{"id":41032,"date":"2017-11-14T00:18:00","date_gmt":"2017-11-14T00:18:00","guid":{"rendered":"https:\/\/inmoment.com\/?p=41032"},"modified":"2024-06-20T14:59:12","modified_gmt":"2024-06-20T20:59:12","slug":"analyzing-airport-reviews-using-nlp","status":"publish","type":"post","link":"https:\/\/inmoment.com\/blog\/analyzing-airport-reviews-using-nlp\/","title":{"rendered":"Analyzing Airport Reviews Using Natural Language Processing"},"content":{"rendered":"

We used cutting-edge\u00a0natural language processing (NLP<\/a>) and\u00a0sentiment analysis<\/a> software to analyze thousands of airport reviews. By combining qualitative and quantitative data, our analyses reveal what travelers are talking about, how they feel, and why they feel that way.\u00a0<\/span><\/p>\n

Read them all: using NLP to analyze airport reviews<\/h2>\n
    \n
  1. Atlanta International<\/a>\u00a0has a big problem with “wayfinding”<\/li>\n
  2. Charlotte Douglas<\/a> can profit big by listening to their customers<\/li>\n
  3. Chicago O’Hare<\/a> needs to learn about viral reputation management<\/li>\n
  4. Dallas\/Fort Worth<\/a> has a dirty secret<\/li>\n
  5. Denver International<\/a> may be a secret haven for the Illuminati<\/li>\n
  6. New York’s JFK<\/a> has to plan for the future<\/li>\n
  7. Las Vegas McCarran<\/a> doesn’t shy away from your vices<\/li>\n
  8. San Francisco<\/a> can teach us about listening to customers<\/li>\n
  9. Seattle-Tacoma<\/a>\u00a0has a vocal customer named Jerry<\/li>\n
  10. Los Angeles<\/a> needs to master the “final mile”<\/li>\n
  11. Summary: The Definitive Data-Driven Airport Ranking List<\/a><\/li>\n<\/ol>\n

    Why are we doing this?<\/b><\/h2>\n

    Each year, the Lexalytics, an Pearl-Plaza company, marketing team sets some time\u00a0aside for an offsite meet-up. This time, fresh off of some awful layovers and baggage nightmares, we got to talking about airports and the experience of traveling. <\/span><\/p>\n

    Some questions arose: <\/span><\/p>\n

    Which airports should we fly through next time? Where should we avoid?<\/span><\/em><\/p>\n

    It didn’t take long to\u00a0find dozens of listicles<\/a>, news articles<\/a>, interest pieces<\/a>, and\u00a0blogs<\/a>. Each one claimed to be the “definitive guide” to American airports. But then we realized that none of them agreed with each other.<\/p>\n

    Who should we trust? We couldn’t even agree on that.<\/p>\n

    Clearly, we weren’t going to find a definitive list on American airports by Googling. So, why not make it ourselves? <\/span><\/p>\n

    We already had the perfect data analytics tool at our disposal powered by\u00a0text analytics<\/a> and machine learning <\/a>with intuitive dashboards that helped us quickly cut through the noise to gain rich, interesting insights.\u00a0<\/span><\/p>\n

    869,973 words, 30,000 travelers, 10 airports<\/h2>\n

    Of course, our first step was to gather a data set.<\/p>\n

    In total, we analyzed\u00a0869,973 words from Facebook reviews left by more than 30,000 real travelers at\u00a0America’s top 10 busiest airports.\u00a0<\/span>This 10-part blog series\u00a0<\/span>details our findings for each airport. <\/span><\/p>\n

    (Shoutout to Gensler<\/a>, the airport architecture and planning firm, our strategic partner for this project.)<\/span><\/p>\n

    \"[AtlantaAirportSentimentCloud.png]\"
    Sentiment-colored word cloud generated from Atlanta airport reviews<\/figcaption><\/figure>Remember, these dashboards don’t represent the opinions of journalists or travel bloggers.\u00a0Instead, they showcase actual insights gleaned from over 30,000 real travelers.\u00a0<\/span><\/p>\n

