A computational analysis of poetic style (original) (raw)
Related papers
A Computational Analysis of Style, Affect, and Imagery in Contemporary Poetry
2012
What makes a poem beautiful? We use computational methods to compare the stylistic and content features employed by awardwinning poets and amateur poets. Building upon existing techniques designed to quantitatively analyze style and affect in texts, we examined elements of poetic craft such as diction, sound devices, emotive language, and imagery. Results showed that the most important indicator of high-quality poetry we could detect was the frequency of references to concrete objects. This result highlights the influence of Imagism in contemporary professional poetry, and suggests that concreteness may be one of the most appealing features of poetry to the modern aesthetic. We also report on other features that characterize high-quality poetry and argue that methods from computational linguistics may provide important insights into the analysis of beauty in verbal art.
Predicting and Classifying the Poetic Quality of the Early and the Late Generation of Romantics: A Computational Stylistic Study, 2023
Poetic quality is an important value for a poet’s literary craft, and it is considered as a cultural heritage of a society. Poetry is made with language and poets use language features in a particular way to create effects and to convey meaning. Measuring poetic quality would appear to be an intrinsically qualitative endeavor. However, it is possible to objectify some of the language features to some degree using a quantitative criterion, which is here proposed. The study represents a preliminary literary computational approach in relation to Romantic poetry which is dominated by a few names: William Blake, William Wordsworth, Samuel Taylor Coleridge, Percy Bysshe Shelley, John Keats, and Lord Byron. There has been little or no research with literary computing techniques focused on measuring and classifying the quality levels of those poets’ works. The study builds on a set of ten measurable stylistic features extracted from one hundred and eight poems regardless of genre or subject. The study carries out an analysis using Binary Logistic Regression Modeling (BLRM) as one of the most commonly used predictive modeling techniques. I used the stylistic features as predictive variables and the quality as the outcome variable indicative of the stylistic characteristics of each of the poems selected. In this way, this study is able to measure the stylistic features in the selected poems and, independently, using Binary Logistic Regression to predict the general poetic quality levels for each of the poets examined. The study is also able to make connections between some of the poets which enabled a more detailed view of the subcomponents’ usage and occurrence in the poems.
A Computational Approach to Style in American Poetry
2007
Abstract We develop a quantitative method to assess the style of American poems and to visualize a collection of poems in relation to one another. Qualitative poetry criticism helped guide our development of metrics that analyze various orthographic, syntactic, and phonemic features. These features are used to discover comprehensive stylistic information from a poem's multi-layered latent structure, and to compute distances between poems in this space. Visualizations provide ready access to the analytical components.
Computational Analysis of the Historical Changes in Poetry and Prose
Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, 2019
The esoteric definitions of poetry are insufficient in enveloping the changes in poetry that the age of mechanical reproduction has witnessed with the widespread proliferation of the use of digital media and artificial intelligence. They are also insufficient in distinguishing between prose and poetry, as the content of both prose and poetry can be poetic. Using quotes as prose considering their poetic, context-free and celebrated nature, stylistic differences between poetry and prose are delved into. Grammar and meter are justified as distinguishing features. Datasets of popular prose and poetry spanning across 1870-1920 and 1970-2019 have been created, and multiple experiments have been conducted to prove that prose and poetry in the latter period are more alike than they were in the former. The accuracy of classification of poetry and prose of 1970-2019 is significantly lesser than that of 1870-1920, thereby proving the convergence of poetry and prose.
Pops and Flops: Some Properties of Famous English Poems
Empirical Studies of the Arts, 2000
This paper describes a preliminary study of linguistic attributes that differentiate popular from obscure poems in English. Following in the footsteps of , and others, frequency of appearance in anthologies was used as an index of poetic popularity. Twenty general anthologies published between 1966 and 1997 were selected and all poems appearing in more than five of them were taken as a reference sample. This gave 85 poems by 54 different authors. (The two most popular were Matthew Arnold's Dover Beach with 16 occurrences and Kubla Khan by Samuel T. Coleridge with 15.)
On the Direction of 19th Century Poetic Style, Underwood and Sellers 2015
Underwood and Sellers have discovered that over the course of roughly a century (1820-1919) Anglo-American poetry has undergone a consistent change in style in a direction favored by editors and reviewers of elite journals. This directional shift aligns with the one Matthew Jockers found in Anglophone novels during roughly the same period (from the beginning of the 19th century to its end). I argue that this change is characteristic of a cultural evolutionary process and sketch a way to simulate such a process as an interaction between a population of texts and a population of writers. I suggest that such directionality is a sign of autonomy in the aesthetic system, that it is not completely coupled to and subsumed by surrounding historical events.
Quantitative Analysis of Style in Mihai Eminescu's Poetry
Studia Universitatis Babeș-Bolyai Informatica, 2019
Quantitative stylistic methods aim to express certain aspects of a text in numeric form, thus allowing the introduction of fast, powerful and accurate computational approaches for analysis. While in the case of literature, the validity and usefulness of such studies is highly controversial, one cannot deny the opportunities brought forward by computational methods: first, the exploration of large sets of documents in search of patterns otherwise difficult to discover by human readers; second, the possibility of opening up new perspectives by uncovering latent features of texts. In this study, we investigate the poetic work of one of the most important Romanian poets, Mihai Eminescu, through a variety of quantitative methods addressing lexical, morphological, semantic and emotional aspects of text. We propose a comparison between the results of the computational approach and established interpretations of Eminescu's work in order to assess the viability of computational methods in poetic style studies.