search

hcmlab / nova

NOVA is a tool for annotating and analyzing behaviours in social interactions. It supports Annotators using Machine Learning already during the coding process. Further it features both, discrete labels and continuous scores and a visuzalization of streams recorded with the SSI Framework.
http://openssi.net/
GNU General Public License v3.0
174 stars 37 forks source link

Love your tool! Just created a video tutorial walk-through with an example #439

Open vinayprabhu opened 4 years ago

vinayprabhu commented 4 years ago

Hi Nova team,

Loved your tool and kudos on the efforts. Just made a video tutorial to help newbies get started.

Hope this helps. Eagerly following how this project progresses :)

tobiasbaur commented 4 years ago

Dear Vinay Uday Prabhu, that's really cool. I think it's very good for people to get an idea on basic annotation. Very nice video.

I have some suggestions for your workflow that might help you and others in the process:

I realized you left-click on the position where you want to start and then you drag the label to the size you want. That's a way to do it. There are also some other options: For example you can use the right mouse button to directly have a "dragable" segment that starts where you right-click and can be dragged to any direction. This way you get bigger segments that are easier to move.

Another way to annotate is by adjusting the red and the green curser (by clicking in the annotation track and on the menu bar directly above the annotation track and hit the "w" button. This way a label between both cursors will be generated.

When resizing or moving a segment, make sure you click it once so it gets selected (it gets blue when its selected).

I'm excited to see what you plan to do with your labels. In case you are also interested in using NOVA's built in machine learning features, please also have a look at chapters 4 and 5 in the documentation.

Very nice job!