Argument condensation for questions as clustered lists of pros, cons and possibly neutral stances

[kaljarv]

resources

Code: https://github.com/maximusvitutus/argument-condensation

Primary user story

Also: “candidates who said these, leaned towards fully agree”, or similar way of showing what type of answering behaviour this argument corresponds to

As a voter with an uncertain opinion about a VAA question, I want to see distilled arguments for the different options, so that I can form a more informed choice.

Considerations

In addition to standard Likert questions, the VAA supports other question types. The answers to some of these don't have an associated numerical value, i.e. they are categorical aka. nominal.

• How to implement the feature in such a way, that it can be useful for Likert questions, nominal questions and possibly even purely numerical questions, such as "What should the level of VAT be?"?

Subtasks

1. Initial planning
   • Which technologies to use?
   • Which of the tech is shared between the other ideas?
   • Which data sources are needed?
   • Is the AI model interacted with in real-time or do we use canned results?
   • Make a sketch of the ideal interaction? E.g. a script of the chat or a rough draft of the visualisation
2. Prototyping
   • Make a UI sketch in Figma
   • Test the suggested workflows using real data and real models
3. Development
   • Steps TBA
4. Admin UI development
   • Optional

[MinhTran0311]

https://www.notion.so/Argument-condensation-for-questions-as-clustered-lists-of-pros-cons-and-possibly-neutral-stances-a-13140660a20a80a58498c64ef44ff296

[samilaa]

@maximusvitutus @0xdaali @samilaa