Alberta's Parks Division gains insight from unstructured data with SAS®
The government organisation that oversees the Alberta park system is responsible for collecting performance measurements from stakeholders – the visitors to its parks. Previously, this was a time-consuming manual process that took up to three weeks each year. Embracing big data and using SAS Text Miner, the Alberta Parks Division has not only automated this process, but has moved beyond collecting data to gleaning insight from both structured and unstructured data sources, providing a foundation for new program and service delivery to meet stakeholders' needs.
The Parks Division of Alberta Tourism, Parks and Recreation manages nearly 480 parks and protected areas covering 27,678 square kilometres in the province of Alberta, Canada. As part of its mandate, this government organisation solicits feedback from park visitors and Albertans in general, through several different channels. By involving Albertans in decisions about their parks, the Parks Division can focus on its clients and work toward continuous improvement.
"It's a matter of efficiency and being responsive to our stakeholders, who are Albertans," said Roy Finzel, Manager of Business Integration and Analysis with the Parks Division. "Even if you're not a visitor to a park, as a taxpayer you have the right to express your opinion on how tax dollars are spent."
The Parks Division is involved in the development of survey methodology and data collection, which is used for performance measurements. However, the volume of that data has increased dramatically over the years, and the nature of that data has also evolved – rather than purely quantitative data, the organisation now has to deal with unstructured commentaries as well.
This data is used to determine what experience visitors are seeking in terms of facilities or services, and how they rate the parks overall. Visitors also have a choice of staying at a private campground or at one of Canada’s national parks based in the province, as well as municipal parks.
By any definition, the Parks Division truly faced a big data opportunity – running one of the province's top government websites in terms of volume, with nearly 400,000 unique visitors per year. Aside from website commentary, the Parks Division uses a number of methods to collect feedback from stakeholders, including phone calls, mail, email, surveys, public consultations and social media.
"It didn't take long to realize that we needed to find a tool or method to automate this process and incorporate unstructured data for the future," said Finzel. At the time, there were few options on the market, so the Parks Division didn't pursue a solution until the development of SAS Text Miner, which applies information retrieval and data mining techniques to structured and unstructured data for knowledge discovery and predictive modelling. "The SAS team has also been helpful in providing support and training," he said.
The solution allows the Parks Division to automatically process comment information from a variety of sources, investigate website visitation patterns and analyse open-ended survey responses.
"This has freed up three weeks of my time each year," said Jared Prins, Program Analyst with the Park Division's Business Integration and Analysis Section. Each year, Prins would read up to 3,000 surveys, manually assign a code to each comment according to category and input that data. He would then have to drop everything else he was doing for that time. "With SAS Text Miner, it only takes a day or two to build that algorithm, and it only takes minutes to gain insight from that data," he said.
Aside from saving a significant amount of time through automation, the solution also provides insight that was previously not accessible – particularly with unstructured data. “With the manual process, it was difficult to tweak our interpretation of comments. With SAS, we can adjust our filters to gain a clearer understanding of things" said Prins.
The solution is helping the Parks Division shift from reporting the past to anticipating the future, and from acquiring knowledge to acquiring useful intelligence on topical trends and new opportunities.
For example, it discovered a link between park services and a camper's perception of safety. Analysis of the data found that campers could be affected by the level of noise, bathroom or site cleanliness, and the amount of officer patrols – and that failing in any of these areas could contribute to campers feeling unsafe.
"That's been one of the biggest benefits of SAS Text Miner – the discoverability aspect, finding relationships that have never been highlighted in the manual method," said Finzel. "We now have opportunities to channel customer communications into products and services that meet their needs. Having the analytics will enable us to better support changes in program delivery."
Now the Parks Division is able to act on the results of analytics to improve the experience of park visitors. For example, SAS Text Miner highlighted a request for hand sanitizers in washrooms, many of which do not have running water. “The request wasn’t particularly high compared to other categories, but SAS Text Miner identified it as a strongly held opinion. If we relied on the manual method, we never would have thought much of it. But SAS Text Miner – even by default – highlighted it as a growing concern. That’s a concrete example of where we’ve been able to identify a customer issue and deal with it immediately,” said Finzel.
Parks Division is looking at ways to incorporate social media into their overall solution, including the SAS Conversation Center, which captures and analyses significant tweets and routes them to the right person.
"We want to ensure visitors are satisfied with the experiences we have to offer, and that's where unstructured data comes in," said Finzel. "We have the building blocks in place, and there's a lot of potential we're just beginning to tap."
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.
Copyright © SAS Institute Inc. All Rights Reserved.
Alberta's Parks Division
Alberta's Parks Division was relying on manual processes to respond to stakeholders, which was time-consuming and made it difficult to glean insight from unstructured data sources.
Using SAS Text Miner, the Parks Division is able to reduce a three-week process down to a couple of days, and discover new insights in a matter of minutes.
The solution has not only automated manual tasks, but also provides insight into both structured and unstructured data sources that was previously not possible.
“We now have opportunities to channel customer communications into products and services that meet their needs. Having the analytics will enable us to better support changes in program delivery”
Manager of Business Integration and Analysis, Alberta Tourism, Parks and Recreation