{"id":12322,"date":"2013-05-20T16:59:25","date_gmt":"2013-05-20T15:59:25","guid":{"rendered":"http:\/\/timoelliott.com\/blog\/?p=5006"},"modified":"2013-05-20T16:59:25","modified_gmt":"2013-05-20T15:59:25","slug":"customized-voice-of-the-customer-analytics-using-sap-hana","status":"publish","type":"post","link":"https:\/\/timoelliott.com\/blog\/2013\/05\/customized-voice-of-the-customer-analytics-using-sap-hana.html","title":{"rendered":"Customized Voice of The Customer Analytics using SAP HANA"},"content":{"rendered":"

At SAPPHIRE NOW and ASUG 2013<\/a>,\u00a0 Mantis Technology Group<\/a> CEO Doug Turner<\/a> and Senior Consultant Jim Egan<\/a> gave a presentation explaining how they provide their customers with sophisticated, customizable \u201cvoice of the customer\u201d solutions, based on SAP\u2019s powerful text analysis technology.<\/p>\n

Their product, Mantis Pulse Analytics<\/a>, uses a combination of SAP BusinessObjects technologies to gather information from social feeds, analyze sentiment, and combine it with other corporate metrics to make the data actionable.<\/p>\n

\"image\"<\/p>\n

Voice of the Customer Analysis<\/h3>\n

There are lots of different sentiment analysis tools on the market, but many of them provide only shallow classification based on the presence of words like \u201cbad\u201d or \u201cgood\u201d in a tweet.<\/p>\n

Others, like SAP Social Media Analytics by NetBase<\/a>, are very powerful and easy to use, but are not primarily designed to flexibly combine information from both internal and external data sources. Mantis uses SAP\u2019s text analysis functionality to combine sentiment data with other information from the web, or from internal systems, to help make the data more actionable.<\/p>\n

Originally acquired from a company called Inxight, SAP\u2019s out-of-the box \u201centity extraction\u201d technology breaks documents down into sentences, then phrases, then concepts, and then sentiment analysis is applied to these concepts.<\/p>\n

Here\u2019s an example analysis on customer survey data from a cruise ship company:<\/p>\n

\"image\"<\/p>\n

Different social sources present a spectrum of different opportunities. Emoticon and acronym-filled teenage tweets may produce little useful sentiment information for a brand, while Facebook posts or entries on a customer feedback page are more likely to provide useful information, and a full customer survey (\u201cplease tell us what else we can do\u2026)\u201d will likely result in highly qualified, very clean information. Individual tweets can be processed very quickly, while entire documents naturally take much longer.<\/p>\n

Using Sentiment Data to Improve Business<\/h3>\n

The number one questions Mantis is asked is \u201cwhat do I do with sentiment data?\u201d — and the answer, of course, depends on the organization. It could be improving brand loyalty, customer service perception, or increase sales \u2013 the goal is to improve the metrics organizations currently use and take better advantage of information that is currently being ignored.<\/p>\n

Customers are now starting to expect the same level of response from a tweet or a post to a Facebook page as a call to your customer service center. If the tweet is ignored, it\u2019s like not picking up the call, with negative consequences to your brand image. The good news is that the most important signals are likely to be the clearest. If, as a consumer, I decide to purposely leverage social media to get the attention of a brand, then I\u2019m likely to use direct, easily understood language.<\/p>\n

Once the relevant information has been processed, it can be presented to customer service representatives in priority order:<\/p>\n

\"image\"<\/p>\n

The Mantis Pulse Analytics system lets users reply directly on social media, or integrate it into existing email-based service ticket systems:<\/p>\n

\"image\"<\/p>\n

Over time, analysis has become more sophisticated and customized to individual needs. Data is collected from more channels including custom sources such as web surveys and information about particularly influential social media users. Existing CRM customer records can be expanded to include social media profile information.<\/p>\n

Time-based correlation analysis allows the comparison of sentiment with things like sales promotions. This helps make the information more actionable. The example below shows sentiment combined with Google Analytics web metrics to show the correlation and success of a marketing campaign by different social channels.<\/p>\n

\"image\"<\/p>\n

Other examples of Mantis Pulse reporting:<\/p>\n

\"products_pulse_tile4\"<\/p>\n

\"products_pulse_tile3\"<\/p>\n

\"products_pulse_tile2\"<\/p>\n

\"products_pulse_tile1\"<\/p>\n

 <\/p>\n

The Challenges of Sentiment Analysis<\/h3>\n

Examples of problems and issues encountered by Mantis (if you\u2019re interested in the subject, you should read articles by Seth Grimes of Alta Plana<\/a>, and see presentations from the Sentiment Analysis Symposium<\/a> he organizes each year)<\/p>\n