|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Replication Data for: An Improved Method of Automated Nonparametric Content Analysis for Social Science |
|
Identification Number: |
doi:10.7910/DVN/AVNZR6 |
|
Distributor: |
Harvard Dataverse |
|
Date of Distribution: |
2021-07-11 |
|
Version: |
1 |
|
Bibliographic Citation: |
Jerzak, Connor; King, Gary; Strezhnev, Anton, 2021, "Replication Data for: An Improved Method of Automated Nonparametric Content Analysis for Social Science", https://doi.org/10.7910/DVN/AVNZR6, Harvard Dataverse, V1 |
|
Citation |
|
|
Title: |
Replication Data for: An Improved Method of Automated Nonparametric Content Analysis for Social Science |
|
Identification Number: |
doi:10.7910/DVN/AVNZR6 |
|
Authoring Entity: |
Jerzak, Connor (Harvard University) |
|
King, Gary (Harvard University) |
|
|
Strezhnev, Anton (New York University) |
|
|
Distributor: |
Harvard Dataverse |
|
Access Authority: |
Jerzak, Connor |
|
Depositor: |
Code Ocean |
|
Holdings Information: |
https://doi.org/10.7910/DVN/AVNZR6 |
|
Study Scope |
|
|
Keywords: |
Social Sciences, Natural language processing, Content analysis, Social media, Classification |
|
Abstract: |
Some scholars build models to classify documents into chosen categories. Others, especially social scientists who tend to focus on population characteristics, instead usually estimate the proportion of documents in each category -- using either parametric "classify-and-count" methods or "direct" nonparametric estimation of proportions without individual classification. Unfortunately, classify-and-count methods can be highly model dependent or generate more bias in the proportions even as the percent of documents correctly classified increases. Direct estimation avoids these problems, but can suffer when the meaning of language changes between training and test sets or is too similar across categories. We develop an improved direct estimation approach without these issues by including and optimizing continuous text features, along with a form of matching adapted from the causal inference literature. Our approach substantially improves performance in a diverse collection of 73 data sets. We also offer easy-to-use software that implements all ideas discussed herein. |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Notes: |
This dataset is made available without information on how it can be used. You should communicate with the Contact(s) specified before use. |
|
Other Study Description Materials |
|
|
Related Materials |
|
|
This is a preservation copy of the replication code that has been published in Code Ocean. Code Ocean is a computational reproducibility platform that enables users to run the code. The Code Ocean replication capsule can be viewed interactively at https://doi.org/10.24433/CO.2196695.v1. |
|
|
Related Publications |
|
|
Citation |
|
|
Title: |
Forthcoming, Political Analysis |
|
Bibliographic Citation: |
Forthcoming, Political Analysis |
|
Label: |
capsule-03f6dcc8-b7c8-4a59-97c8-7e2914d2543d.zip |
|
Notes: |
application/zip |
|
Label: |
results-03f6dcc8-b7c8-4a59-97c8-7e2914d2543d.zip |
|
Notes: |
application/zip |