Posts Tagged: Customer feedback analysis

Part 4: Topic Modelling, an approach to Text Analytics

This is the 4th article in my series of Text Analytics posts explaining popular approaches to feedback analysis. Last week, we talked about text categorization, a Machine Learning approach that requires training data. We concluded that it can’t detect emerging themes in people’s feedback and that it’s only as accurate as the supplied training data. Today, we’ll discuss topic modelling, also a Machine Learning approach, but an unsupervised one, which means that this approach learns…

Read More

Why US airlines rank best or worst, according to passengers

Last week, ThePointsGuy published the 2018 “The Best And Worst Airlines In America”. According to Forbes’ interview with Brian Kelly, the author of the report, 9 airlines were reviewed using 10 objective criteria. Here, we extend this report by adding the element of customer perception according to online reviews.

Read More

3 Best Practices for Coding Open-Ended Questions

Open-ended survey questions often provide the most useful insights, but if you are dealing with hundreds or thousands of answers, summarising them will give you the biggest headache. The answer lies in coding open-ended questions. This means assigning one or more categories (also called codes) to each response. But how to go about it?

Read More

Sarcasm in Customer Feedback – How common is it?

Most people believe that text analytics solutions fail because sarcasm in customer feedback is very common. Somebody writes “Great service, yeah right!” and the dumb algorithm tags it as positive. So, whenever I speak on text analytics, someone in the audience will always ask: But how do you deal with sarcasm?

Read More

Actionable insights: can data analysis software deliver them?

When it comes to making sense of data, getting actionable insights is the holy grail. But what does this even mean? When is a finding an insight? When is an insight actionable? Can data analysis deliver them? Let’s get to the bottom of this by looking at some examples. Imagine, you have conducted a survey of 100,000 students, and you seek actionable insights for what to improve at a university. Non-insightful vs. Insightful Knowledge Non-insightful…

Read More

Top 3 reasons why most NLP fails

Understanding customer comments, on a large scale, needs to be automated. So, it requires Natural Language Processing (NLP) or Text Analytics. Unfortunately, most open-source NLP tools were developed on text researchers have easy access to. These are typically news articles, research papers and movie reviews. I learned that the analysis of customer comments is quite different, and here is why.

Read More

The rise and fall of open-ended questions

Recently I had an interesting discussion with Ron Stroeven, one the founders of Infotools, about open-enders, short for open-ended questions. In 1990 Infotools was established, but Ron has worked in market research far longer than that. He has a wealth of experience in survey design and data analysis, so it was fascinating to hear his view on open-enders, their history, and future.

Read More

Accuracy study – coding open-ended questions in a Net Promoter Score survey

Four people and several automated solutions were tested on a task of coding open-ended questions in a Net Promoter Score (NPS) survey. Their task: figure out the five key reasons behind an NPS survey and the five areas that could be improved. Here, we compare their performance using an academic metric of consistency. 250 students at a Swiss business school responded to a classical NPS survey with a scale question How likely are you to recommend the…

Read More

  • 1
  • 2
Customer Experience Update