Belgian Data Protection Authority – Intelligent Chatbot

Case

The Belgian Data Protection Authority has access to interpretations and clarifications on the privacy law based on questions from citizens and organisations. Currently, it is time-consuming to deal with incoming requests, and specialists spend time answering similar questions which were already discussed previously.

What was the problem?

The Belgian Data Protection Authority receives questions requests from citizens and organisations via email. These questions need to be linked by an expert to certain ruling and legislation, after which an answer is presented and published on the website. 

Many of the incoming requests have already been published, and in these cases, the expert spends time simply linking the previous publication(s) to the incoming request.

The Belgian Data Protection authority wanted to explore the possibility of using an intelligent agent integrated into a website, which could automate this. The agent would need to start a natural conversation and, in an intelligent way, guide the conversation to the relevant publications and documents.

How did we solve this problem?

The problem was solved using several machine learning techniques.

First, with topic-modelling techniques, we were able to find underlying themes within the privacy legislation which could be used to steer the questioning and conversation.

Secondly, an intelligent agent was implemented, which was used to mine information to steer the conversation in several languages.

Thirdly, if the question could not be resolved by interacting with the intelligent agent, a search functionality was provided to retrieve the relevant publications for the user.

Work performed

  • Finding underlying structure in document collections
  • Intelligent agent
  • High precision search engine

Added value

  • Providing the correct information to citizens and organisations in a more efficient and natural way
The project was a good demonstration of several machine learning techniques working together to automate, save time and still retain a human-like interaction
—  Joeri Ruyssinck, CEO ML2Grow

Newsletter

Receive news about AI.
This field is for validation purposes and should be left unchanged.