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/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Political activity on social media presents a data-rich window into politicalbehavior, but the vast amount of data means that almost all content analyses ofsocial media require a data labeling step. However, most automated machineclassification methods ignore the multimodality of posted content, focusingeither on text or images. State-of-the-art vision-and-language models areunusable for most political science research: they require all observations tohave both image and text and require computationally expensive pretraining.This paper proposes a novel vision-and-language framework called multimodalrepresentations using modality translation (MARMOT). MARMOT presents twomethodological contributions: it can construct representations for observationsmissing image or text, and it replaces the computationally expensivepretraining with modality translation. MARMOT outperforms an ensemble text-onlyclassifier in 19 of 20 categories in multilabel classifications of tweetsreporting election incidents during the 2016 U.S. general election. Moreover,MARMOT shows significant improvements over the results of benchmark multimodalmodels on the Hateful Memes dataset, improving the best result set byVisualBERT in terms of accuracy from 0.6473 to 0.6760 and area under thereceiver operating characteristic curve (AUC) from 0.7141 to 0.7530.

MARMOT: A Deep Learning Framework for Constructing Multimodal Representations for Vision-and-Language Tasks