Creating Projects
Learn how to create and setup projects in CoLoop for qualitative research. Follow steps to upload research material, generate project descriptions, and optimize transcription for accurate analysis. Start your research journey efficiently with CoLoop.
Start of by creating a project to contain your research material. You can do this by clicking ‘Create Project’ when you first login.
Project setup
After creating a project you will be prompted to …
1. Choose a region to store your raw files (read more about this here)
2. Upload discussion guide(s)
This should be in DOCX format and contain examples of the types of questions and discussion points your research focused on. This can also be used to automatically generate a project description (step 4).
3. Enter any additional objectives
These should be the main objectives of your research project. These will be used to generate the project description in (step 4).
4. Generate or write a project description based on this information
You can generate this if you’ve uploaded a discussion guide and provided some objectives or simply write it yourself. This description will serve as the AI’s ‘long term memory’. It will be used as context when answering any questions.
What does this do?
- These steps are used to provide context that will be used to improve downstream performance
- They also help to improve transcription with brand names and provide suggested questions in the analysis grid
- At a minimum we strongly recommend providing a description of your project and any other requirements you have in the project description.
- This can drastically improve performance when answering questions or summarising themes (read more about this here)
Uploading research material
Coloop supports the following formats for the time being. We strongly recommend using audio or video files if possible as we can guarantee the format and quality of these will be high enough for the system to work.
| File Format/Data Source | Support | Additional Information |
|---|---|---|
| Audio files | ✅ | Recommended (very high accuracy!) |
| Video files | ✅ | Recommended (very high accuracy!) |
| Text files (.txt) | ✅ | Recommended |
| Other languages | ✅ | CoLoop supports audio files in 13 different languages. Read more |
| Word documents (.docx) | ✅ | Range of formats supported including Rev |
| Community data | ✅ | Should be in excel format. |
| Recollective | ✅ | Supports all qualitative tasks Read more |
| Incling | ✅ | Supports all qualitative tasks Read more |
| Otter transcripts | 🟡 | Low quality |
| Rev transcripts | 🟡 | Requires formatting |
| Other transcripts | 🟡 | Requires formatting |
| PDF files | ❌ | Copy and paste text in |
| Survey data | ❌ | Currently being worked on |
| Social media data | ❌ | Not supported |
You can upload multiple pieces of research material to CoLoop. The system is currently optimised to support typical qual studies of 1-10 focus groups or 5-40 depth interviews. We do not currently support qual at scale studies involving few or single answers from many hundreds of participants.
You can upload multiple pieces of research material to CoLoop. The system is currently optimised to support typical qual studies of 1-10 focus groups; 5-50 depth interviews; 50-100 Participant Online Studies. We do not currently support qual at scale studies involving few or single answers from many hundreds of participants.
Transcription (Audio and video)
Open then the 3 dots menu to the right of the title.Coloop uses state of the art transcription models to convert English audio or video to text. The accuracy of this can be further enhanced by clicking Complete and providing the following optional information below.
1. Number of speakers
- Enter the expected number of speakers in the audio or video
- This includes anyone present in the audio e.g. support staff, soundtracks from stimulus material etc.
2. Speaker accent
- We currently offer UK, US and AU English.
- Leave this unset or pick the nearest one if your participants are none of the above.
3. Custom vocabulary
- Enter any brand names or keywords that appear in your discussion guide
- The list does not have to be exhaustive - even providing a few can cause dramatic improvements.
Labelling speakers
Once uploaded and transcribed (if audio or video) CoLoop requires speakers to be labelled with a name and role.
Do this by clicking on the Complete task button. This will open the transcript and prompt you to enter a name for each speaker.
CoLoop can also automatically assign names and roles to your speakers based on the context. All you need to do is click on the Auto-label speakers option.
Assigning roles to speakers
CoLoop needs to know whether somebody is a researcher or a participant. This is to steer the AI to use comments made by participants as supporting evidence and researchers as context.
CoLoop can assign these automatically, but it might leave out some that are unclear, in which case you can edit them afterwards. Change the role by clicking on the icon next to the speakers name in the transcript. If you aren’t sure or it isn’t clear choose participant.
Change the role by clicking on the icon next to the speakers name in the transcript. If you aren’t sure or it isn’t clear choose participant.
Finishing up
Once you’ve set up your project CoLoop will load your research material into memory ready for you to start analysing.
You must wait for a file to finish indexing for it to be available for analysis. Interacting with the chat before this will cause files that haven’t finished loading to be left out.
Next Steps
Once you’ve set up a project jump into the analysis grid or chat and start asking questions!
Was this page helpful?