{"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-multi-sentiment-resource-enhanced-attention","title":"A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification","arxiv_id":"1807.04990","date":"2018-07-13","proceeding":"ACL 2018 7","authors":["Zeyang Lei","Yujiu Yang","Min Yang","Yi Liu"],"abstract":"Deep learning approaches for sentiment classification do not fully exploit\nsentiment linguistic knowledge. In this paper, we propose a\nMulti-sentiment-resource Enhanced Attention Network (MEAN) to alleviate the\nproblem by integrating three kinds of sentiment linguistic knowledge (e.g.,\nsentiment lexicon, negation words, intensity words) into the deep neural\nnetwork via attention mechanisms. By using various types of sentiment\nresources, MEAN utilizes sentiment-relevant information from different\nrepresentation subspaces, which makes it more effective to capture the overall\nsemantics of the sentiment, negation and intensity words for sentiment\nprediction. The experimental results demonstrate that MEAN has robust\nsuperiority over strong competitors.","url_abs":"http://arxiv.org/abs/1807.04990v1","url_pdf":"http://arxiv.org/pdf/1807.04990v1.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"negation","task_name":"Negation"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-mr","task":"Sentiment Analysis","dataset":"MR","model":"MEAN","rank_in_archive_order":5,"of":19,"metrics":{"Accuracy":"84.5"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-5-fine-grained","task":"Sentiment Analysis","dataset":"SST-5 Fine-grained classification","model":"MEAN","rank_in_archive_order":16,"of":31,"metrics":{"Accuracy":"51.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.04990","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}