Icon

competition_​final

Finally we use Sentiment Analysis to analyze the feelings of those who write the comments, in this way we aim to study the validity of our hypotheses on human reactions to nuditycoefficient that may prove to be of interest for firms' marketing sector.passAfter some data processing in the metanodes we pass to test each hypothesis separately, even though the process is quite similar : we normalize predictors; then we apply abinomial linear regression to test the model and finally we look at the resulting graphs As the files we used were particularly heavy,we are including here the link for a drive withall the files:Google drive link: https://drive.google.com/drive/folders/1nv-i2sbHfSiHH16uLbQ9LDp74DewjGal?usp=sharing CalculateNudity coefficientNormailze all variablesexcept for response(number of likes)Negative binomialregressionNudity coefficienton number of likesmediated by luxuryNormailze all variablesexcept for response(negativity of comments)Nudity coefficienton negativity incomments mediatedby luxuryNegative binomialregressionExtract data frombrands tablesVader to analyzesentiment ofcommentsJoining table withcorrespondingcomments' sentimentNode 965LinearregressionNudity coefficienton engagement ratemediated by luxuryNormailze all variablesexcept for response(engagement rate)Nudity coefficienton positivity incomments mediatedby luxuryNormailze all variablesexcept for response(positivity of comments)Negative binomialregressionNudity coefficienton general feeling incomments mediatedby luxuryNormailze all variablesexcept for response(general feelingof comments)LinearregressionNode 979CNN Normalizer Table to R R View (Workspace) Normalizer R View (Workspace) Table to R Data extraction Python Script Joiner RowID Math Formula Table to R R View (Workspace) Normalizer R View (Workspace) Normalizer Table to R R View (Workspace) Normalizer Table to R Table to R Finally we use Sentiment Analysis to analyze the feelings of those who write the comments, in this way we aim to study the validity of our hypotheses on human reactions to nuditycoefficient that may prove to be of interest for firms' marketing sector.passAfter some data processing in the metanodes we pass to test each hypothesis separately, even though the process is quite similar : we normalize predictors; then we apply abinomial linear regression to test the model and finally we look at the resulting graphs As the files we used were particularly heavy,we are including here the link for a drive withall the files:Google drive link: https://drive.google.com/drive/folders/1nv-i2sbHfSiHH16uLbQ9LDp74DewjGal?usp=sharing CalculateNudity coefficientNormailze all variablesexcept for response(number of likes)Negative binomialregressionNudity coefficienton number of likesmediated by luxuryNormailze all variablesexcept for response(negativity of comments)Nudity coefficienton negativity incomments mediatedby luxuryNegative binomialregressionExtract data frombrands tablesVader to analyzesentiment ofcommentsJoining table withcorrespondingcomments' sentimentNode 965LinearregressionNudity coefficienton engagement ratemediated by luxuryNormailze all variablesexcept for response(engagement rate)Nudity coefficienton positivity incomments mediatedby luxuryNormailze all variablesexcept for response(positivity of comments)Negative binomialregressionNudity coefficienton general feeling incomments mediatedby luxuryNormailze all variablesexcept for response(general feelingof comments)LinearregressionNode 979CNN Normalizer Table to R R View (Workspace) Normalizer R View (Workspace) Table to R Data extraction Python Script Joiner RowID Math Formula Table to R R View (Workspace) Normalizer R View (Workspace) Normalizer Table to R R View (Workspace) Normalizer Table to R Table to R

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: LORENZO
Created at: 2021-11-17
On NodePit since: 2021-12-07
Last update: 2024-11-21
Created with KNIME version: v4.5.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!