Text Mining and Digital Humanities: Quantitative Analysis of African American Poetry

Primary Faculty Mentor’s Name

Seretha D. Williams

Proposal Track

Student

Session Format

Poster

Abstract

“Text Mining and Digital Humanities: Quantitative Analysis of African American Poetry” uses quantitative and qualitative analysis to formulate research questions about African American poetry. In this project, we use text-mining software to determine whether distinctive word patterns can be used to quantify the characteristics of African American poetry. For the purposes of this study, we rejected the notion that Black poetry is defined as poetry written by black authors. Instead, we argue, the distinctions in black poems should be specific enough to be classified in a separate category from other kinds of literature such as American literature, and we assert the definition of black poetry should not reduce “blackness”- what we describe as the shared cultural traditions or practices of African Americans- to certain experiences or tropes such as the rural, folk black experience.

We selected Langston Hughes and the Harlem Renaissance as the earliest historical point for our inquiry, and we used Margaret Walker, Gwendolyn Brooks, Maya Angelou, and Alice Walker, poets whom Hughes directly influenced, as comparisons. We created a text database of the collected poems of the five authors and assessed the frequency of words/phrases related to three main categories that recur in the scholarship of black poetry: memory, identity, and music. After running our text data through mining software and looking specifically for words coded as memory, identity, and music variables, we were able to support our initial claim that quantitative analysis can be used as to support qualitative assertions of black poetry as a distinct genre of American poetry.

The data collected from the first category, memory, yields some significant conclusions. Firstly, all of the poets frequently use the term blood. The recurrence of blood purports the connection that black poetry has to ancestry and heritage. It also points to a collective-consciousness among African-Americans. In addition to blood, death is another word that our poets frequently use. This heavy usage may indicate a link between black poetry and the historical oppression blacks have experienced.

The second data set, identity, reveals that race is an important component of identity for all of the writers. Terms relating to blackness appear numerous in the works of all the authors. Furthermore, the results suggest that the older poets, Hughes and Margaret Walker, connect naming to identity. In contrast, the younger poets place significantly less emphasis on this correlation.

The results yielded from the last category suggest that Hughes and Margaret Walker draw upon the trope of song more heavily than the other poets do. This usage attests to their reliance on the vernacular and oral tradition.

Keywords

digital, humanities, African-american, poetry

Award Consideration

1

Location

Concourse and Atrium

Presentation Year

2015

Start Date

11-7-2015 10:10 AM

End Date

11-7-2015 11:20 AM

Publication Type and Release Option

Presentation (Open Access)

This document is currently not available here.

Share

COinS
 
Nov 7th, 10:10 AM Nov 7th, 11:20 AM

Text Mining and Digital Humanities: Quantitative Analysis of African American Poetry

Concourse and Atrium

“Text Mining and Digital Humanities: Quantitative Analysis of African American Poetry” uses quantitative and qualitative analysis to formulate research questions about African American poetry. In this project, we use text-mining software to determine whether distinctive word patterns can be used to quantify the characteristics of African American poetry. For the purposes of this study, we rejected the notion that Black poetry is defined as poetry written by black authors. Instead, we argue, the distinctions in black poems should be specific enough to be classified in a separate category from other kinds of literature such as American literature, and we assert the definition of black poetry should not reduce “blackness”- what we describe as the shared cultural traditions or practices of African Americans- to certain experiences or tropes such as the rural, folk black experience.

We selected Langston Hughes and the Harlem Renaissance as the earliest historical point for our inquiry, and we used Margaret Walker, Gwendolyn Brooks, Maya Angelou, and Alice Walker, poets whom Hughes directly influenced, as comparisons. We created a text database of the collected poems of the five authors and assessed the frequency of words/phrases related to three main categories that recur in the scholarship of black poetry: memory, identity, and music. After running our text data through mining software and looking specifically for words coded as memory, identity, and music variables, we were able to support our initial claim that quantitative analysis can be used as to support qualitative assertions of black poetry as a distinct genre of American poetry.

The data collected from the first category, memory, yields some significant conclusions. Firstly, all of the poets frequently use the term blood. The recurrence of blood purports the connection that black poetry has to ancestry and heritage. It also points to a collective-consciousness among African-Americans. In addition to blood, death is another word that our poets frequently use. This heavy usage may indicate a link between black poetry and the historical oppression blacks have experienced.

The second data set, identity, reveals that race is an important component of identity for all of the writers. Terms relating to blackness appear numerous in the works of all the authors. Furthermore, the results suggest that the older poets, Hughes and Margaret Walker, connect naming to identity. In contrast, the younger poets place significantly less emphasis on this correlation.

The results yielded from the last category suggest that Hughes and Margaret Walker draw upon the trope of song more heavily than the other poets do. This usage attests to their reliance on the vernacular and oral tradition.