Polis
Polis is a real-time system that uses advanced statistics and machine learning to collect, analyze, and understand what large numbers of people are thinking in their own words. (DeepL)
Pol.is] is also often written as Pol.is, but I did so because the original owner calls himself Polis. nihia.iconPolis is a system that collects and analyzes the opinions and sentiments of large numbers of people in real time. The system uses advanced statistics and machine learning to make the collected opinions easier to understand.
Main Features
Real-time collection and analysis: Collect and analyze the opinions of large numbers of people in real time to understand current opinion trends.
Efficient opinion gathering: designed to be more organic than surveys and less labor intensive than focus groups.
Cluster Analysis: The collected opinions are analyzed in clusters to identify common and conflicting opinions. This provides a holistic view of the diversity of opinions.
Main applications
Policy Making: Governments and businesses can gather citizen and customer feedback to help improve policies and services.
Community consensus building: Used to facilitate coordination and consensus building within the community.
technical background
Polis primarily uses the following technologies
Dimensionality Reduction: Use PCA (Principal Component Analysis), UMAP, etc. to reduce high-dimensional data to lower dimensions for easier visual understanding.
Cluster analysis: clusters opinions using the K-Means method or the Leiden algorithm to extract common groups of opinions.
nishio.iconWhat we tried
gpt-4.icon
The Polis project is an AI-powered sentiment collection platform designed to be more organic than surveys and less labor intensive than focus groups. It aims to satisfy the basic human need to be understood at scale. the basic human need to be understood
Dimensionality reduction
Clustering
---
This page is auto-translated from /nishio/Polis using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.