Exploratory Data Analysis of Urdu Poetry

The study presented here provides numerical insight into ghazal -- the most appreciated genre in Urdu poetry. Using 48,761 poetic works from 4,754 poets produced over a period of 800 years, this study explores the main features of Urdu ghazal that make it popular and admired more than other forms. A detailed explanation is provided as to the types of words used for expressing love, nature, birds, and flowers etc. Also considered is the way in which the poets addressed their loved ones in their poetry. The style of poetry is numerically analyzed using Multi Dimensional Scaling to reveal the lexical diversity and similarities/differences between the different poetic works that have drawn the attention of critics, such as Iqbal and Ghalib, Mir Taqi Mir and Mir Dard. The analysis produced here is particularly helpful for research in computational stylistics, neurocognitive poetics, and sentiment analysis.