{"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/financial-aspect-based-sentiment-analysis","title":"Financial Aspect-Based Sentiment Analysis using Deep Representations","arxiv_id":"1808.07931","date":"2018-08-23","proceeding":null,"authors":["Steve Yang","Jason Rosenfeld","Jacques Makutonin"],"abstract":"The topic of aspect-based sentiment analysis (ABSA) has been explored for a\nvariety of industries, but it still remains much unexplored in finance. The\nrecent release of data for an open challenge (FiQA) from the companion\nproceedings of WWW '18 has provided valuable finance-specific annotations. FiQA\ncontains high quality labels, but it still lacks data quantity to apply\ntraditional ABSA deep learning architecture. In this paper, we employ\nhigh-level semantic representations and methods of inductive transfer learning\nfor NLP. We experiment with extensions of recently developed domain adaptation\nmethods and target task fine-tuning that significantly improve performance on a\nsmall dataset. Our results show an 8.7% improvement in the F1 score for\nclassification and an 11% improvement over the MSE for regression on current\nstate-of-the-art results.","url_abs":"http://arxiv.org/abs/1808.07931v1","url_pdf":"http://arxiv.org/pdf/1808.07931v1.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":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-fiqa","task":"Sentiment Analysis","dataset":"FiQA","model":"Deep Representations","rank_in_archive_order":3,"of":4,"metrics":{"MSE":"0.08","R^2":"0.40"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.07931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}