Login

16th European DDI Users Conference, Chur

2–6 Dec 2024
University of Applied Sciences of the Grisons (Pulvermühlestrasse 57)
Europe/Zurich timezone
Conference Hashtag: #EDDI2024
The theme 'nicecompact' does not exist.

Program Committee

Session

Machine Learning and Media

3 Dec 2024, 15:15
Aula (University of Applied Sciences of the Grisons (Pulvermühlestrasse 57))

Aula

University of Applied Sciences of the Grisons (Pulvermühlestrasse 57)

Chur, Switzerland

Conveners

Machine Learning and Media

  • Jon Johnson (CLOSER, UCL)

Presentation materials

There are no materials yet.

  1. 15. Metadata for Social Media and Web Tracking Data
    Wolfgang Zenk-Möltgen (GESIS - Leibniz Institute for the Social Sciences)
    03/12/2024, 15:15
    Regular Presentation

    At GESIS, we plan to collect more digital behavioral data, e.g. social media data and web tracking data. Data sources are currently X/Twitter and tracking data collected by GESIS. The GESIS Web Tracking software works via a browser plugin on desktop devices. To document these data sources for archiving, additional new information is needed beyond the usual survey metadata.

    Challenges are...

    Go to contribution page
  2. 39. Streamlining Media File Conversion to DDI-Lifecycle "Other Material" Using AI
    Benjamin Beuster (Sikt - Norwegian agency for shared services in education and research)
    03/12/2024, 15:35
    Short Presentation

    Social research increasingly includes media formats like audio and video, which are often poorly documented and inaccessible. While archives handle traditional survey data well, media files are mostly limited to minimally annotated zip files due to the complexity of proper documentation. Recent advancements in AI, including the Whisper model, along with the use of Pydantic models and...

    Go to contribution page
  3. 42. AI for Data / Data for AI: Augmentation and Improved Discoverability of DDI Metadata Using LLMs
    Aivin Solatorio (The World Bank)
    03/12/2024, 15:55
    Regular Presentation

    Microdata provides tremendous value in socioeconomic analysis. However, these data may not be easily discoverable when metadata are not as rich, structured, and optimized as they could be. In the case of microdata, an issue is the semantic discoverability of information contained in the variable-level metadata (the data dictionary). This paper presents an unsupervised framework that leverages...

    Go to contribution page
Building timetable...