RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI우수등재

    셀프-어텐션(Self-Attention)을 활용한 집단 감정 서사 연구의 가능성 = The Possibility of Collective Emotion Narrative Research Using Self-Attention

    한글로보기

    https://www.riss.kr/link?id=A109251039

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    Artificial intelligence-based emotion analysis helps analyze collective emotion. However, analytics have mainly been limited to categorizing data into a few well-known emotions.
    Considering the theoretical debates surrounding emotions, we can say this limits the possibilities of emotion analysis. In this article, I examine the potential for AI-based emotion analysis to go beyond these limitations and capture emotional narratives. At the core of this possibility is self-attention. Self-attention is a crucial technology in Transformer architecture. It captures more delicate and diverse connections and dependencies between tokens in the data because it focuses on task-based connections rather than structural identity-based connections. Various models based on self-attention allow us to devise diverse strategies to explore emotional narratives more sophisticatedly. This article proposes two strategies that utilize automatic document generation AI and masked word prediction AI. Furthermore, using COVID-19-related data, I present a real-world example of the first strategy that uses automatic document generation to recreate the dominant emotion narrative in a given data set.
    번역하기

    Artificial intelligence-based emotion analysis helps analyze collective emotion. However, analytics have mainly been limited to categorizing data into a few well-known emotions. Considering the theoretical debates surrounding emotions, we can say this...

    Artificial intelligence-based emotion analysis helps analyze collective emotion. However, analytics have mainly been limited to categorizing data into a few well-known emotions.
    Considering the theoretical debates surrounding emotions, we can say this limits the possibilities of emotion analysis. In this article, I examine the potential for AI-based emotion analysis to go beyond these limitations and capture emotional narratives. At the core of this possibility is self-attention. Self-attention is a crucial technology in Transformer architecture. It captures more delicate and diverse connections and dependencies between tokens in the data because it focuses on task-based connections rather than structural identity-based connections. Various models based on self-attention allow us to devise diverse strategies to explore emotional narratives more sophisticatedly. This article proposes two strategies that utilize automatic document generation AI and masked word prediction AI. Furthermore, using COVID-19-related data, I present a real-world example of the first strategy that uses automatic document generation to recreate the dominant emotion narrative in a given data set.

    더보기

    참고문헌 (Reference)

    1 이철성 ; 최동희 ; 김성순 ; 강재우, "한글 마이크로블로그 텍스트의 감정 분류 및 분석" 40 (40): 159-167, 2013

    2 이진경, "철학의 외부" 그린비 2006

    3 박형신, "집합행위와 감정 : 집합적 분노는 언제 왜 폭력적으로 표출되는가" 41 (41): 161-196, 2018

    4 정수남, "빗장걸기와 탈사회적 공간의 감정동학 : 하층계급의 모욕과 분노에 대하여" 55 (55): 37-70, 2021

    5 사이토 고키, "밑바닥부터 시작하는 딥러닝 2" 한빛미디어 2019

    6 신진숙, "노화 감정의 동학과 문화 정치 : 2000년대 다큐멘터리 노년서사를 중심으로" 54 (54): 121-159, 2020

    7 Ekman, Paul, "Universal Facial Expressions in Emotion" 15 (15): 140-147, 1973

    8 Barrett, Lisa F, "The Theory of Constructed Emotion: An Active Inference Account of Interoception and Categorization" 12 (12): 1-23, 2017

