# Comparing informativeness of an NLG chatbot vs graphical app in diet-information domain

arXiv: https://arxiv.org/abs/2206.13435 · HTML: https://mlsanity.com/paper/2206.13435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 40 references that are in the map.
- First posted on arXiv 23 Jun 2022.

## Builds on (most cited first, 5 of 5)

- [A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems](https://mlsanity.com/paper/2011.03992/) (2020)
- [Underreporting of errors in NLG output, and what to do about it](https://mlsanity.com/paper/2108.01182/) (2021)
- [Making effective use of healthcare data using data-to-text technology](https://mlsanity.com/paper/1808.03507/) (2018)
- [How are you? Introducing stress-based text tailoring](https://mlsanity.com/paper/2007.09970/) (2020)
- [Foodbot: A Goal-Oriented Just-in-Time Healthy Eating Interventions Chatbot](https://mlsanity.com/paper/2009.05704/) (2020)

## Built on by (most cited first, 1 of 1)

- [When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition](https://mlsanity.com/paper/2511.20652/) (2025)

## Abstract (arXiv)

Visual representation of data like charts and tables can be challenging to understand for readers. Previous work showed that combining visualisations with text can improve the communication of insights in static contexts, but little is known about interactive ones. In this work we present an NLG chatbot that processes natural language queries and provides insights through a combination of charts and text. We apply it to nutrition, a domain communication quality is critical. Through crowd-sourced evaluation we compare the informativeness of our chatbot against traditional, static diet-apps. We find that the conversational context significantly improved users' understanding of dietary data in various tasks, and that users considered the chatbot as more useful and quick to use than traditional apps.