Step 1: Select a type of visualisation:

Support Vector Machine Logistic Regression Decision Tree Naive Bayes K-NearestNeighbor

Criterion:

? Entropy and Gini are two criterions for decision tree model based on different principles. Entropy works better when datasets are not big enough Entropy Gini

Type of NB:

? Use different probability distribution models(Gaussian distribution and Bernoulli distribution). Estimate Gaussian distribution does better on successive datasets and Bernoulli distribution does well in datasets which are have binary tendency Gaussian Bernoulli

Regularization C:

? Inverse of regularization strength; must be a positive float. Like in support vector machines, smaller values specify stronger regularization.

Input a minimum K you want to choose

? Give the minimum K and maximum K you want to use in KNN. A gridsearch will perform to find the best K in your range

max_depth:

? Remember that the number of samples required to populate the tree doubles for each additional level the tree grows to. Use max_depth to control the size of the tree to prevent overfitting.

Input a maximum K you want to choose

Parameter reference Parameter reference Parameter reference Parameter reference

Step 2: Choose a name for your model:

Step 3: Choose the speaker for your data:

Select the speaker for the first category:

first speaker second speaker

Select the speaker for the second category:

first speaker second speaker

Step 4: Select features for training(at least one feature):

Average Time Gaps Between Each Speaker
Average Words Per Minute
Average Time Per Turn
Average Words Per Turn
Total Speaking Time of the Speaker
Total Turns of the Conversation

Step 1: Select a type of model:

Box plot OLS 3D

Select Feature For Your 1st Visualisation Figure: (Chart 1 on the left, Chart 2 on the right)

Submit

Select Feature For Your 1st Visualisation Figure: (Chart 1 on the left, Chart 2 on the right)

Submit

Select Feature For Your 1st Visualisation Figure: (Chart 1 on the left, Chart 2 on the right)

Submit