In cities, 311 non-emergency call systems don’t just offer citizens a line to government answers, they also serve as a window for city officials to understand citizen needs, issues with infrastructure and much more.
To improve these systems and the lines of communication between city officials and residents, innovative cities are beginning to tap technology.
Machine Learning, Crowdsourcing Up Boston’s 311 Game
Machine learning and crowdsourcing are on the docket to make the city of Boston’s 311 system simpler and more user-friendly. Mayor Marty Walsh and the Boston Department of Innovation and Technology announced last month that instead of asking users to guess the dozens of inputs their issue fits into within the BOS:311 web system, the city will ask users to simply write about the issue in their own words. The city will build a data set and use predictive modeling to sort through user inputs.
According to the DOIT:
The model we’re building functions basically like a search engine, but is customized for this specific application. It will be created from a training data set of how other users have described their own issues in the past, from which the model learns what words and phrases are most common when talking about different case types. We’ll improve the model over time by adding more examples to that training data set, and the model will even adapt to changes in the pattern of incoming cases — for example, by recognizing that snow-related case types typically come in batches (i.e., during and after a storm), and thus automatically making those suggestions more likely to be shown when we’ve received a spike in snow cases.
To build the data set necessary to train the website, the DOIT has created a form for citizens to fill out, asking them to offer alternate and more colloquial terms for 311 requests. Eventually, the system will be intelligent enough to garner information from multiple requests as opposed to just general phrases.
“This is really a reflection of the way we’re approaching our interactions with constituents,” Boston Chief Data Officer Andrew Therriault told StateScoop. “We’re thinking about it as if citizens are our customers, and doing a lot of the same things you see in the technology world today, things that embrace user-centered design and improve user experience.”
Atlanta Looks at AI Chatbot to Streamline 311
Chatbots, computer programs designed to simulate conversations with users, are quickly entering state and local governments to make services more efficient and free up time for employees. In Atlanta, the city has launched a project to augment its ATL 311 services via the technology. The city hopes to provide more timely information to residents more quickly and after-hours, thus relieving the workload for government employees who may be otherwise tasked with answering those questions.
“If the user calls the 311 line, they will need to call during service hours, which may or may not be convenient for the user. If the user visits the website, they can only search for the answers to their questions in the way that the city has already documented them. A good chatbot does not have either of these limitations,” Atlanta Deputy Chief Information Officer Kirk Talbott told StateScoop.
In developing the chatbot, the city is mining the 311 website for frequently requested information and will use the info to develop the bot using Microsoft Bot Framework.
“Being able to have bots that are trained off of specific and privileged data sets allows for new capabilities in those mission-critical type environments where you can't allow that data to just go out into the ether,” David McClellan, practice director at Neal Analytics, the company developing the chatbot, told StateScoop.
San Antonio’s 311 Gets Gamified
In San Antonio, Texas, city officials have been using social media to gather information about road maintenance and other infrastructure needs for some time, but a new startup called Cityflag is taking 311 to the next level by incorporating social and game elements into a new smartphone app.
The 311 app will “gamify” the experience for citizens by offering badges or rewards as they enter information in hopes of improving civic engagement.
"One of the interesting things is yes, it starts with 311, but it's really a citizen-engagement platform," San Antonio Chief Innovation Officer Jose De La Cruz told StateScoop. "It's a better way for us to engage with our residents."
The city will also look to incorporate the information garnered from the app to supplement its data for city projects.
"It will give us more data and more location data we can get down to specific areas of town [where] these issues are occurring and think about how we can be more proactive in how we deliver our services," De La Cruz said.