Description
The objective of this project is to enhance user understanding of an existing dashboard by tailoring explanations to individual users, based on interaction logs and provenance data.
Tasks
Implementing latest track library within the existing onboarding project
Refine onboarding content using the interaction logs and provenance graph to offer context-aware insights.
Leveraging the LLM's capabilities to determine the onboarding sequence by the dashboard usage patterns and and the type, location, and data inherent to each visual.
Dynamically adjusting the narrative to cater to varied user expertise levels.
Implementing a responsive interface where users can seek further clarity, for instance, by prompting questions like "Explain this state to me?" The LLM-backed onboarding would then adapt its responses, ensuring a personalized and enriched user experience within data visualization platforms.
Further tasks would involve user study with expert interviews to evaluate the usability and usefulness of the topic.
Requirements
- Interest and knowledge in visualization.
- Good programming skills.
- Creativity and enthusiasm.
Environment
The project should be implemented as a standalone application, desktop or web-based (to be discussed).
Supervision: Vaishali Dhanoa (Pro2Future), Andreas Hinterreiter (JKU Linz), Paul Haferlbauer (Pro2Future), Marc Streit (JKU Linz), Eduard Gröller (TU Wien)
Contact: vaishali.dhanoa@pro2future.at
Related Work:
A Process Model for Dashboard Onboarding (Vaishali et. al EuroVIS 2022),
Track, Zach et. al (IEEE VIS’20)
A survey of knowledge-enhanced text generation (augment knowledge of LLMs with additional data)
Retrieval-augmented generation (RAG) (Also about concept of knowledge augmentation but more practical)