{
    "version" : "https://jsonfeed.org/version/1",
    "content" : "news",
    "type" : "single",
    "title" : "The Data Briefing: How to Best Prepare Federal Government Datasets for Chatbots |Digital.gov",
    "description": "The Data Briefing: How to Best Prepare Federal Government Datasets for Chatbots",
    "home_page_url" : "/preview/gsa/digitalgov.gov/bc-archive-content-3/","feed_url" : "/preview/gsa/digitalgov.gov/bc-archive-content-3/2017/05/10/the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots/index.json","item" : [
    {"title" :"The Data Briefing: How to Best Prepare Federal Government Datasets for Chatbots","summary" : "Forbes magazine recently ran an article showcasing six handy mobile apps that were built using federal government open data. The apps range from the Alternative Fueling Station Locator to ZocDoc (a doctor locator). What I especially like about the Forbes article is that the author describes the federal government data sets behind each app. There","date" : "2017-05-10T11:00:46-04:00","date_modified" : "2025-01-27T19:42:55-05:00","authors" : {"bbrantley" : "Bill Brantley"},"topics" : {
        
            "artificial intelligence" : "Artificial intelligence",
            "best-practices" : "Best practices",
            "emerging-tech" : "Emerging tech",
            "innovation" : "Innovation",
            "mobile" : "Mobile",
            "open-data" : "Open data",
            "social-media" : "Social media"
            },"branch" : "bc-archive-content-3",
      "filename" :"2017-05-10-the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots.md",
      
      "filepath" :"news/2017/05/2017-05-10-the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots.md",
      "filepathURL" :"https://github.com/GSA/digitalgov.gov/blob/bc-archive-content-3/content/news/2017/05/2017-05-10-the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots.md",
      "editpathURL" :"https://github.com/GSA/digitalgov.gov/edit/bc-archive-content-3/content/news/2017/05/2017-05-10-the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots.md","slug" : "the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots","url" : "/preview/gsa/digitalgov.gov/bc-archive-content-3/2017/05/10/the-data-briefing-how-to-best-prepare-federal-government-datasets-for-chatbots/","content" :"\u003cp\u003eForbes magazine recently ran an \u003ca href=\"https://www.forbes.com/sites/metabrown/2017/04/30/check-out-these-6-handy-apps-that-wouldnt-exist-without-government-open-data/#7180960b6859\"\u003earticle showcasing six handy mobile apps that were built using federal government open data\u003c/a\u003e. The apps range from the \u003ca href=\"http://www.afdc.energy.gov/locator/stations/\"\u003eAlternative Fueling Station Locator\u003c/a\u003e to \u003ca href=\"https://www.zocdoc.com/\"\u003eZocDoc\u003c/a\u003e (a doctor locator). What I especially like about the Forbes article is that the author describes the federal government data sets behind each app. There are many more mobile apps built by \u003ca href=\"https://www.usa.gov/mobile-apps\"\u003efederal government agencies\u003c/a\u003e or using \u003ca href=\"https://www.data.gov/applications\"\u003efederal government data sources\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eAlong with \u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/2016/01/27/the-data-briefing-improving-the-federal-government-through-mobile-apps/\"\u003emobile apps\u003c/a\u003e, there are \u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/topics/mobile/\"\u003eresponsive websites\u003c/a\u003e and \u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/2016/09/20/progressive-web-applications-part-1-the-new-pack-mule-of-the-internet/\"\u003eprogressive web apps\u003c/a\u003e. These information sources are optimized for mobile devices. The apps are responsive and easy-to-use but, they merely deliver information as any website does. What users are now demanding is a more personal experience when interacting with data.\u003c/p\u003e\n\u003cp\u003eEnter the chatbot. \u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/2016/04/20/the-data-briefing-chatbots-and-the-rise-of-conversational-commerce-and-citizen-experience/\"\u003eChatbots\u003c/a\u003e put a friendly face on the data sets and informational content of a website. The number of chatbots has exploded in recent years as users prefer to interact conversationally rather than using an online search. \u003ca href=\"https://chatbotsmagazine.com/how-to-write-for-a-bot-ce8afc25e54b?source=email-92b5c875be4d-1493983821063-digest.reader------0-6\u0026amp;sectionName=top\"\u003eChatbots have personalities\u003c/a\u003e and can often sound like you are talking to a friend rather than a bunch of “if this, then” algorithms. \u003ca href=\"http://www.fedtechmagazine.com/article/2017/02/chatbot-here-help\"\u003eThe U.S. federal government is in the process of building chatbots\u003c/a\u003e, so expect to see more federal government chatbots being released in 2017 and 2018.