Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/74409
題名: | Mining opinion holders and opinion patterns in US financial statements | 作者: | Chen, Chien-Liang;Liu, Chao-Lin;Chang, Yuan-Chen;Tsai, Hsiang-Ping 陳建良;劉昭麟;張元晨;蔡湘萍 |
貢獻者: | 資科系;語言所 | 關鍵詞: | Conditional random field; Information extraction; Opinion mining; Semantic labeling; Sentiment analysis; Text mining; Artificial intelligence; Finance; Image segmentation; Quality control; Random processes; Semantics; Data mining | 日期: | Nov-2011 | 上傳時間: | 8-Apr-2015 | 摘要: | Subjective statements provide qualitative evaluation of the financial status of the reporting corporations, in addition to the quantitative information released in US 10-K filings. Both qualitative and quantitative appraisals are crucial for quality financial decisions. To extract such opinioned statements from the reports, we built tagging models based on the conditional random field (CRF) techniques, considering a variety of combinations of linguistic factors including morphology, orthography, predicate-argument structure, syntax and simple semantics. The CRF models showed reasonable effectiveness to find opinion holders in experiments when we adopted the popular MPQA corpus for training and testing. We also identified opinion patterns in the form of multi-word expressions (MWEs), which is a major contribution of our work. In a recent article published in a prestigious journal in Finance, single words, rather than MWEs, were reported to indicate positive and negative judgments in financial statements. © 2011 IEEE. | 關聯: | Proceedings - 2011 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2011, 論文編號 6120721, 62-68 最佳論文佳作獎, 中華民國人工智慧學會 10.1109/TAAI.2011.19 |
資料類型: | conference |
Appears in Collections: | 會議論文 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
4601a062.pdf | 252.59 kB | Adobe PDF2 | View/Open |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.