MALAYALAM LANGUAGE (MIX CODE) Recipe channels Youtube Comments

The dataset used for performing Text Classification is a combination of two different datasets scrapped from the comment section of two Youtube channels namely "Veen's Curryworld" and "Lekshmi Nair". The data is extracted using the YouTube API and contains two atrributes namely “text” and “label” where the former contains the comments and later contains the corresponding label. The comments are classified into 7 labels:

- Label 1: Gratitude

- Label 2: About the recipe

- Label 3: About the video

- Label 4: Praising

- Label 5: Hybrid

- Label 6: Undefined

- Label 7: Suggestions and Queries

The number of instances in each category is listed below:

- Label 1: 484

- Label 2: 396

- Label 3: 300

- Label 4: 362

- Label 5: 249

- Label 6: 2062

- Label 7: 438