Whether it’s software for manual annotation or GPU-driven computing for automatic text/image processing, we’ve got you covered.
The Societal Analytics Lab offers a range of services for VU FSW researchers, and is involved in the development and maintenance of various digital infrastructure projects.
Our main goal is to facilitate the use of big multimodal data and computational methods:
For this, we have acquired our computing server, in which we have safely stored popular tools:
- AmCAT: AmCAT makes it easy to upload, analyze, and sample big data. You keep full control over your data, you can share it, keep it closed, and export it when needed.
- Whisper: Whisper is an automatic speech recognition system. It enables transcription in multiple languages, as well as translation from those languages into English.
- LIWC: LIWC is the gold standard in software for analyzing word use. It can be used to study a single individual, groups of people over time, or all of social media.
- OpenWeb-UI + Ollama: They open-source projects that serve as powerful and user-friendly platforms to run Large Language Models.
- Prodigy: Prodigy is an efficient annotation and training tool that enables entity recognition, detection, image classification, and more!
You can check more info in the presentation we gave during the Lab tools introduction event.
This way, researchers can focus on research rather than acquiring infrastructure:
Icons are property of the companies stated or come from https://www.flaticon.com/.
