2024 Summer Undergraduate Research Program (SURP) Symposium
Location
John Deere Auditorium, Curris Business Building, University of Nothern Iowa
Presentation Type
Poster Presentation (UNI Access Only)
Document Type
poster
Abstract
This research is focused of tracking a users sociability and giving recommendations based on their sociability score Student’s performance in school is affected by their mental health If we give students the tools to measure their own sociability, then they will be able to take the steps to socialize more and improve their mental and emotional wellbeing Our data was collected from participants and converted into a set of features that the neural network is able to process Our machine learning algorithm is roughly 50-60% accurate at applying what it learned from the training data onto the testing data This means that the network was capable of detecting the difference between two speakers 50-60% of the time.
Start Date
26-7-2024 11:00 AM
End Date
26-7-2024 1:30 PM
Event Host
Summer Undergraduate Research Program, University of Northern Iowa
Faculty Advisor
Dheryta Jaisinghani
Department
Department of Computer Science
Copyright
©2024 Brandon Schmidt, Dheryta Jaisinghani
File Format
application/pdf
Recommended Citation
Schmidt, Brandon and Jaisinghani, Dheryta, "Improving Student’s Socialness with Neural Networks on Smartphones" (2024). Summer Undergraduate Research Program (SURP) Symposium. 14.
https://scholarworks.uni.edu/surp/2024/all/14
Improving Student’s Socialness with Neural Networks on Smartphones
John Deere Auditorium, Curris Business Building, University of Nothern Iowa
This research is focused of tracking a users sociability and giving recommendations based on their sociability score Student’s performance in school is affected by their mental health If we give students the tools to measure their own sociability, then they will be able to take the steps to socialize more and improve their mental and emotional wellbeing Our data was collected from participants and converted into a set of features that the neural network is able to process Our machine learning algorithm is roughly 50-60% accurate at applying what it learned from the training data onto the testing data This means that the network was capable of detecting the difference between two speakers 50-60% of the time.
