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

切換: 標籤 | MARC模式 | ISBD

Interpretable and Generative AI for ...

Cheng, Zhaoqi.

FindBook

Google Book

Amazon

博客來

Interpretable and Generative AI for Actionable Insights from Textual Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Interpretable and Generative AI for Actionable Insights from Textual Data./
作者:	Cheng, Zhaoqi.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	161 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31241307
ISBN:	9798382592497

Interpretable and Generative AI for Actionable Insights from Textual Data.
Cheng, Zhaoqi.

Interpretable and Generative AI for Actionable Insights from Textual Data. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 161 p.

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--Boston University, 2024.

This item must not be sold to any third party vendors.

The applications of artificial intelligence (AI) and natural language processing (NLP) methods have enabled managers and researchers to process, interpret, and extract value from text efficiently. These systems offer a lens through which to understand consumer behavior, monitor the dynamics of markets and brands. Recent advancements, including interpretable AI, variational autoencoders and the most recent transformer-based large language models (LLMs), have significantly altered the research landscape. These models, with their robust capabilities for language representation and generation, introduce both new opportunities and challenges in converting raw textual data into actionable business insights. In line with this research trend, this dissertation aims to compile and adapt three of my works on interpretable and generative models for insights from the textual data.The first essay explores the development of interpretable machine learning algorithm for the automatic extraction of corpus-level concepts from textual data without the need for human-defined guidance or labeled concepts. Through a case study involving online purchase journey data, we demonstrates the ability of the model to identify and quantify the importance of customer review concepts correlated with purchase conversion, providing external validation of its efficacy as an exploratory tool.The second essay presents the use of Variational AutoEncoder that transforms unstructured patent text into a structured, spatial representation of firms' innovation activities. By learning a disentangled vector space of patents, the model offers interpretable insights into firms' AI-based intellectual property portfolios. Through applications across three decades of patents, this chapter showcases the model's utility in visualizing technology landscapes, engineering intuitive features from text, and augmenting patent applications to reduce rejection risks, thereby illustrating the transformative potential of generative AI in analyzing unstructured corporate data.The third essay explores the capabilities and limitations of large language models (LLMs) in simulating human preferences and reasoning in the context of misinformation. By adopting the dual process theory, this study investigates the extent to which LLMs can mimic human discernment in the accuracy estimation and the sharing of political news headlines. We argue that while current LLMs struggle to replicate complex cognitive reasoning behaviors, the integration of psychological theories offers a pathway to align language agents more closely with human reasoning processes.Broadly, this dissertation addresses the issues of how to align the NLP systems with human intentions for the task of language understanding, language representation, agent development in information systems research, and highlights potential avenues for future research in these areas.

ISBN: 9798382592497Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Natural language processing

Interpretable and Generative AI for Actionable Insights from Textual Data.
LDR:04113nmm a2200385 4500 001 2397104
005 20240617111738.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798382592497
035 $a (MiAaPQ)AAI31241307
035 $a AAI31241307
040 $a MiAaPQ $c MiAaPQ
100 1 $a Cheng, Zhaoqi. $3 3412252
245 1 0 $a Interpretable and Generative AI for Actionable Insights from Textual Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 161 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Lee, Dokyun.
502 $a Thesis (Ph.D.)--Boston University, 2024.
506 $a This item must not be sold to any third party vendors.
520 $a The applications of artificial intelligence (AI) and natural language processing (NLP) methods have enabled managers and researchers to process, interpret, and extract value from text efficiently. These systems offer a lens through which to understand consumer behavior, monitor the dynamics of markets and brands. Recent advancements, including interpretable AI, variational autoencoders and the most recent transformer-based large language models (LLMs), have significantly altered the research landscape. These models, with their robust capabilities for language representation and generation, introduce both new opportunities and challenges in converting raw textual data into actionable business insights. In line with this research trend, this dissertation aims to compile and adapt three of my works on interpretable and generative models for insights from the textual data.The first essay explores the development of interpretable machine learning algorithm for the automatic extraction of corpus-level concepts from textual data without the need for human-defined guidance or labeled concepts. Through a case study involving online purchase journey data, we demonstrates the ability of the model to identify and quantify the importance of customer review concepts correlated with purchase conversion, providing external validation of its efficacy as an exploratory tool.The second essay presents the use of Variational AutoEncoder that transforms unstructured patent text into a structured, spatial representation of firms' innovation activities. By learning a disentangled vector space of patents, the model offers interpretable insights into firms' AI-based intellectual property portfolios. Through applications across three decades of patents, this chapter showcases the model's utility in visualizing technology landscapes, engineering intuitive features from text, and augmenting patent applications to reduce rejection risks, thereby illustrating the transformative potential of generative AI in analyzing unstructured corporate data.The third essay explores the capabilities and limitations of large language models (LLMs) in simulating human preferences and reasoning in the context of misinformation. By adopting the dual process theory, this study investigates the extent to which LLMs can mimic human discernment in the accuracy estimation and the sharing of political news headlines. We argue that while current LLMs struggle to replicate complex cognitive reasoning behaviors, the integration of psychological theories offers a pathway to align language agents more closely with human reasoning processes.Broadly, this dissertation addresses the issues of how to align the NLP systems with human intentions for the task of language understanding, language representation, agent development in information systems research, and highlights potential avenues for future research in these areas.
590 $a School code: 0017.
650 4 $a Computer science. $3 523869
653 $a Natural language processing
653 $a Large language models
653 $a Textual data
653 $a Human reasoning processes
690 $a 0454
690 $a 0984
690 $a 0800
710 2 $a Boston University. $b Management QSB. $3 3288601
773 0 $t Dissertations Abstracts International $g 85-11B.
790 $a 0017
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31241307