AI News, Webinar on Open Ended Survey Analysis using Machine Learning
Webinar on Open Ended Survey Analysis using Machine Learning
Webinars always play a vital role in understanding a product and the technology used behind it which will educate users to learn WHAT, WHY and HOW about any technology and product.
Now analyzing digital and social media is not restricted to just basic sentiment analysis and count based metrics.
We believe it is important to classify incoming customer conversation about a brand based on following lines: You can read here more about Contextual Semantic Search, the Machine Learning technology behind Open Ended Survey Analysis.
What Data Scientists Can Learn From Qualitative Research
Open-ended survey questions often provide the most useful insights, but if you are dealing with hundreds or thousands of people’s answers, summarising them will give you the biggest headache.
If you don’t have a qualitative research background, this article will help you learn the best practices from people who have been working with text, also referred to as qualitative data, for decades.
From text to codes to analysis When terms like ‘big data’ are thrown around they almost always refer to quantitative data: data that can be easily expressed as numbers or categories.
The NPS score, calculated from numeric answers to ‘How likely on a scale from 0 to 9 are you to recommend us to friend or family?’ will give you a single measure of company’s performance.
Each of the responses is known as a verbatim.‘Coding’ or ‘tagging’ each response with one or more codes helps capture what the response is about, and in turn summarise the results of the entire survey effectively.
If we compare coding to NLP methods for analysing text, in some cases coding can be similar to text categorisation and in others to keyword extraction.
We often refer to how to perform the task manually, but if you are looking at using an automatic solution, this knowledge will help you understand what matters and how to choose an approach that’s effective.
If the top level code describes what the response is about, a mid level code can describe if it is positive or negative and a third level the attribute or specific theme.
For example, a code ‘cleanliness’ could cover responses mentioning words like ‘clean’, ‘tidy’, ‘dirty’, ‘dusty’ and phrases like ‘looked like a dump’, ‘could eat of the floor’.
Having many codes, particularly in a flat frame, makes it harder as there can be ambiguity and sometimes it isn’t clear what exactly a response mean.
This has the benefit that you can guarantee the items you are interested in will be covered but you need to be careful of bias.When you use a pre-existing coding frame, you are starting with a bias as to what the answers could be and might miss themes that would emerge naturally from people’s responses.
The process for this is iterative: If you happen to add a new code, split an existing code into two, or change its description, make sure to review codes of all responses that could be affected.
How to analyze open-ended survey questions
However, this article is about analysis, not survey design, so from here on we’ll assume you’re making great surveys and focus on analyzing the data you collect.
boolean yes / no, multiple choice, Likert scale) then your analysis should be a fairly straightforward game of crunching numbers, and there are plenty of articles on the web that talk about analyzing quantitative data with formulas in spreadsheets.
In this article we’ll give a basic overview of how to analyze qualitative data in layman’s terms, and offer a few suggestions on how to get better insights from open-ended survey questions, while making your life easier.
If most people told you they’d rather fight one horse-sized duck instead of 100 duck-sized horses, how would that information change your product?
Other uses for qualitative data analysis include analysis of competitors, industry trends, customer interview transcripts, user testing notes, and of course analyzing survey results.
After someone’s order is delivered, they’re emailed a survey which asks them a few open-ended questions like “How was your delivery experience?” and “What can we improve for next time?” Imagine this is one of the answers to the first question: The delivery driver was two hours late.
Most survey software is built to help you collect a lot of data, but they usually have few features to help you make sense of the data you’ve collected.
Eventually you might discover that the caller ID problem isn’t a common complaint (only 5 people out of 2000 mentioned that in the past month), but late drivers certainly is (340 / 2000 in the past month).
Pattern-recognition allows animals to do cool stuff like create cognitive maps of the environment, distinguish individuals and their emotional state based on facial features, and use gestures to communicate with others.
The cognitive repertoire of humans far exceeds that of animals, and gives humans creativity and invention, spoken and written languages, reasoning and rapid decision-making, imagination and mental time travel, and magical thinking &
This works okay, however it’s prone to mistakes because the context is missing—the word “late” alone could be used in a variety of contexts—and there are many ways to describe a late driver without using that particular keyword, for example “not on time” or “delayed delivery”.
As well as the training data requirement, machine learning systems are difficult to set up, so most user researchers outside of huge companies or academia ultimately resort to analyzing qualitative data manually.
- On Sunday, March 24, 2019
Webinar: Introduction to SPSS Text Analytics
If you have questions or comments on the content of this video, please email us at email@example.com What can we do with our textual survey data? How can ...
Introduction to NHSN Dialysis Event Webinar, September 2016
Training Objectives 1. Edit the NHSN Monthly Reporting Plan to show your outpatient hemodialysis facility is participating in Dialysis Event Surveillance. 2.
How Dialogflow Enterprise Edition Can Transform the Enterprise Contact Center (Cloud Next '18)
How many times have you repeatedly dialed 0 or shouted “representative” when faced with a poor IVR experience? Automated phone agents and chatbots have ...
Introduction to Quantitative Data Analysis
A First Leximancer 4.5 Analysis
This video shows how to perform a basic automatic content analysis using the Leximancer version 4.5 software.
How to Find Product Market Fit - CS183F
Peter Reinhardt, co-founder and CEO of Segment, shares his experience on finding product market fit.
Enrich Your Research with Open Text Analysis
Data analysis Part 1
Keynote (Google I/O '18)
Learn about the latest product and platform innovations at Google in a Keynote led by Sundar Pichai. This video is also subtitled in Chinese, Indonesian, Italian, ...
SOLUTIONS SHOWCASE - Kensho on GCP: Machine Learning in your Browser
Recorded on Mar 24 2016 at GCP NEXT 2016 in San Francisco. Financial services is an information industry at its heart. Kensho and GCP bring high-end ...