E-democracy platform with automated Artificial Intelligence user voting (based on user profiles) and transparent social data collection

Currently there are a number of E-democracy 'solutions' that potentially allow the electorate to create polls, take votes and then have their elected representative vote the same way e.g. in Parliament, thus ensuring real or 'direct' democracy. However, our view is that these solutions are flawed as the electorate cannot reasonably be expected to become involved with and vote on every single issue. Existing solutions attempt to solve the above problem but are suboptimal and restrict the acceptability and uptake of the E-democracy proposal.
This project aims to develop a Django 2.X based E-democracy platform with an extra option of automated Artificial Intelligence (AI) voting based on a user's profile, consisting of a number of attributes that will record a user's political views. The user will have various settings/preferences to control all aspects of automation, delegation, notifications etc.
The objectives are that the platform will contain all expected features plus enhancements such as being able to notify and explain (Explainable AI, a current interest of the School) to the user how and why the automated system intends to vote if they do not vote themselves. It will also gather and display various statistics to aid the political campaigning process, and other less obvious features such as automatic profile selection of political ward/seat to aid users, administrators and allow the system to cope elegantly with electoral boundary changes etc. attributes to record a user's political views. The user will control all aspects of automation, delegation, notifications etc., through various settings/preferences.
By creating true 'democracy' many current issues such as lobbying, lack of transparency etc. can be removed, leading to an accountable government and a fairer society.
Widespread uptake of the platform would, with the users' permission, also provide a valuable source of transparently obtained social data for data mining. For example, as users modify their profile over time, 'live' sentiment analysis would be very useful to a government body wishing to monitor and optimize the allocation of their constrained resources.