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 November, 2014

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) →

5 secrets your Net Promoter Score (NPS™) can’t unlock

NPS surveys have been so successful, that the abbreviation needs no expansion in customer centric companies. The score provides several benefits. Its simplicity makes it easy to track, to disseminate to various parts of the organization and to compare against benchmarks.
 
However, what is still in its infancy is ACTION based on NPS. Recently, Jeremy, an analyst at an online retailer was faced with the same problem. His stakeholders were asking the dreaded “So what”? question followed by the even more dreaded “Why”? question. Jeremy’s stakeholders are not alone and analysts often don’t have answers.
 
Key
 
It may seem obvious that the answers lie in the treasure trove of textual verbatim responses within the survey. But most companies lack a systematic and thorough process to unleash the power of this information. A deliberate reading of these responses can provide several benefits. A few of them are :
 
DriversIdentify the drivers of the scores – By analyzing the verbatim comments, the company over a few quarters realized that “Deals available” and “Speed of delivery“ were disproportionately driving their Promoters

RouteTrack department-level performance- This has to be done carefully and only after data has been synthesized over periods of time. The company uses the score in conjunction with the text analysis as a metric for incentives for their departments

leaf graphicDecide priorities  - Companies can use this information to decide priorities. While cursory and superficial readings may identify the top 1 or 2 drivers the real value lies in identifying drivers that are easy to effect and that move the needle. The company realized that “limiting changes to their site”, though low on the totem poll of drivers, was an easy fix that satisfied a decent chunk of high rollers

leaf graphicClose the loop with customers - A customer who feels heard is more likely to be loyal than one who is not. And if their request or suggestion is on your product roadmap even better. While harder to implement at a B2C company, identifying the grouses of borderline Passives can provide insights into how to convert them to promoters

leaf graphicIdentify customers for follow up research -  While some priorities will be clear after synthesis of verbatim comments customers can be identified  for follow-up research as well as for tracking.
 
However, we must admit that reading through comments is a challenging task especially when volumes of verbatim exceed a few hundred sentences a quarter. In our next post we will discuss some of these challenges and pitfalls and how they could be overcome. If you want to learn more please visit us at our website www.setuserv.com or click here for another use case of NPS verbatim synthesis.
 

Posted in: Net Promoter Score, Survey Synthesis

Leave a Comment (0) →

Thank you!!

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