AI has been reigning in the industries and business ecosystems with its unending capabilities to accelerate automation and provide business intelligence. Disruptive technologies like artificial intelligence, machine learning, blockchain, etc. have enabled companies to create better user experiences and advance business growth. Emotional AI is a rather recent development in the field of modern technology, and it claims that AI systems can read facial expressions and analyze human emotions. This method is also known as affect recognition technology. Recently Article 19, a British human rights organization published a report stating the increasing use of AI-based emotion recognition technology in China by the law enforcement authorities, corporate bodies, and the state itself.
Facial recognition technology is being tested by businesses and governments for everything from policing to employee timesheets. Even more granular results are on their way, promise the companies behind the technology: Automatic emotion recognition could soon help robots understand humans better, or detect road rage in car drivers. But experts are warning that the facial-recognition algorithms that attempt to interpret facial expressions could be based on uncertain science. The claims are a part of AI Now Institute's annual report (pdf), a nonprofit that studies the impact of AI on society. The report also includes recommendations for the regulation of AI and greater transparency in the industry.
The final step for many artificial intelligence (AI) researchers is the development of a system that can identify human emotion from voice and facial expressions. While some facial scanning technology is available, there is still a long way to go in terms of properly identifying emotional states due to the complexity of nuances in speech as well as facial muscle movement. The University of Science and Technology researchers in Hefei, China, believe that they have made a breakthrough. Their paper, "Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition," expresses how an AI system may be able to recognize human emotion through state-of-the-art accuracy on a popular benchmark. In their published paper, the researchers say, "Automatic emotion recognition (AER) is a challenging task due to the abstract concept and multiple expressions of emotion. Inspired by this cognitive process in human beings, it's natural to simultaneously utilize audio and visual information in AER … The whole pipeline can be completed in a neural network."
In the run-up to the election last year, Ben Heubl from The Economist used the Emotion API to chart the emotions portrayed by the candidates during the debates (note: auto-play video in that link). In his walkthrough of the implementation, Ben used Python to process the video files, and R to create the charts from the sentiment scores generated by the API. Now, the learn dplyr blog has recreated the analysis using R. A detailed walkthrough steps through the process of creating a free Emotion API key, submitting a video to the API using the httr package, and retrieving the emotion scores as an R data frame. For the complete details, including the R code used to interface with the Emotion API, follow the link below.