f SetuServ

We synthesize text conversations like nobody else does!

Sign up for a FREE demo
Name
Email
Contact Number
Company
Industry
Thank you! We will get back to you soon.

Archive for Social Media Synthesis

Unrealistic Expectations from Text Analytics Tools

Our last blog described how organizations can improve their Net Promoter ScoreTM by analyzing verbatim responses. In fact, today organizations have a wealth of information in various text data sources such as customer complaints, reviews and social media conversations. Most customer centric organizations deploy text analytics tools to glean actionable insights. But, still if you ask any analyst that “How often were you stuck with text analytics tools, and had to massage the data manually?” the answer would most often be, “Almost always.” And the underlying reason for this is the complicated and contextual nature of text analytics itself.

 

KeyFor example, an airline that used a leading text analytics tool to mine customer complaints had “upgrade to business class” as a key theme. However, this theme is not specific enough to drive any Action. It is unclear whether the customers complained about “upgrades that were cancelled” or “inability to use miles for upgrades” or were simply saying that the “upgrades are expensive”. Each of these specific themes would demand different action and it is very difficult for a software to extract insights at this level of specificity.

 

KeyAlso, accuracy is often a concern with text analytics tools as they can’t adequately interpret the context and nuance of human language. For example, as Andrew Wilson rightly noted in this article , most of today’s text analytics tools would classify the following statement as a negative comment about the Scion: “With the supercharger included on my Scion, it is one bad machine,” not being able to recognize the colloquial use of the word “bad” to actually mean “good”.

 

While specificity is needed to make the themes actionable, accuracy is needed to act with confidence (especially when the action is at a micro level). At the current rate of Natural Language Processing (NLP) technology advancement, it will be decades before technology evolves to the level of human interpretation. As a result, leading technology companies like Google and IBM have increasingly relied on humans to train, evaluate, edit or correct an algorithm’s work, as explained in this article in the New York times.

 

Organizations need to understand where NLP works best and where it doesn’t so that human review can be used to complement NLP. Because human review becomes expensive and time consuming as the scale increases, it is very important to optimize the combination of NLP and human review so that it is scalable & cost effective.

 

If you want to learn more about how SetuServ deploys this optimized solution for it’s clients, please visit us at our website www.setuserv.com or click here for a case study on synthesizing reviews.

Posted in: Social Media Synthesis, Survey Synthesis

Leave a Comment (0) →

Which Tweets work best?

Organizations are increasingly seeking to engage with customers on social media. A challenge for organizations is choosing the kinds of messages that drive the most engagement. We recently analyzed the social media presence of some ad agencies, with a special focus on Twitter and derived insights that shed light on the issue.
 
The findings show that the tweets containing links to pictures and tweets on events, promotions and awards generate the highest customer engagement, as measured by the retweet ratio. Tweets containing hashtags, non-picture URLs, scientific research also have a retweet ratio that is better than the average.
 

 
  This trend was consistently true for each twitter stream from each of the 7 agencies  
 

An interesting finding was that, InTouch’s picture URL’s had an exceptionally high retweet ratio, as seen in the graph above. This may be driven by the fact that the pictures contained photos of executives and movie/sport stars.
 
To obtain these results, we at SetuServ analyzed about 15,000 tweets, from various agencies. SetuServ deployed its unique Skierarchy approach to Natural Language Processing that combines machine learning with human curation. Our approach allows us to glean insights with accuracy and granularity not possible with other solutions. Finding the right balance between machine learning and human curation is essential in getting accurate insights from text data. At SetuServ we believe we’ve done just that.
 
For more information, check us out at www.setuserv.com or call us at 312-823-4300.

Posted in: Social Media Synthesis

Leave a Comment (0) →

Thank you!!

We will get back shortly
Talk to us
Name
Email
Contact Number
Comments