-
Notifications
You must be signed in to change notification settings - Fork 2
Frequently Asked Questions when working with the Discourse Analysis Tool Suite (DATS)
The D-WISE project is a research project at the University of Hamburg. For more information, please visit: www.dwise.uni-hamburg.de.
The DATS is created for qualitative discourse analysis with a hermeneutical focus.
The Discourse Analysis Tool Suite is a project at University Hamburg financed by the BMBF and created as open source prototypical work environment.
We have several pages for guiding user through DATS. For detailed walk throughs, feel free to check out our 'User Guide':
- https://github.com/uhh-lt/dats/wiki/User-Guide; and for specific working steps our 'How To':
- https://github.com/uhh-lt/dats/wiki/How-To
If you want to know more about the machine learning models we use, please check out:
For now, annotations in english, german and italian are supported by DDATSWTS.
@inproceedings{schneider-etal-2023-wise,
title = "The {D}-{WISE} Tool Suite: Multi-Modal Machine-Learning-Powered Tools Supporting and Enhancing Digital Discourse Analysis",
author = "Schneider, Florian and
Fischer, Tim and
Petersen-Frey, Fynn and
Eiser, Isabel and
Koch, Gertraud and
Biemann, Chris",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-demo.31",
doi = "10.18653/v1/2023.acl-demo.31",
pages = "328--335",
abstract = "This work introduces the D-WISE Tool Suite (DWTS), a novel working environment for digital qualitative discourse analysis in the Digital Humanities (DH). The DWTS addresses limitations of current DH tools induced by the ever-increasing amount of heterogeneous, unstructured, and multi-modal data in which the discourses of contemporary societies are encoded. To provide meaningful insights from such data, our system leverages and combines state-of-the-art machine learning technologies from Natural Language Processing and Com-puter Vision. Further, the DWTS is conceived and developed by an interdisciplinary team ofcultural anthropologists and computer scientists to ensure the tool{'}s usability for modernDH research. Central features of the DWTS are: a) import of multi-modal data like text, image, audio, and video b) preprocessing pipelines for automatic annotations c) lexical and semantic search of documents d) manual span, bounding box, time-span, and frame annotations e) documentation of the research process.",
}
DATS is created as a tool to support multimodal data analysis, including text, images, audio, and video. You can analyze the following data formats:
-
Text
- .txt
- .html (this also includes mixed HTML documents with images or video)
- .doc and .docx
- .odt
-
Image
- .jpg and .jpeg
- .png
-
Audio
- .mpg and .mpeg
- .ogg
- .wav
-
Video
- .mp4
- .webm
- .m4v
DATS is designed for the Sociology of Knowledge Approach to Discourse, focusing hermeneutical oriented projects
DATS is a browser-based software - for now, you cannot download DATS and use it offline. Try it here.
For a glossary of the terminologies and definitions used in DATS, please see:
DATS works best with large displays (1920x1080) on computers and laptops. The interface won't be displayed in an ideal way on tablets. Please use the Chrome browser.
No, there is no user limit for collaborative research projects in DATS.
For getting in touch, feel free to contact dwise@uni-hamburg.de.
How long will my account and my data be saved on the DATS servers? Will my data be deleted after a while?
At this moment, the project is temporarily funded. We can not give an exact timeframe how long we can provide server capacities. In that case we will inform any user beforehand, to download and protect their research data.
Please contact dwise@uni-hamburg.de for deleting your account. This is not an automatic procedure and may take some time. Please note that all your content (e.g. memos, codes, annotations, tags etc.) will be deleted for you and your collaborators.
For resetting your password, please contact dwise@uni-hamburg.de. This is not an automatic procedure and may take some time.
Yes you can change your E-Mail address, see (LINK).
Currently, your project is safe on the DATS Servers. It will be saved automatically. Nonetheless, we recommend to keep a copy of all your raw files on your own device.
Yes, your project is saved automatically as soon as you make any changes.
You can create an infinite number of projects.
Please see How to add users to your project.
Currently, it is not (yet) possible to assign roles or permissions to individual user. Every user has the same permissions.
All data is not strictly password protected nor encrypted. Further, it is uploaded and stored on our D-WISE Servers. Since we cannot guarantee full privacy of your data, we currently recommend to only upload anonymised and or non-sensible data.
You can upload your own data. Please see this guide: How to import / upload documents to a project However, it is currently not (yet) supported to import the previously exported data.
You can export all data of the project. Please see this guide (LINK)
Yes, the maximum allowed file size is 100MB.
For more information on utility tools being useful as extensions for DATS, please see our Github Page on 'Utility Tools':
For getting in touch or technical support, feel free to contact dwise@uni-hamburg.de or check out the DATS user guide at github: https://github.com/uhh-lt/dats/wiki/userguide
Please use the feedback button in the bottom left to submit feedback to us.
You can try to restart your computer, your browser, or clean your browser cache or contact dwise@uni-hamburg.de.