Expand +



Listen. Understand. Take Action.

by Rebecca Newell | SAPinsider

April 1, 2012

Information found in social media channels can be extremely valuable to a business, but the amount of time needed to comb through the web in search of this data is out of most people’s reach. And early automated solutions built to mine this information have fallen flat, unable to account for the context that gives data its meaning. In this article, you’ll learn how the SAP Social Media Analytics application by NetBase can help businesses gauge consumer sentiment in real time.

People of all ages and backgrounds are updating statuses on Facebook, following associates on Twitter, commenting on blog posts, and gathering in forums to chat about everything from diapers, to sports, to enterprise software. Within this surge of social media information, there are people talking specifically about your company, products, and market dynamics.

This information is extremely valuable and can enable your business to stay in tune with customer sentiment and opinion, whether it is positive, negative, or somewhere in between. Unfortunately, it can be difficult to track information in the social media world and often requires hours of manual searches and categorization efforts. Not many of us can dedicate this amount of time solely to combing through the web, regardless of the potential benefits for our business. So this wealth of knowledge remains untapped.

However, the right tool — one that will automatically locate and analyze information that pertains specifically to your company from various social media sites — can change all that.

Track Net Sentiment

The SAP Social Media Analytics application by NetBase is an on-demand, subscription-based solution that businesses can use to gauge consumer sentiment in real time. With it, users can enter any topic in the application and see a summary of that topic’s net sentiment. This allows business analysts and marketers to instantly extract actual customer perceptions from terabytes of social media chatter. The application helps you understand what customers love (and hate) about brands, categories, issues, and trends. You can also receive scorecards that let you stay on top of three key metrics — buzz, net sentiment, and passion intensity — so you can respond to changing conditions faster (see Figure 1). With SAP Social Media Analytics, companies can:

  • Monitor brand health more frequently and with fewer resources
  • Understand more than just positive and negative sentiment, with visibility into the behavior and emotion expressed by consumers
  • Gauge the social media impact of marketing campaigns and events
  • Track awareness of external risks, such as social media awareness of health issues associated with an ingredient you may use in a product
  • Track consumer sentiment about competitors
  • Measure your brand equity

Figure 1 Buzz, net sentiment, and passion intensity displayed as a chart using SAP Social Media Analytics.

The Importance of Natural Language Processing

The social web is based on language, and language is messy. The introduction of one word can completely change the meaning expressed in a sentence. If you’re using a basic text analysis solution, it may not be tracking information accurately. The true meaning of a phrase can only be determined with deeper analysis by a sophisticated natural language processing (NLP) engine that understands every word and its context.

SAP Social Media Analytics uses such an engine to understand the nuances of language and correctly determine the expressed sentiment, extracting insights such as behaviors (buy, want, return), emotions (love, hate), and the intensity of emotions (adore, despise). It does this by breaking down the sentence structure and analyzing the context of the complete sentence (see Figure 2).

Figure 2 SAP Social Media Analytics tracks and breaks down customer opinions using a natural language processing engine to correctly determine the complex meaning of sentences.

For example, “The iPhone has never been good” is a negative statement even though it uses the word “good.” “The iPhone has never been this good,” however, is positive. In the sentence, “I like using my iPhone, but I hate the way that applications work on the Droid,” the words “iPhone” and “hate” occur close together, but are not associated. If systems that use pattern matching judge sentiments using the keywords “good” and “hate” alone, they would be wrong more than half of the time.

The NLP engine within SAP Social Media Analytics reads and understands millions of social media postings every minute. For every sentence, it identifies and links the subjects, objects, verbs, adjectives, and other linguistic patterns. By analyzing each sentence, the NLP engine can account for the complexities in language that are at the root of sentence meaning. It also recognizes variations in modern language, such as urban words or slang (“My new phone is sick!”), alternative spellings (“luv,” “kewl,” or “gr8”), abbreviations (“IMHO” or “ttyl”), and common misspellings (“teh/the”).

Tap into the Potential

Tapping into the ever-growing stream of social media information can help you stay in tune with feedback about your company. Using SAP Social Media Analytics, you can track sentiment analysis; quickly discover market needs and trends; quantify customer perceptions about products, services, and companies; and operate as a customer-driven business. To learn more, visit


To hear Rebecca Newell discuss some of the ideas in this article in more detail, including the business value of net sentiment, listen to this online exclusive podcast.


Rebecca Newell ( has held executive-level marketing and business management positions for more than 20 years. Rebecca began her career in the world of technology at Intel, then continued on to Novell and 3Com before joining SAP. At SAP, she has developed comprehensive go-to-market strategies to drive success for the solution extension applications portfolio worldwide.

An email has been sent to:

More from SAPinsider


Please log in to post a comment.

No comments have been submitted on this article. Be the first to comment!