The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

Analyze Text from Survey Answers

LvbuilderLvbuilder Member Posts: 2 Learner I
in Help

I'm looking to analyze survey answers I received  (attached). It is the essay type answers that need help.

There were four questions that asked about technology, financing, monthly costs and one open-ended question. There is about 120 answers to each question and I'd like to get results summarized by the industry that answered. For example...government employees hated technology, while business owners loved it, and zoologists were neutral.

I'd also like to capture themes if they exist. Such as the business owners who loved technology also said 3D printing was the solution, while zoologists said technology might be OK, but the cost really needs to come down first.

The answers aren't long (about 40 pages of reading total), so I can just read them to do this, but learning a new software skill would be great. I did get the main spreadsheet loaded just fine and the data is there (just two columns, the industry and the answer). I did get #of answers by industry and the Wordcloud to work, but the Wordcloud was a mess and didn't pull words from the answers, it just plotted the answers.

So far, I must not have located the right video tutorials. Perhaps someone can point me in the direction of a good one you have for this concept (analyze essay answers)? I searched the questions here and found some answers, but they seemed tooo complex for this simple operation. 

In the end visualization would be great as well, but not essential. We are trying to communicate the info to people in the main field, but who may not have knowledge in this subset of the field. Make sense?

Thanks in advance for your input.

Kelly

Best Answer

  • MarcoBarradasMarcoBarradas Administrator, Employee-RapidMiner, RapidMiner Certified Analyst, Member Posts: 272 Unicorn
    Solution Accepted
    Hi @Lvbuilder

    Please try to load any of our Community Samples that have examples on how to achieve what you want.
    //Community Samples/Community Data Science/Topic Classification of Audit PDFs

    you'll find them under 


    For your use case you'll need learn about text mining and for that you can take our free course. 
    https://academy.rapidminer.com/catalog?query=text

    Hope this helps you get started.

Answers

  • kaymankayman Member Posts: 662 Unicorn
    There are a few starters on the rapidminer academy

    use https://academy.rapidminer.com/pages/content-library and filter on 'text', this should give some good results already
  • LvbuilderLvbuilder Member Posts: 2 Learner I
    edited March 2022
    Thanks kayman. I appreciate the response. I've been all through the library and can't seem to figure out which one is best to use. It should be a very simple operation and I'm embarrassed that I can't figure it out. At this point I have just run though the essay answers with my brain and summarized that way.  Deadline to complete has passed. Thanks again.
Sign In or Register to comment.