Allen Mathew Madathil
Download Project (1.1 MB)
The proposed project is a graphical user interface for annotating recorded data on the social media composing process. This data can be used to learn about human behavioral patterns. Although this application was built for Windows, but it can be easily scaled to other platforms like Android as it was developed using Java. The Graphical User Interface allows the user to load the video files and label the video segments according to the actions performed. Labels are divided into two categories like action label and verbal label which are further subdivided into many categories. There are around 90 labels to choose from. For each action, the start time and end time are recorded. The labels along with the start time and end time of the actions are saved in a text file. The name of this text file matches the video file so whenever the user reopens the same video, previously saved labels are retrieved from the file which helps the user to continue where he left off. Another feature is that the application has a time-label bar which helps to visualize the labels with its corresponding time frames. Apart from learning about human behavioral patterns this tool can be modified and used for many other research works that require video labeling.
Van Tam Nguyen, Patrick W. Thomas
Primary Advisor's Department
Stander Symposium project, College of Arts and Sciences
"Social Media Content Labelling Toolkit" (2020). Stander Symposium Projects. 1797.
This presentation was given live via Zoom at 2:00 p.m. (Eastern Time) on Wednesday, April 22.