Parlex

Forecasting parliamentary reaction through past debate analysis

The challenge

Over 500 pages worth of debate transcripts are added to the parliamentary record each day. There is a strong need for tools that can navigate through this volume of data and find insight. From researchers and legislators to parliamentarians and librarians, we have heard from teams across government are looking for help navigating the parliamentary landscape more efficiently, leading to a better overall user experience.

The solution

Parlex allows users to navigate Hansard data. By analysing years of parliamentary debate contributions from MPs and Peers, Parlex offers insights into how parliament might react to a new policy if it were debated tomorrow. This tool helps policy professionals gauge parliamentary sentiment towards specific issues, determining whether a policy will be well-received or face significant opposition. This allows policy teams to understand the political climate and anticipate potential challenges or support for a policy before it is formally proposed and to build a parliamentary handling strategy.

The results

Parlex is still in early-stage user testing. However, in interviews with three users, researching a parliamentarian took 1-3 minutes using Parlex. Interviewees estimated that the same task would have taken 30-60 minutes without Parlex.

Learnings / insights

Use great datasets! By leveraging the existing Hansard API for the Parlex product i.AI was able to apply hybrid search and other ML techniques to garner new insights into parliamentary business

Details

Organisation name
Department for Science, Innovation and Technology (DSIT) / Incubator for Artificial Intelligence (i.AI)
Government body
UK Government
User group
Civil servants
Use case type
Specific
Type of technology
Generative AI
Phase
Beta
Impact
Better Customer experience

Links

Get in touch

Email ai-knowledge-hub@dsit.gov.uk to:

  • find out how to use or collaborate on this tool
  • talk to us about your own tool

Content created: 9 May 2025 | Last updated: 23 May 2025