{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/empath-understanding-topic-signals-in-large","title":"Empath: Understanding Topic Signals in Large-Scale Text","arxiv_id":"1602.06979","date":"2016-02-22","proceeding":null,"authors":["Ethan Fast","Binbin Chen","Michael Bernstein"],"abstract":"Human language is colored by a broad range of topics, but existing text\nanalysis tools only focus on a small number of them. We present Empath, a tool\nthat can generate and validate new lexical categories on demand from a small\nset of seed terms (like \"bleed\" and \"punch\" to generate the category violence).\nEmpath draws connotations between words and phrases by deep learning a neural\nembedding across more than 1.8 billion words of modern fiction. Given a small\nset of seed words that characterize a category, Empath uses its neural\nembedding to discover new related terms, then validates the category with a\ncrowd-powered filter. Empath also analyzes text across 200 built-in,\npre-validated categories we have generated from common topics in our web\ndataset, like neglect, government, and social media. We show that Empath's\ndata-driven, human validated categories are highly correlated (r=0.906) with\nsimilar categories in LIWC.","url_abs":"http://arxiv.org/abs/1602.06979v1","url_pdf":"http://arxiv.org/pdf/1602.06979v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"empath-understanding-topic-signals-in-large","repo_url":"https://github.com/manavkaushik/fake-news-dection-using-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.06979","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}