\u003c/p\u003e\n\u003cdiv class=\"image\"\u003e\n  \u003cimg\n    src=\"https://s3.amazonaws.com/digitalgov/_legacy-img/2017/05/600-x-400-low-res-Chatbot-concept-with-instant-messenger-displayed-on-smart-phone-a-image-iStock-Thinkstock-588366818.jpg\"\n    alt=\"Chatbot concept with instant messenger displayed on smart phone.\"/\u003e\u003cp\u003ea-image/iStock/Thinkstock\u003c/p\u003e\u003c/div\u003e\n\n\n\u003cp\u003eSo, how do agencies prepare their government datasets for chatbots? The key is to think conversationally. How will users ask about the data and what should the responses be? Follow the steps below to map how your agency’s datasets will be transformed into a conversation.\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eWhat is the bot’s domain? Domain is a term of art and refers to the bot’s breadth of understanding and depth of understanding. Let’s say we want to transform the Alternative Fueling Station Locator into a chatbot. For breadth, what kind of alternative fuels will the bot know about? The different fueling techniques and for what type of vehicles. For depth, how much of a deep dive can the bot take into electrical vehicle recharging? Will the bot know the location of every electrical recharging station in the U.S.? The operating hours for each electrical recharging station? Establishing the domain will help in step two.\u003c/li\u003e\n\u003cli\u003ePreset-conversation paths and free-flowing paths of conversation. Sometimes, the chatbot works better when the user is given a clear path to follow and options to choose from. Other times, the user wants to talk through their information request. Understanding when to use preset paths and when to allow users to freely explore the bot’s domain is essential to developing an effective chatbot.\u003c/li\u003e\n\u003cli\u003eMap the conversation trees. A conversation tree is a map of the possible conversations including how the bot will respond to keywords. Conversation trees also include the inputs from datasets in response to the conversations. Many practitioners recommend using \u003ca href=\"http://www.mindmapping.com/\"\u003emind mapping\u003c/a\u003e to visualize the conversation trees.\u003c/li\u003e\n\u003cli\u003eMap the keywords to the data queries. Create a dictionary of keywords and then list the datasets around the keywords. The idea is to determine how the keyword will shape the dataset query to receive the query results in the most effective manner for each keyword.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eBy following the above steps, agencies are creating \u003ca href=\"https://digital.gov/2013/07/29/how-to-create-open-structured-content/\"\u003estructured content built specifically for chatbots\u003c/a\u003e. Mobile apps, responsive websites, and progressive web apps still have a role to play. However, users are demanding more ways to access government data not embedded in a site. Users want on-demand information, like how chatbots deliver information. Agencies need to free the datasets to be useful in many ways that people want to access federal government data.\u003c/p\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cstrong\u003eDisclaimer\u003c/strong\u003e: All references to specific brands, products, and/or companies are used only for illustrative purposes and do not imply endorsement by the U.S. federal government or any federal government agency.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eEach week, \u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/topics/emerging-tech/\"\u003eThe Data Briefing\u003c/a\u003e showcases the latest federal data news and trends. Visit this blog every week to learn how data is transforming government and improving government services for the American people. If you have ideas for a topic or have questions about government data, please contact me via email.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003ca href=\"/preview/gsa/digitalgov.gov/bc-archive-content-3/authors/bbrantley/\"\u003eDr. William Brantley\u003c/a\u003e is the Training Administrator for the U.S. Patent and Trademark Office’s Global Intellectual Property Academy. All opinions are his own and do not reflect the opinions of the USPTO or GSA.\u003c/em\u003e\u003c/p\u003e\n"}
  ]
}