Integrating Big Data Into Evaluation: R Code for Topic Identification and Modeling

Despite the rising popularity of big data, there is speculation that evaluators have been slow adopters of these new statistical approaches. Several possible reasons have been offered for why this is the case: ethical concerns, institutional capacity, and evaluator capacity and values. In this metho...

Full description

Saved in:
Bibliographic Details
Published in:The American journal of evaluation 2022-09, Vol.43 (3), p.412-436
Main Authors: Cintron, Dakota W., Montrosse-Moorhead, Bianca
Format: Article
Language:English
Subjects:
Data Analysis
Data Interpretation
Data Use
Evaluation Methods
Evaluation Problems
Evaluation Research
Research Methodology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Despite the rising popularity of big data, there is speculation that evaluators have been slow adopters of these new statistical approaches. Several possible reasons have been offered for why this is the case: ethical concerns, institutional capacity, and evaluator capacity and values. In this method note, we address one of these barriers and aim to build evaluator capacity to integrate big data analytics into their studies. We focus our efforts on a specific topic modeling technique referred to as latent Dirichlet allocation (LDA) because of the ubiquitousness of qualitative textual data in evaluation. Given current equity debates, both within evaluation and the communities in which we practice, we analyze 1,796 tweets that use the hashtag #equity with the R packages topicmodels and ldatuning to illustrate the use of LDA. Furthermore, a freely available workbook for implementing LDA topic modeling is provided as Supplemental Material Online.
ISSN:1098-2140
1557-0878
DOI:10.1177/10982140211031640