"Sentiment analysis in Excel"

peter_attridgepeter_attridge Member Posts: 1 Learner I
edited June 2019 in Help

Hi Everyone,

I have 120 participants in a study (120 excel sheets in one file). Each row in the file is a line of text and I want to look at positive, negative, neutral comments in a subset of these files. Column A is the text, Column B is my Identifier (Block, Peg, Puzzle, Tea) which designates what activity they were doing. My idea is that I can get an analysis of each identifier and then a group of two of the identifiers together. However, I cannot seem to make this work.


1. Do I need to separate each identifier into its own Excel file and then run the analysis?

1A. If I want to combine identifiers do I do this for them as well?

2. Is there an easier way to do this that I am missing?


Thanks for the help!


  • Options
    Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    @peter_attridge Without seeing your data, you're probably going to have to loop over all the sheets in the Excel file and combine them into one data set and then feed them into a Process Documents operator and then maybe a Cross Validation operator with a Naive Bayes learners (as a first start). From there you can see how well it's classifying your sentiment labels. 

  • Options
    sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager

    hello @peter_attridge welcome to the community. It's hard for me to see exactly what you're doing without a sample data set. Is it possible to post either the actual one or a fake one just to see the format?


    Just to add to @Thomas_Ott's comment, there is a new operator in the Operator Toolbox called "Read Excel Sheet Names" which does, well, exactly what it says. You can then use the output of this operator in a Loop Values operator to go sheet by sheet with Read Excel.



Sign In or Register to comment.