InvestChat: Exploring Multimodal Interaction via Natural Language, Touch, and Pen in an Investment Dashboard

Abstract

We designed and implemented InvestChat, a multimodal tablet-based application that supports stock market exploration with multiple coordinated views and an LLM-powered chat. We evaluated the application with 12 novice investors. Our findings suggest that combining natural language, touch, and pen input during stock market exploration facilitates user engagement. Participants leveraged the modalities in complementary ways, enjoying the freedom of choice and finding natural language most effective.

Workflow Status

Review status

pending

Role

unreviewed

Read priority

soon

Vote

Not set.

Saved

no

Collections

Not filed yet.

Next action

Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

BibTeX

@article{tost2026investchat,
  title = {InvestChat: Exploring Multimodal Interaction via Natural Language, Touch, and Pen in an Investment Dashboard},
  author = {Sarah Lykke Tost and Adson Lucas de Paiva Sales and Henrik Østergaard and Vaishali Dhanoa and Gabriela Molina León},
  year = {2026},
  abstract = {We designed and implemented InvestChat, a multimodal tablet-based application that supports stock market exploration with multiple coordinated views and an LLM-powered chat. We evaluated the application with 12 novice investors. Our findings suggest that combining natural language, touch, and pen input during stock market exploration facilitates user engagement. Participants leveraged the modalities in complementary ways, enjoying the freedom of choice and finding natural language most effective},
  url = {https://arxiv.org/abs/2604.19537},
  keywords = {cs.HC},
  eprint = {2604.19537},
  archiveprefix = {arXiv},
}

Metadata

{}