English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Pro

Presents the zaia usage as premium feature

ZAIA

Presents AI Discovery search usage as a premium feature

AI Discovery

Presents AI Discovery explain and summary usage as a premium feature

Content Analysis

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Presents the pdf analysis as premium feature

PDF Analysis

1500 Top-up

3000 Top-up

Zendy Basic

2500 Top-up

Zendy Unlimited

Presents the access of premium content as premium feature

Premium Content

To analyse large numbers of texts, social science researchers areincreasingly confronting the challenge of text classification. When manuallabeling is not possible and researchers have to find automatized ways toclassify texts, computer science provides a useful toolbox of machine-learningmethods whose performance remains understudied in the social sciences. In thisarticle, we compare the performance of the most widely used text classifiers byapplying them to a typical research scenario in social science research: arelatively small labeled dataset with infrequent occurrence of categories ofinterest, which is a part of a large unlabeled dataset. As an example case, welook at Twitter communication regarding climate change, a topic of increasingscholarly interest in interdisciplinary social science research. Using a noveldataset including 5,750 tweets from various international organizationsregarding the highly ambiguous concept of climate change, we evaluate theperformance of methods in automatically classifying tweets based on whetherthey are about climate change or not. In this context, we highlight two mainfindings. First, supervised machine-learning methods perform better thanstate-of-the-art lexicons, in particular as class balance increases. Second,traditional machine-learning methods, such as logistic regression and randomforest, perform similarly to sophisticated deep-learning methods, whilstrequiring much less training time and computational resources. The results haveimportant implications for the analysis of short texts in social scienceresearch.

Short text classification with machine learning in the social sciences: The case of climate change on Twitter