{"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/a-recurrent-neural-network-for-sentiment","title":"A Recurrent Neural Network for Sentiment Quantification","arxiv_id":"1809.00836","date":"2018-09-04","proceeding":null,"authors":["Andrea Esuli","Alejandro Moreo Fernández","Fabrizio Sebastiani"],"abstract":"Quantification is a supervised learning task that consists in predicting,\ngiven a set of classes C and a set D of unlabelled items, the prevalence (or\nrelative frequency) p(c|D) of each class c in C. Quantification can in\nprinciple be solved by classifying all the unlabelled items and counting how\nmany of them have been attributed to each class. However, this \"classify and\ncount\" approach has been shown to yield suboptimal quantification accuracy;\nthis has established quantification as a task of its own, and given rise to a\nnumber of methods specifically devised for it. We propose a recurrent neural\nnetwork architecture for quantification (that we call QuaNet) that observes the\nclassification predictions to learn higher-order \"quantification embeddings\",\nwhich are then refined by incorporating quantification predictions of simple\nclassify-and-count-like methods. We test {QuaNet on sentiment quantification on\ntext, showing that it substantially outperforms several state-of-the-art\nbaselines.","url_abs":"http://arxiv.org/abs/1809.00836v1","url_pdf":"http://arxiv.org/pdf/1809.00836v1.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":"a-recurrent-neural-network-for-sentiment","repo_url":"https://github.com/HLT-ISTI/QuaNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}