    Real<\/i> feedback from\u00a0real<\/i> people who use these facilities every day, written in their<\/em>\u00a0words.<\/span><\/p>\n

    This is data-driven\u00a0voice of customer<\/a>\u00a0in action.\u00a0The result?\u00a0Deeper insights and much more nuance than a simple star rating or NPS survey.<\/span><\/p>\n

    What’s more, in this series we take you behind the scenes. We show you the steps involved in analyzing these airport reviews, and how each airport in question can use these insights to create better traveler experiences, reduce costs, and increase revenue.<\/span><\/p>\n

    First insights after analyzing airport reviews<\/b><\/h2>\n

    Right off the bat, our new airport review analytics project delivered some very interesting insights. <\/span><\/p>\n

    For example, going into this project we noticed that San Francisco International<\/a>\u00a0rarely makes it into airport quality listicles. <\/span><\/p>\n

    But when we analyzed Facebook reviews in Semantria Storage and Visualization, we found that many travelers praise SFO as one of the finest airports in America.<\/span><\/p>\n

    \"\"
    Sentiment surrounding SFO wayfinding trends positive over time<\/figcaption><\/figure><\/p>\n

    Why does the travel industry ignore\u00a0San Francisco\u2019s airport when it’s so well-reviewed by customers? <\/span><\/p>\n

    Using industry packs for instant configuration<\/b><\/h2>\n

    One more cool side-note before we get started.<\/span><\/p>\n

    At first, every analysis we conducted told us that \u201csecurity\u201d rated positively. This came as a surprise: getting through security at the airport is not exactly a low-stress endeavor.<\/span><\/p>\n

    But after activating Lexalytics’\u00a0<\/span>airline industry pack configuration<\/span><\/a>, security went from bright green<\/span> to dark red<\/span>. That is, the sentiment weight dropped from a net positive to a net negative. <\/span><\/p>\n

    The airline industry pack allows me to see the conversation within the unique context of the airline industry. Enabling this industry configuration was as easy as selecting the expiration date for a credit card. I selected it from a drop-down menu, and that was it.\u00a0<\/span><\/p>\n

    Airport series: using NLP to analyze airport reviews<\/h2>\n

    This series goes alphabetically, airport by airport, to unleash the\u00a0collective voice<\/a> of America’s airport customers.\u00a0<\/span><\/p>\n

    First up in our series is the busiest airport in the world:\u00a0<\/span>Atlanta<\/span>\u00a0International Airport<\/a>, which has a big problem with “wayfinding”.<\/p>\n

      \n
    1. Atlanta International<\/a>\u00a0has a big problem with “wayfinding”<\/li>\n
    2. Charlotte Douglas<\/a> can profit big by listening to their customers<\/li>\n
    3. Chicago O’Hare<\/a> needs to learn about viral reputation management<\/li>\n
    4. Dallas\/Fort Worth<\/a> has a dirty secret<\/li>\n
    5. Denver International<\/a> may be a secret haven for the Illuminati<\/li>\n
    6. New York’s JFK<\/a> has to plan for the future<\/li>\n
    7. Las Vegas McCarran<\/a> doesn’t shy away from your vices<\/li>\n
    8. San Francisco<\/a> can teach us about listening to customers<\/li>\n
    9. Seattle-Tacoma<\/a>\u00a0has a vocal customer named Jerry<\/li>\n
    10. Los Angeles<\/a> needs to master the “final mile”<\/li>\n
    11. Summary: The Definitive Data-Driven Airport Ranking List<\/a><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

      We used cutting-edge\u00a0natural language processing (NLP) and\u00a0sentiment analysis software to analyze thousands of airport reviews. Here’s what we found.<\/p>\n","protected":false},"author":9,"featured_media":41035,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1],"tags":[830],"industry":[],"class_list":["post-41032","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-general","tag-lexalytics"],"acf":[],"_links":{"self":[{"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/posts\/41032","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/comments?post=41032"}],"version-history":[{"count":0,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/posts\/41032\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/media\/41035"}],"wp:attachment":[{"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/media?parent=41032"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/categories?post=41032"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/tags?post=41032"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/inmoment.com\/wp-json\/wp\/v2\/industry?post=41032"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}