{"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/overcoming-language-variation-in-sentiment","title":"Overcoming Language Variation in Sentiment Analysis with Social Attention","arxiv_id":"1511.06052","date":"2015-11-19","proceeding":"TACL 2017 1","authors":["Yi Yang","Jacob Eisenstein"],"abstract":"Variation in language is ubiquitous, particularly in newer forms of writing\nsuch as social media. Fortunately, variation is not random, it is often linked\nto social properties of the author. In this paper, we show how to exploit\nsocial networks to make sentiment analysis more robust to social language\nvariation. The key idea is linguistic homophily: the tendency of socially\nlinked individuals to use language in similar ways. We formalize this idea in a\nnovel attention-based neural network architecture, in which attention is\ndivided among several basis models, depending on the author's position in the\nsocial network. This has the effect of smoothing the classification function\nacross the social network, and makes it possible to induce personalized\nclassifiers even for authors for whom there is no labeled data or demographic\nmetadata. This model significantly improves the accuracies of sentiment\nanalysis on Twitter and on review data.","url_abs":"http://arxiv.org/abs/1511.06052v4","url_pdf":"http://arxiv.org/pdf/1511.06052v4.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":"overcoming-language-variation-in-sentiment","repo_url":"https://github.com/yiyang-gt/social-attention","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.06052","atlas_url":"https://app.syntology.ai/?focus=1511.06052","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}