{"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/pelesent-cross-domain-polarity-classification","title":"PELESent: Cross-domain polarity classification using distant supervision","arxiv_id":"1707.02657","date":"2017-07-09","proceeding":null,"authors":["Edilson A. Corrêa Jr","Vanessa Q. Marinho","Leandro B. dos Santos","Thales F. C. Bertaglia","Marcos V. Treviso","Henrico B. Brum"],"abstract":"The enormous amount of texts published daily by Internet users has fostered\nthe development of methods to analyze this content in several natural language\nprocessing areas, such as sentiment analysis. The main goal of this task is to\nclassify the polarity of a message. Even though many approaches have been\nproposed for sentiment analysis, some of the most successful ones rely on the\navailability of large annotated corpus, which is an expensive and\ntime-consuming process. In recent years, distant supervision has been used to\nobtain larger datasets. So, inspired by these techniques, in this paper we\nextend such approaches to incorporate popular graphic symbols used in\nelectronic messages, the emojis, in order to create a large sentiment corpus\nfor Portuguese. Trained on almost one million tweets, several models were\ntested in both same domain and cross-domain corpora. Our methods obtained very\ncompetitive results in five annotated corpora from mixed domains (Twitter and\nproduct reviews), which proves the domain-independent property of such\napproach. In addition, our results suggest that the combination of emoticons\nand emojis is able to properly capture the sentiment of a message.","url_abs":"http://arxiv.org/abs/1707.02657v1","url_pdf":"http://arxiv.org/pdf/1707.02657v1.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":"pelesent-cross-domain-polarity-classification","repo_url":"https://github.com/edilsonacjr/pelesent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}