Expanding the scope of face detection technology from the ubiquitous security perspective, a Qatar-based scientist is utilising it to understand the demographic attributes of online users.
“Face detection technology opens up a lot of opportunities in social computing and considered a key element in computational social science, as they allow the demographic attributes of online users to be inferred quickly,” Dr Jisun An, a scientist at Qatar Computing Research Institute (QCRI), a research institute under Hamad Bin Khalifa University, told Gulf Times.
“There are 68 points at various parts of the face, called the face landmarks. Using them, the face can be roughly drawn and based on that you can detect if it is a human face or not," she explained.
“Face detection technology can not only recognise between two faces but also give the demographic features of the face as well as the gender, race and age of the person,” explained Dr An.
“This is being applied in many areas from practical applications to social science research. Using the face detection technique I have been trying to understand the human behaviour and trying to make an understanding of the influencers and the public,” she continued.
According to the scientist, in recent years, face detection technology has been rapidly applied to many areas from practical applications to social science research.
“In social computing, these demographic features can be used to understand the individual and group behaviour using large scale data. Most of the time, we use the social media data for this purpose,” noted the researcher.
Social media data can reveal how humans behave in various fields. This can be used to infer the demographics of the social media users.
“It is challenging to infer the demographic but using face recognition technology, it can be done. It can be applied to millions of people and how they behave. By using these techniques we reveal the demographics of the users of especially those who trend on the social media,” maintained Dr An.
The QCRI researcher feels that demographics are one of the key predictors of human behaviour.
“The life of a 50-year-old African American woman is probably very different from that of a 16-year-old white boy. The $190bn US advertising industry uses demographics to help de?ne consumer segments that can then be targeted through dedicated campaigns. In my studies, I also found that most of the trending topics are driven by some particular groups or races in the US and the comments by other people are usually ignored,” added Dr An.