Polis is a real-time system for gathering, analyzing and understanding what large groups of people think in their own words, enabled by advanced statistics and machine learning.

"Pol.is is a software product developed by Occupy Wall Street activists in the US. Participants draft agreement statements (“UberX should pay drivers a living wage"), and then each participant can privately vote to agree, disagree, or simply pass on each statement.

The Pol.is software applies semantic clustering to these statements and votes to analyze and chart the group into clusters. With enough data, this results in discernible factions based on any number of expressed viewpoints. Importantly, Pol.is also identifies popular statements between otherwise opposing factions, exposing areas of consensus. In doing so, the software maps the relationships between how participants feel about the issues surrounding the topic. Compared to some other engagement tools whose participation syntheses can still best be described as, “a word cloud”, Pol.is is working at an entirely different level.

The deliberative group can then use this data for additional discussions and designing compromises. The facilitators drive the stakeholders' conversation, through voting, towards co-creating a rough consensus (rather than complete agreement). In the case of UberX, areas of consensus included the arguments that the company must not undercut minimum fare prices, and that app-based ride services must only pick up passengers dispatched from apps, rather than off the street. The decisions were then sent to the requesting government agency to either adopt or reject. From here, civil servants translated the recommendations to specific policies and reviewed their legal viability, with the option to consult the original petitioners for clarification. (This step, a human layer of people who can transpose digital feedback into analog institutions, shows up in several successful public engagement platforms and is an important investment to keep in mind when setting up such a program).

In the UberX case, 31,115 votes were cast on a flexible set of regulations, which were soon adopted by the government. The process was successfully repeated to determine regulations around Airbnb in Taiwan.

Many digital platforms are rightly critiqued for engaging individuals as sole actors, rather than collective groups. vTaiwan stands out as a truly multistakeholder process from start to finish. It is also a strong and too rare example of a blended online-offline participatory process.”

– Matt Stempeck, Next Generation Engagement Platforms