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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

There is an escalating need for methods to identify latent patterns in textdata from many domains. We introduce a new method to identify topics in acorpus and represent documents as topic sequences. Discourse Atom TopicModeling draws on advances in theoretical machine learning to integrate topicmodeling and word embedding, capitalizing on the distinct capabilities of each.We first identify a set of vectors ("discourse atoms") that provide a sparserepresentation of an embedding space. Atom vectors can be interpreted as latenttopics: Through a generative model, atoms map onto distributions over words;one can also infer the topic that generated a sequence of words. We illustrateour method with a prominent example of underutilized text: the U.S. NationalViolent Death Reporting System (NVDRS). The NVDRS summarizes violent deathincidents with structured variables and unstructured narratives. We identify225 latent topics in the narratives (e.g., preparation for death and physicalaggression); many of these topics are not captured by existing structuredvariables. Motivated by known patterns in suicide and homicide by gender, andrecent research on gender biases in semantic space, we identify the gender biasof our topics (e.g., a topic about pain medication is feminine). We thencompare the gender bias of topics to their prevalence in narratives of femaleversus male victims. Results provide a detailed quantitative picture ofreporting about lethal violence and its gendered nature. Our method offers aflexible and broadly applicable approach to model topics in text data.

Integrating topic modeling and word embedding to characterize violent deaths