SparkEdu AI

Using emotion-recognition Artificial Intelligence to recommend stimulating and crucial learning experiences that allows teachers to track their students progress. 

Studies show that when students are more engaged, they are much more likely to learn. Student engagement and emotional response can be gathered through facial expressions. 

Our solution allows for teachers to collect these data points and utilize them while they teaching by using Artificial Intelligence facial recognition programs and depth cameras.

After class the teacher can check the AI dashboard and see each students emotional response, along with different attention, participation, attendance, and other responses that can help tailor their courses to their student's learning style and interests.

The teacher can also make goals to reach, such as rates of participation and excitement and track this over a semester or year. 

This concept helps new and experienced teachers tailor their lessons to each classes learning style, offers an affordable teacher training through experience, helps teachers learn which students may need more tailored help in the class. 

Additionally, this technology can be applied to MOOCs, by using the student’s camera and transmitting data to the instructional creator remotely without transmitting the student’s stream of themselves. We hope that this technology can help teachers better connect with their remote students. 

There are many ways that educators gather student information that can help them improve their learning, such as by using data collected by MOOCs. However, this way can’t be personalized and is difficult to get a full picture because of low completion rates in MOOCs and more importantly, this information is just a snapshot. This personalized information is crucial in creating a classroom where students feelings are taken into account but in a quantifiable way. Studies show that when students are more engaged, they are much more likely to learn. This type of data can be gathered through facial expressions.

Until now, teachers are responsible for gathering this information and reflecting on this themselves after the school day. They may do this by looking at students grades and notes. They also have to recall who answered which questions and remember who was least engaged to make sure they are still on track.

Our solution allows for teachers to collect this information and utilize it while they teaching by using Artificial Intelligence facial recognition programs and depth cameras. This data is then fed through machine learning and data science algorithmic processes to produce a dashboard for easy understanding and goal setting.

In the next 12 months, SparkEdu AI will be completing teacher trainings and indepth research with 5 more classrooms and continuing to gather data points. We also will continue to speak with the teachers and students to gain feedback to better help them.

This same technology can be applied to MOOCs, by using the student’s camera and transmitting data to the instructional creator remotely without transmitting the student’s stream of themselves. We hope to transition to MOOCs to help teachers better connect with their remote students.

We are currently serving 2 classrooms, by helping new teachers understand their students learning style.

We expect to be serving 5 more classrooms for a total of 7 classrooms in 12 months. We hope to help new teachers find their best teaching style and learn from what is shown to work on their dashboards. We hope to follow these teachers and continually see their progress with the solution and understand any blockers they are having in the classroom that our solution can further remediate. After this, we hope to partner with different online learning platforms in order to help these students with this learning platform that holds historically low completion rates.

I’ve held many positions in education and in Artificial Intelligence as teacher, startup founder, hackathon lead, and data analyst. My Cognitive Science in Education masters thesis focus was on e-learning and best practices for encouraging student motivation and engagement. I taught and created science curriculum through my internship with the Museum of Science and Industry, and at the Digital Media Academy at University of Chicago. I have extensive research experience working in a behavioral neuroscience lab, as well as through self-directed research interviewing students about learning. I currently work in my company’s Advanced Analytics AI group.

We plan on creating long-term sustainability through partnerships with e-learning providers, educational researchers, and marketing companies.

I’m applying to Solve because I love the exchange of ideas that comes from participating. I was able to meet amazing people when submitting solutions and by attending at MIT in previous years. I was so inspired when coming two years ago for refugee education solutions, the people involved are amazing and it pushed me to create my own startup! 

I'm excited to read about the tailored partnerships that Solve is able to help me gain and I feel that this is the piece that our solution is in most need of in order to scale.