In service industries such as hospitality and gaming, the ability to capture, comprehendand act on guest or patron feedback is critical. Previously we learned from Kelly that user generated content from social review sites influences the purchase process for hotel rooms. Take a moment to think about how many times a hotel or casino interacts with their guests or patrons. With each of those interactions, there is the potential for data to be created. What better way to understand the wants, needs and preferences of guests and patrons than by mining that data?
But when it comes down to it - what percentage of the data generated by theseinteractions are you actually able to use? With so many channels for interaction, such as social media review sites and forums, guest profile comments, guest survey responses, call center logs and emails, whether internal or external, the amount of data can be overwhelming. One of the biggest challenges with feedback data is that the main insights are contained in unstructured text data, which can be complex and labor- intensive to gain insights from. But what if you could organize and visualize customer feedback data, would that help you quickly gain the insights that you needed?
The answer is yes. You can use a variety of analytic techniques to help you interpret orquantify unstructured text data, whether it is publically available or internally generated. The technique you choose should depend not only on the type of data involved, but also on the business problem you're trying to solve.
When it comes to social data, descriptive statistics can provides asnapshot of current or historical performance. This method is used to answer questions like: "How many followers? How many reviews have been posted over the last two weeks? What is my average rating across the major review sites? How many times did someone mention the word 'comfortable' in a review?" This type of analysis is most commonly found in reputation management applications or other applications that help hospitality and gaming companies monitor and respond to social activity.
Social network analysis identifies connections among users in asocial network, as well as the impact of the activity of those users. It also identifies interconnected groups of individuals and shows the influence each participant has within social networks. This technique was developed to identify fraud in the financial services and healthcare industries, but these days it's also used by marketers in the communications, retail and hospitality industries to identify those that are most influential to the purchase decision.
When you need to analyze and quantify unstructured text data, textanalytics is the best analytic option. Most text analytics procedures are based on some form of natural language processing (NLP). NLP is a methodology based on linguistics that uses both predictive analytics and rules-based processing to interpret the context and content of unstructured text documents. Within text analytics there are several types of methods that can be used on unstructured text data, whether it's internal, online or transcribed from voice. The three main categories of text analytics are:
- Content categorization. This identifies key topics and phrases in electronic text and sorts them into categories. It eliminates the manual work of reading and tagging documents, giving you much faster results. Text documents can be organized and tagged for search, making it easier to find, sort or process the content. This approach makes it easier to assign certain issues to specific departments that can resolve the issue. It also makes it easier for internal teams to find specific content stored in the text repositories.
- Text mining, which is similar to data mining. This method uncovers related concepts in large volumes of conversations. It surfaces key topics that can be used in future analyses, like predicting or understanding guest behavior.
- Sentiment analysis. This helps you understand guest opinions by applying NLP to the text documents. It identifies how your guests feel about key attributes of your product, brand or service – often in great detail.
Unstructured data can be notoriously complex, but applying text analytics makes it easyto filter, search and cross-reference this data. Hospitality and gaming companies have plenty to gain from a deeper understanding of their customers expressed need and preferences. Without text analytics, however, the time required to read and code all of that information can be highly prohibitive.