    9 Kozlowski, Austin C., "The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings" 84 (84): 905-949, 2019

    10 Lindquist, Kristen A., "The Brain Basis of Emotion: A Meta-Analytic Review" 35 (35): 121-143, 2012

    1 이철성 ; 최동희 ; 김성순 ; 강재우, "한글 마이크로블로그 텍스트의 감정 분류 및 분석" 40 (40): 159-167, 2013

    2 이진경, "철학의 외부" 그린비 2006

    3 박형신, "집합행위와 감정 : 집합적 분노는 언제 왜 폭력적으로 표출되는가" 41 (41): 161-196, 2018

    4 정수남, "빗장걸기와 탈사회적 공간의 감정동학 : 하층계급의 모욕과 분노에 대하여" 55 (55): 37-70, 2021

    5 사이토 고키, "밑바닥부터 시작하는 딥러닝 2" 한빛미디어 2019

    6 신진숙, "노화 감정의 동학과 문화 정치 : 2000년대 다큐멘터리 노년서사를 중심으로" 54 (54): 121-159, 2020

    7 Ekman, Paul, "Universal Facial Expressions in Emotion" 15 (15): 140-147, 1973

    8 Barrett, Lisa F, "The Theory of Constructed Emotion: An Active Inference Account of Interoception and Categorization" 12 (12): 1-23, 2017

    9 Kozlowski, Austin C., "The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings" 84 (84): 905-949, 2019

    10 Lindquist, Kristen A., "The Brain Basis of Emotion: A Meta-Analytic Review" 35 (35): 121-143, 2012

    11 Cacioppo, John T., "Specific Forms of Facial EMG Response Index Emotions during an Interview: From Darwin to the Continuous Flow Hypothesis of Affect-Laden Information Processing" 54 (54): 592-604, 1988

    12 Liu, Bing, "Sentiment Analysis: Mining Opinions, Sentiments, and Emotions" Cambridge University Press 2015

    13 Blei, David M, "Probabilistic Topic Models" 55 (55): 77-84, 2012

    14 Gendron, Maria,, "Perceptions of Emotion from Facial Expressions Are Not Culturally Universal: Evidence from a Remote Culture" 14 (14): 251-262, 2014

    15 Argyle, Lisa P., "Out of One, Many: Using Language Models to Simulate Human Samples" 31 (31): 337-351, 2023

    16 Hochreiter, Sepp, "Long Short-Term Memory" 9 (9): 1735-1780, 1997

    17 Taboada, Maite, "Lexicon-Based Methods for Sentiment Analysis" 37 (37): 267-307, 2011

    18 Rule, Alix, "Lexical Shifts, Substantive Changes, and Continuity in State of the Union Discourse, 1790-2014" 112 (112): 10837-10844, 2015

    19 Brown, Tom B., "Language Models Are Few-Shot Learners" 1877-1901, 2020

    20 Russell, James A, "Is There Universal Recognition of Emotion from Facial Expression? A Review of the Cross-Cultural Studies" 115 (115): 102-141, 1994

    21 Radford, Alec, "Improving Language Understanding by Generative Pre-Training"

    22 Barrett, Lisa F, "How Emotions Are Made: The Secret Life of the Brain" Pan Macmillan 2017

    23 Ravichandiran, Sudharsan, "Getting Started with Google BERT: Build and Train State-of-the-Art Natural Language Processing Models Using BERT" Packt Publishing Ltd 2021

    24 Elman, Jeffrey L, "Finding Structure in Time" 14 (14): 179-211, 1990

    25 Siegel, Erika H., "Emotion Fingerprints or Emotion Populations? A Meta-Analytic Investigation of Autonomic Features of Emotion Categories" 144 (144): 343-393, 2018

    26 Gonçalves, Pollyanna, "Comparing and Combining Sentiment Analysis Methods" 27-38, 2013

    27 Robinson, Michael D., "Belief and Feeling: Evidence for an Accessibility Model of Emotional Self-Report" 128 (128): 934-960, 2002

    28 van Heijst, Karlijn, "Basic Emotions or Constructed Emotions: Insights From Taking an Evolutionary Perspective" 2023

    29 Vaswani, Ashish, "Attention Is All You Need" 6000-6010, 2017

    30 Ekman, Paul, "Are There Basic Emotions?" 99 (99): 550-553, 1992

    31 Ortony, Andrew, "Are All “Basic Emotions” Emotions? A Problem for the (Basic) Emotions Construct" 17 (17): 41-61, 2022

    32 Kahneman, Daniel, "A Survey Method for Characterizing Daily Life Experience: The Day Reconstruction Method" 306 (306): 1776-1780, 2004

    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