Back to search

Article

Validity of Large Language Models for Sentiment Analysis: Evidence of performance comparable to human coders

2023-12-28

Abstract excerpt

<p>Assessing the sentiment of content is a major focus of communication science. Previous research has compared the performance of ‘gold-standard’ methods – exemplified by trained human coders – with approaches such as crowd-sourcing, data dictionaries, and machine learning. Aggregated crowd-sourced assessments and trained human coders perform best, but trained coders may not be scalable and crowd-sourcing may rai...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
484d7c52-4277-553f-8631-54a010ca0494
DOI
10.31234/osf.io/kcuwy
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Validity of Large Language Models for Sentiment Analysis: Evidence of performance comparable to human codersDOI 10.31234/osf.io/kcuwy
Select a neighboring publication to make it the new centre.