東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Three Essays on Financial Text Analy...

Zheng, Jiexin,

FindBook

Google Book

Amazon

博客來

Three Essays on Financial Text Analysis /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Three Essays on Financial Text Analysis // Jiexin Zheng.
作者:	Zheng, Jiexin,
面頁冊數:	1 electronic resource (160 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
Contained By:	Dissertations Abstracts International86-05B.
標題:	Readability. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31718389
ISBN:	9798346543152

Three Essays on Financial Text Analysis /
Zheng, Jiexin,

Three Essays on Financial Text Analysis /Jiexin Zheng. - 1 electronic resource (160 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: B.

Processing financial text in an effective and efficient manner is a challenging task due to its complexity, large volume, and the strategic behaviors of communicators. Both the computational power of AI and the generalizability of human knowledge are desired for the effective processing of financial text. This three-study thesis focus on exploring human-AI augmentations methodologies for extracting valuable information from financial texts. In the first study, an algorithm is proposed that leverages both a human-defined sentiment word list and the word embedding approach to quantify text sentiment over time. The algorithm is then applied to investigate the evolutionary effects of sentiment words in financial text, shedding light on the strategic communication of managers and its influence on sentiment analysis. The second study introduces an augmentation approach that combines human knowledge with artificial intelligence for sentiment extraction from corporate disclosures. By incorporating a human-defined sentiment word list into a word embedding model, a weighting scheme is constructed to enhance the effectiveness of common sentiment measures. This study highlights the value of human knowledge in mitigating managers' strategic manipulation and emphasizes the complementarity between human knowledge and AI in processing financial text. The third study proposes a novel readability measure, the Language Predictability Score (\uD835\uDC3F\uD835\uDC43 \uD835\uDC46), aimed at assessing the processing costs associated with comprehending corporate disclosure text. Large language models are employed to simulate the language ability of market participants, and these models are then used to estimate the processing cost of a large sample of management discussion and analysis (MD&As) from annual reports. Empirical evidence suggests that the constructed \uD835\uDC3F\uD835\uDC43 \uD835\uDC46 measure can effectively reflect the processing difficulty experienced by market participants. This study demonstrates the effectiveness of capturing novel information in financial text from a human perspective while leveraging AI to enhance efficiency. Overall, these studies collectively contribute to the advancement of methodologies for processing financial text.

English

ISBN: 9798346543152Subjects--Topical Terms:

3815586
Readability.

Three Essays on Financial Text Analysis /
LDR:03581nmm a22004333i 4500 001 2431356
005 20250603111435.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798346543152
035 $a (MiAaPQD)AAI31718389
035 $a AAI31718389
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Zheng, Jiexin, $e author. $3 3820117
245 1 0 $a Three Essays on Financial Text Analysis / $c Jiexin Zheng.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (160 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
500 $a Advisors: Zheng, Rong.
502 $b Ph.D. $c Hong Kong University of Science and Technology (Hong Kong) $d 2024.
520 $a Processing financial text in an effective and efficient manner is a challenging task due to its complexity, large volume, and the strategic behaviors of communicators. Both the computational power of AI and the generalizability of human knowledge are desired for the effective processing of financial text. This three-study thesis focus on exploring human-AI augmentations methodologies for extracting valuable information from financial texts. In the first study, an algorithm is proposed that leverages both a human-defined sentiment word list and the word embedding approach to quantify text sentiment over time. The algorithm is then applied to investigate the evolutionary effects of sentiment words in financial text, shedding light on the strategic communication of managers and its influence on sentiment analysis. The second study introduces an augmentation approach that combines human knowledge with artificial intelligence for sentiment extraction from corporate disclosures. By incorporating a human-defined sentiment word list into a word embedding model, a weighting scheme is constructed to enhance the effectiveness of common sentiment measures. This study highlights the value of human knowledge in mitigating managers' strategic manipulation and emphasizes the complementarity between human knowledge and AI in processing financial text. The third study proposes a novel readability measure, the Language Predictability Score (\uD835\uDC3F\uD835\uDC43 \uD835\uDC46), aimed at assessing the processing costs associated with comprehending corporate disclosure text. Large language models are employed to simulate the language ability of market participants, and these models are then used to estimate the processing cost of a large sample of management discussion and analysis (MD&As) from annual reports. Empirical evidence suggests that the constructed \uD835\uDC3F\uD835\uDC43 \uD835\uDC46 measure can effectively reflect the processing difficulty experienced by market participants. This study demonstrates the effectiveness of capturing novel information in financial text from a human perspective while leveraging AI to enhance efficiency. Overall, these studies collectively contribute to the advancement of methodologies for processing financial text.
546 $a English
590 $a School code: 1223
650 4 $a Readability. $3 3815586
650 4 $a Deep learning. $3 3554982
650 4 $a Investments. $3 566987
650 4 $a Communication. $3 524709
650 4 $a Cognitive ability. $3 3560491
650 4 $a Data compression. $3 3681696
650 4 $a Investors. $3 3544951
650 4 $a Drug overdose. $3 3771273
650 4 $a Sentiment analysis. $2 lcstt $3 3266790
650 4 $a Decision making. $3 517204
650 4 $a Text analysis. $3 3561686
650 4 $a Semantics. $3 520060
650 4 $a Fraud. $3 721834
650 4 $a Cognitive psychology. $3 523881
650 4 $a Finance. $3 542899
650 4 $a Logic. $3 529544
690 $a 0272
690 $a 0800
690 $a 0459
690 $a 0633
690 $a 0508
690 $a 0395
690 $a 0454
690 $a 0796
710 2 $a Hong Kong University of Science and Technology (Hong Kong). $e degree granting institution. $3 3814653
720 1 $a Zheng, Rong $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05B.
790 $a 1223
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31718389