Civic Tech Field Guide
Donate

https://docs.decidim.org/en/develop/develop/ai_tools.html

AI tools for Decidim

Work in progress AI integration for the participation platform that allows platform admins to install and configure a spam detection service so that any suspicious content gets reported at the earliest possible step.

Active
Since 2024
Barcelona, Spain
Open source: Yes (https://github.com/decidim/decidim/tree/develop?tab=AGPL-3.0-1-ov-file#readme)

"This service can be trained either using the datasets that we provide, or using your own content. This way the engine learns your own business domain and it is able to detect spam or things that are not relevant for your activity." There is also functionality to allow real-time training on instance-specific content, which is informed by admins marking specific content as spam. The service uses a Bayesian strategy. Admins can also integrate other spam detection services. Like the rest of Decidim, it can be applied to specific platform modules. So if not all modules are receiving spam, admins don't need to apply the AI spam filter to them.

Funding details

Funded byDateAmount
Small donorlink

Evidence of this project's impact

1,988,415 users have created 75,885 proposals across 286 processes (Source)2024-12

Over 50,000 registered users (Source)2018-10

Resources

Related projects

Parent organization: Decidim

Project type
Feature
Project stage
Alpha
Founded
2024
Language(s)
Spanish, English
Employees
11
Pricing
Free
Tech stack
N/A
Added
2024-12-05
Last modified
2026-07-12T16:45:52.000Z

Additional details

Tech stack
Redis, Sidekiq, WhatsApp Business Chat, Babel, Livefyre, ZURB Foundation, jQuery, Ruby on Rails, Leaflet, Ruby, core-js, Open Graph, PWA, Tailwind CSS, Vue.js, Vuetify
Integrates with
Decidim
Institutions using the platform
450\. According to an open source tracking tool, 1,988,415 users have created 75,885 proposals across 286 processes. The tool includes a gallery view of all the Decidim instances:
How AI is used
Spam moderation uses machine learning to flag suspicious content, reducing the moderator workload while balancing accuracy and multilingual adaptation. The platform supports automatic translation, enabling inclusive discussions by integrating services like eTranslation. We are piloting a project with the EU initiative **IDEM** to enhance accessibility for diverse users. This includes tools that simplify information for people with disabilities, seniors, and migrants in multiple languages.
Number of end users
2,046,665 across 286 processes
Number of integrations
1
GitHub contributors
100
Metrics of success
Over 50,000 registered users, 1,988,415 users have created 75,885 proposals across 286 processes
Geographic focus
Global
Pricing
Free
Pricing — license model
Free for download or offers a free subscription option with full features.
Pricing — government / nonprofit discount
No
Support included
No