The browser extension will run the detector in the background and update the user interface (UI) to show the detection result when the user loads the video," said Dr Lim Chern Hong.
The research significantly impacts Youtube users (1 billion hours of video watched every day) as it aims to improve the clickbait detection problem on that platform. It can prevent users from wasting time watching irrelevant videos. Social media companies can also use this to avoid recommending clickbait videos to their customers.
"Furthermore, since computers can process text-based data more efficiently than video, our proposed method can get a general idea of the whole video in seconds," Dr Lim added.
The main novelty of the research product is the audio transcript to analyse the content of the Youtube video. Combining the title, tags, thumbnail, comments, audio transcript and statistics using a Multi-modal Deep Learning architecture can detect whether a video is clickbait or not.
The research began with a Final Year Project group in the undergraduate program, Bachelor of Computer Science. With support from the university, technically and financially, the research team managed to sustain and drive the research to higher achievements. Also involved in the project were Associate Professor Dr Wong Kok Sheik and student Bhanuka Manesha Samarasekara Vitharana Gamage, who has since graduated.
"We will continuously improve the model's performance. We intend to extend the product to support more premium features such as parental control in the future. Our product's potential markets and stakeholders are general consumers watching YouTube videos and companies and online video platforms planning on using our API to filter YouTube videos with clickbait," Dr Lim shared.
The prototype of the BaitRadar was launched in the Chrome Web Store and is ready to download by users. The research was published at the top conference in signal processing (ICASSP 2021). The product also won a Gold medal in Malaysia's 33rd International Invention, Innovation & Technology Exhibition (ITEX 2021).