{"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/good-debt-or-bad-debt-detecting-semantic","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","arxiv_id":"1307.5336","date":"2013-07-19","proceeding":null,"authors":["Pekka Malo","Ankur Sinha","Pyry Takala","Pekka Korhonen","Jyrki Wallenius"],"abstract":"The use of robo-readers to analyze news texts is an emerging technology trend\nin computational finance. In recent research, a substantial effort has been\ninvested to develop sophisticated financial polarity-lexicons that can be used\nto investigate how financial sentiments relate to future company performance.\nHowever, based on experience from other fields, where sentiment analysis is\ncommonly applied, it is well-known that the overall semantic orientation of a\nsentence may differ from the prior polarity of individual words. The objective\nof this article is to investigate how semantic orientations can be better\ndetected in financial and economic news by accommodating the overall\nphrase-structure information and domain-specific use of language. Our three\nmain contributions are: (1) establishment of a human-annotated finance\nphrase-bank, which can be used as benchmark for training and evaluating\nalternative models; (2) presentation of a technique to enhance financial\nlexicons with attributes that help to identify expected direction of events\nthat affect overall sentiment; (3) development of a linearized phrase-structure\nmodel for detecting contextual semantic orientations in financial and economic\nnews texts. The relevance of the newly added lexicon features and the benefit\nof using the proposed learning-algorithm are demonstrated in a comparative\nstudy against previously used general sentiment models as well as the popular\nword frequency models used in recent financial studies. The proposed framework\nis parsimonious and avoids the explosion in feature-space caused by the use of\nconventional n-gram features.","url_abs":"http://arxiv.org/abs/1307.5336v2","url_pdf":"http://arxiv.org/pdf/1307.5336v2.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":"good-debt-or-bad-debt-detecting-semantic","repo_url":"https://github.com/clementgr/sentiment-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"good-debt-or-bad-debt-detecting-semantic","repo_url":"https://github.com/hc495/staicc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"good-debt-or-bad-debt-detecting-semantic","repo_url":"https://github.com/yya518/FinBERT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1307.5336","atlas_url":"https://app.syntology.ai/?focus=1307.5336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}