New York lawmakers have passed a moratorium that would ban the use of facial recognition in schools until 2022. Their decision comes a month after the New York Civil Liberties Union sued the State Education Department for approving Lockport City School District's facial recognition system. If you'll recall, Lockport started testing a facial and object recognition technology called "Aegis" in June 2019, and the district officially activated it in January this year. The bill mandating the moratorium still needs Governor Cuomo's approval, but once it's official, the New York education department will also be compelled to study and craft regulation around the technology's use. Education Policy Center deputy director Stephanie Coyle issued a statement for the NYCLU, explaining how facial recognition can affect Black and Brown students' experiences.
"Subjecting 5-year-olds to this technology will not make anyone safer, and we can't allow invasive surveillance to become the norm in our public spaces," said Stefanie Coyle, deputy director of the Education Policy Center for the New York Civil Liberties Union. "Reminding people of their greatest fears is a disappointing tactic, meant to distract from the fact that this product is discriminatory, unethical and not secure." The debate in Lockport has unfolded over nearly two years. The school district initially announced its plans to install a facial recognition security system, called Aegis, in March 2018. The district spent $1.4 million, with money it had been awarded by the state, to install the technology across 300 cameras.
Recently, the Victorian Government brought in new rules stating Victorian state schools will be banned from using facial recognition technology in classrooms unless they have the approval of parents, students and the Department of Education. Students may be justifiably horrified at the thought of being monitored as they move throughout the school during the day. But a roll marking system could be as simple as looking at a tablet or iPad once a day instead of being signed off on a paper roll. It simply depends on the implementation. Trials have already begun in independent schools in NSW and up to 100 campuses across Australia.
For years, the Denver public school system worked with Video Insight, a Houston-based video management software company that centralized the storage of video footage used across its campuses. So when Panasonic acquired Video Insight, school officials simply transferred the job of updating and expanding their security system to the Japanese electronics giant. That meant new digital HD cameras and access to more powerful analytics software, including Panasonic's facial recognition, a tool the public school system's safety department is now exploring. Denver, where some activists are pushing for a ban on government use of facial recognition, is not alone. Mass shootings have put school administrators across the country on edge, and they're understandably looking at anything that might prevent another tragedy.
Interactive Educational Systems (IESs) have developed rapidly in recent years to address the issue of quality and affordability of education. Analogous to other domains in AI, there are specific tasks of AIEd for which labels are scarce. For instance, labels like exam score and grade are considered important in educational and social context. However, obtaining the labels is costly as they require student actions taken outside the system. Likewise, while student events like course dropout and review correctness are automatically recorded by IESs, they are few in number as the events occur sporadically in practice. A common way of circumventing the label-scarcity problem is the pre-train/fine-tine method. Accordingly, existing works pre-train a model to learn representations of contents in learning items. However, such methods fail to utilize the student interaction data available and model student learning behavior. To this end, we propose assessment modeling, fundamental pre-training tasks for IESs. An assessment is a feature of student-system interactions which can act as pedagogical evaluation, such as student response correctness or timeliness. Assessment modeling is the prediction of assessments conditioned on the surrounding context of interactions. Although it is natural to pre-train interactive features available in large amount, narrowing down the prediction targets to assessments holds relevance to the label-scarce educational problems while reducing irrelevant noises. To the best of our knowledge, this is the first work investigating appropriate pre-training method of predicting educational features from student-system interactions. While the effectiveness of different combinations of assessments is open for exploration, we suggest assessment modeling as a guiding principle for selecting proper pre-training tasks for the label-scarce educational problems.