March 15, 2013 § Leave a comment
When we started thinking about text analysis, one of the issues we discussed was sentiment analysis. Lots of people have tried to figure this out and some companies claim a pretty high success rate using algorithms or other techniques.
Our feeling is that language is so complex and that the subtleties of things such as sarcasm make it really difficult to be very accurate. So we took a different approach to the problem. What if we leave the determination of sentiment up to real humans? If we do that, it simplifies the task to finding which comments to read.
CloudMR’s patent-pending algorithm sorts a list of comments in priority order. The comments most likely to resonate with other respondents are sorted at the top. If you want to know sentiment, just read the top comment for yourself. If you are feeling really energetic, read the first ten. Sentiment problem solved…
March 1, 2013 § Leave a comment
An Adaptive Survey® is a market research method that combines qualitative and quantitative research features. This unique combination allows researchers to speed up the research process by gathering ideas and prioritizing them in the same research project.
Adaptive Surveys are offered by CloudMR, Inc. and this blog is related to that company. The benefits of this technique…
- Systematically gather and prioritize open-ended text in a single project
- Replace dozens of traditional market research rating scales with a single Adaptive Question™
- Answer questions you didn’t even know to ask
- Get higher response rates since Adaptive Surveys® are short and conversational
- Add structure to unstructured data
- Prioritize ideas using any representative sample you choose
February 20, 2011 § Leave a comment
Lots of engineers around me are talking about sentiment analysis. Most of the market researchers I know are more than skeptical about it. I can see the allure of some sort of magical box that will automatically make sense of all of these verbatim comments, but for me it doesn’t really matter. Just give me the handful of comments that resonate with most of the respondents and I’ll read them myself – sentiment and all. That is what is so exciting about some of CloudMR’s early testing of their proprietary algorithm. It doesn’t include fancy text analyzers or extra complexity. It quickly generates a score for each comment and sorts them. Interestingly the early models stratify the comments and group like ideas all together. Since I can easily see that grouping, the algorithm is clearly doing something right and producing the top ideas. It will be fun to see this implemented over the next few weeks. Jeffrey Henning has an interesting post about this same issue from last summer.