본문

서브메뉴

Human-Centered Natural Language Processing for Countering Misinformation
Human-Centered Natural Language Processing for Countering Misinformation
Human-Centered Natural Language Processing for Countering Misinformation

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211152104
ISBN  
9798382740676
DDC  
004
저자명  
Kazemi, Ashkan.
서명/저자  
Human-Centered Natural Language Processing for Countering Misinformation
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
주기사항  
Advisor: Mihalcea, Rada;Perez-Rosas, Veronica.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약As curbing the spread of online misinformation has proven to be challenging, we look to artificial intelligence (AI) and natural language technology for helping individuals and society counter and limit it. Despite current advances, state-of-the-art natural language processing (NLP) and AI still struggle to automatically identify and understand misinformation. Humans exposed to harmful content may experience lasting negative consequences in real life, and it is often difficult to change one's mind once they form wrong beliefs. Addressing these interwoven technical and social challenges requires research and understanding into the core mechanisms that drive the phenomena of misinformation. This thesis introduces human-centered NLP tasks and methods that can help prioritize human welfare in countering misinformation. We present findings on the differences in how people of different backgrounds perceive misinformation, and how misinformation unfolds in different conditions such as end-to-end encrypted social media in India. We build on this understanding to create models and datasets for identifying misinformation at scale that put humans in the decision making seat, through claim matching, matching claims with fact-check reports, and query rewriting that scale the efforts of fact-checkers. Our work highlights the global impact of misinformation, and contributes to advancing the equitability of available language technologies through models and datasets in a variety of high and low resources and languages. We also make fundamental contributions to data, algorithms, and models through: multilingual and low-resource embeddings and retrieval for better claim matching, reinforcement learning for reformulating queries for better misinformation discovery, unsupervised and graph-based focused content extraction through introducing the Biased TextRank algorithm, and explanation generation through extractive (Biased TextRank) and abstractive (GPT-2) summarization. Through this thesis, we aim to promote individual and social wellbeing by creating language technologies built on a deeper understanding of misinformation, and provide tools to help journalists as well as internet users to identify and navigate around it.
일반주제명  
Computer science
일반주제명  
Communication
키워드  
Natural language processing
키워드  
Misinformation
키워드  
Human-centered NLP
키워드  
Biased TextRank
기타저자  
University of Michigan Computer Science & Engineering
기본자료저록  
Dissertations Abstracts International. 85-12A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162860
■00520250211152104
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382740676
■035    ▼a(MiAaPQ)AAI31349063
■035    ▼a(MiAaPQ)umichrackham005371
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aKazemi,  Ashkan.
■24510▼aHuman-Centered  Natural  Language  Processing  for  Countering  Misinformation
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  A.
■500    ▼aAdvisor:  Mihalcea,  Rada;Perez-Rosas,  Veronica.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aAs  curbing  the  spread  of  online  misinformation  has  proven  to  be  challenging,  we  look  to  artificial  intelligence  (AI)  and  natural  language  technology  for  helping  individuals  and  society  counter  and  limit  it.  Despite  current  advances,  state-of-the-art  natural  language  processing  (NLP)  and  AI  still  struggle  to  automatically  identify  and  understand  misinformation.  Humans  exposed  to  harmful  content  may  experience  lasting  negative  consequences  in  real  life,  and  it  is  often  difficult  to  change  one's  mind  once  they  form  wrong  beliefs.  Addressing  these  interwoven  technical  and  social  challenges  requires  research  and  understanding  into  the  core  mechanisms  that  drive  the  phenomena  of  misinformation.    This  thesis  introduces  human-centered  NLP  tasks  and  methods  that  can  help  prioritize  human  welfare  in  countering  misinformation.  We  present  findings  on  the  differences  in  how  people  of  different  backgrounds  perceive  misinformation,  and  how  misinformation  unfolds  in  different  conditions  such  as  end-to-end  encrypted  social  media  in  India.  We  build  on  this  understanding  to  create  models  and  datasets  for  identifying  misinformation  at  scale  that  put  humans  in  the  decision  making  seat,  through  claim  matching,  matching  claims  with  fact-check  reports,  and  query  rewriting  that  scale  the  efforts  of  fact-checkers.  Our  work  highlights  the  global  impact  of  misinformation,  and  contributes  to  advancing  the  equitability  of  available  language  technologies  through  models  and  datasets  in  a  variety  of  high  and  low  resources  and  languages.    We  also  make  fundamental  contributions  to  data,  algorithms,  and  models  through:  multilingual  and  low-resource  embeddings  and  retrieval  for  better  claim  matching,  reinforcement  learning  for  reformulating  queries  for  better  misinformation  discovery,  unsupervised  and  graph-based  focused  content  extraction  through  introducing  the  Biased  TextRank  algorithm,  and  explanation  generation  through  extractive  (Biased  TextRank)  and  abstractive  (GPT-2)  summarization.    Through  this  thesis,  we  aim  to  promote  individual  and  social  wellbeing  by  creating  language  technologies  built  on  a  deeper  understanding  of  misinformation,  and  provide  tools  to  help  journalists  as  well  as  internet  users  to  identify  and  navigate  around  it.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aCommunication
■653    ▼aNatural  language  processing
■653    ▼aMisinformation
■653    ▼aHuman-centered  NLP
■653    ▼aBiased  TextRank
■690    ▼a0984
■690    ▼a0800
■690    ▼a0459
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-12A.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162860▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF12825 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.