Use AI for the evaluation of consultation procedures


⛶  Open fullscreen





This content is a preview from an external site.

Pitch: 📎 GovHack 23.03_V1.pdf

The "Restruct Feedback" Hackathon challenge addresses a critical issue that arises during the draft legislation consultation process - unstructured text responses. Stakeholders are typically invited to provide feedback on draft legislation, which can result in an overwhelming number of responses that are disorganized and difficult to analyze. This challenge aims to streamline the process by creating a workflow that efficiently and effectively structures and categorizes feedback. This, in turn, will help the federal administration to understand and act on feedback quickly, reducing the time-consuming efforts involved in analyzing unstructured responses.

To achieve this, the proposed workflow involves using the ChatGPT API to analyze the sentiment of each response and categorize them based on the organization and summary of the main points. ChatGPT is a natural language processing tool developed by OpenAI that can understand and analyze language at an advanced level. By leveraging its capabilities, participants in the challenge can create a system that can effectively analyze and categorize unstructured text responses, making it easier for the federal administration to identify and address critical issues in the draft legislation.

Overall, the "Restruct Feedback" Hackathon challenge aims to simplify and streamline the draft legislation consultation process. By creating an efficient workflow that structures and categorizes unstructured text responses using the ChatGPT API, the federal administration can quickly understand and act on feedback, leading to more effective legislation development.

Organization: BK Federal Chancellery & Others

Edited content version 41

28.03.2023 08:47 ~ delixfe

Repository updated

26.03.2023 09:06 ~ loleg

Event finished

24.03.2023 16:00


24.03.2023 14:51

Edited content version 33

24.03.2023 14:51 ~ Timothy

Edited content version 31

24.03.2023 14:51 ~ Timothy

backend: toward mass processing

backend: iterate over data submission text files


24.03.2023 13:52

Edited content version 29

24.03.2023 13:52 ~ Timothy

Edited content version 27

24.03.2023 13:44 ~ Timothy

Added Stadt Bern (@philippemeyer5)


24.03.2023 13:37

Edited content version 25

24.03.2023 13:37 ~ Timothy

The website programmed by Michael Luggen has some additional AI generated content now:

24.03.2023 13:34 ~ Philippemeyer

SGV added (@philippemeyer5)

Added KT Obwalden, Jura (@philippemeyer5)


24.03.2023 13:25

Edited content version 21

24.03.2023 13:25 ~ Timothy

Edited content version 19

24.03.2023 13:24 ~ Timothy

Kanton Luzern und Testkanton added (@philippemeyer5)

Added Summary Bern (@philippemeyer5)

Added Summary Hauptstadtregion Schweiz (@philippemeyer5)

Added SGB

With summary and sentiment. (@philippemeyer5)

Added Hauptstadtregion Schweiz

Hope this works, first time working in json. (@philippemeyer5)

renamed directory (@vazpe)

moved (@vazpe)

moved files to a subfolder (@vazpe)

Create (@vazpe)


24.03.2023 10:32

Joined the team

24.03.2023 10:32 ~ Philippemeyer

Add files via upload (@vazpe)

add folder structure for eid


24.03.2023 09:17

Joined the team

24.03.2023 09:17 ~ Timothy

remove unused files

Add files via upload

backend: more iterations and then stuck

This model's maximum context length is 4097 tokens. However, your messages resulted in 5088 tokens.

Add files via upload

Create .gitkeep

backend: more test iterations

add another resource

add consultation as text doc

added consultation docs and results to data

refactor data directory structure

add more resources

add more resources links to READMEs

backend: refactoring

add .env-template

replace ':' with '__' in data

Delete Arbeitgeberverband_20210121.msg (@vazpe)

Delete VernehmlassungKtGenfkeineBemerkung_20210226.msg (@vazpe)

Initial backend commit

first html based con consultation.json


23.03.2023 15:13

23.03.2023 15:13 ~ delixfe


23.03.2023 14:00

Working title, and first goal ready.

23.03.2023 14:00 ~ l00mi


23.03.2023 14:00

Edited content version 9

23.03.2023 14:00 ~ l00mi

Joined the team

23.03.2023 12:41 ~ SebastianSingler

Event started

23.03.2023 09:00
Alle Teilnehmer*innen, Sponsor, Partner, Freiwilligen und Mitarbeiter*innen unseres Hackathons sind verpflichtet, dem Hack Code of Conduct zuzustimmen. Die Organisatoren werden diesen Kodex während der gesamten Veranstaltung durchsetzen. Wir erwarten die Zusammenarbeit aller Teilnehmer*innen, um eine sichere Umgebung für alle zu gewährleisten. Mehr Details befinden sich in die GovTech Hackathon Guidelines.

Tous les participant-es, sponsors, partenaires, bénévoles et collaborateurs/collaboratrices de notre hackathon sont tenus d'accepter le Hack Code of Conduct. Les organisateurs feront appliquer ce code tout au long de l'événement. Nous attendons de tous les participants qu'ils coopèrent afin de garantir un environnement sûr pour tous. Pour plus de détails, veuillez consulter les Guidelines du GovTech Hackathon.

Creative Commons LicenceDie Inhalte dieser Website stehen, sofern nicht anders angegeben, unter einer Creative Commons Attribution 4.0 International License | Le contenu de ce site web est, sauf indication contraire, sous licence Creative Commons Attribution 4.0 International.

GovTech Hackathon 2023