Corpus Annotation and Analysis of Sarcasm on Twitter: #CatsMovie vs. #TheRiseOfSkywalker.

Sentiment analysis is a natural language processing task that has received increased attention in the last decade due to the vast amount of opinionated data on social media platforms such as Twitter. Although the methodologies employed have grown in number and sophistication, analysing irony and sar...

Descripción completa

Detalles Bibliográficos
Publicado en:Atlantis (0210-6124) Vol. 44; no. 1; pp. 186 - 208
Autores principales: MORENO-ORTIZ, ANTONIO, GARCÍA-GÁMEZ, MARÍA
Formato: Artículo
Publicado: Departament de Llengues i Literatures Modernes i d'Estudis Anglesos Jun2022
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=157735229&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 157735229
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        02106124
        VSM
      jtl: Atlantis (0210-6124)
      issn: 02106124
      maglogo: N
    pubinfo:
      dt: Jun2022
      vid: 44
      iid: 1
      pid: 19799
      pub: Departament de Llengues i Literatures Modernes i d'Estudis Anglesos
    artinfo:
      ui:
        157735229
        10.28914/Atlantis-2022-44.1.11
      ppf: 186
      ppct: 22
      formats:
        fmt:
          @attributes:
            type: P
            size: 1.4MB
      tig:
        atl: Corpus Annotation and Analysis of Sarcasm on Twitter: #CatsMovie vs. #TheRiseOfSkywalker.
      aug:
        au:
          MORENO-ORTIZ, ANTONIO
          GARCÍA-GÁMEZ, MARÍA
        affil: Universidad de Málaga
      su:
        Sentiment analysis
        X Corp.
        Microblogs
        Natural language processing
        Social media
        Twitter (Web resource)
        Sarcasm
        Discourse analysis
        Film reviewing
      sug:
        subj:
          Sentiment analysis
          X Corp.
          Microblogs
          Natural language processing
          Social media
          Twitter (Web resource)
          Sarcasm
          Discourse analysis
          Film reviewing
      keyword:
        análisis de sentimiento
        anotación de corpus
        corpus annotation
        detección de sarcasmo
        redes sociales
        sarcasm detection
        sentiment analysis
        social networks
        análisis de sentimiento
        anotación de corpus
        detección de sarcasmo
        redes sociales
      ab:
        Sentiment analysis is a natural language processing task that has received increased attention in the last decade due to the vast amount of opinionated data on social media platforms such as Twitter. Although the methodologies employed have grown in number and sophistication, analysing irony and sarcasm still poses a severe problem. From the linguistic perspective, sarcasm has been studied in discourse analysis from several perspectives, but little attention has been given to specific metrics that measure its relevance. In this paper we describe the creation of a manually-annotated dataset where detailed text markers are included. This dataset is a sample from a larger corpus of tweets (n= 76,764) on two highly controversial films: Cats and Star Wars: The Rise of Skywalker. We took two different samples for each film, one before and one after their release, to compare reception and presence of sarcasm. We then used a sentiment analysis tool to measure the impact of sarcasm in polarity detection and then manually classified the mechanisms of sarcasm generation. The resulting corpus will be useful for machine learning approaches to sarcasm detection as well as discourse analysis studies on irony and sarcasm.
        El análisis de sentimiento es una de las aplicaciones del procesamiento del lenguaje natural que más atención ha recibido en la última década, principalmente debido a la cantidad de opiniones vertidas en redes sociales como Twitter. Pese a que las metodologías empleadas son cada vez más sofisticadas, el sarcasmo sigue siendo un gran problema. Aunque el sarcasmo ha sido estudiado desde varias perspectivas en el análisis del discurso, no se ha prestado mucha atención a su presencia y relevancia real, aportando métricas concretas. En este trabajo se describe la creación de un dataset anotado manualmente en el que se incluyen marcadores textuales. Dicho dataset es la muestra de un corpus de tweets (n= 76.764) sobre dos películas controvertidas: Cats y Star Wars. El Ascenso de Skywalker. Tomamos dos muestras para cada película, antes y después de su estreno, para comparar su acogida. Empleamos una herramienta de análisis de sentimiento para medir el impacto del sarcasmo en la detección de la polaridad, y posteriormente identificamos y clasificamos los mecanismos de generación de sarcasmo. Este corpus puede ser de gran utilidad para la detección del sarcasmo mediante aprendizaje automático, así como para estudios de análisis del discurso sobre la expresión del sarcasmo.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Copyright of Atlantis (0210-6124) is the property of Departament de Llengues i Literatures Modernes i d'Estudis Anglesos and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use.
      item: Atlantis (0210-6124)
      holder: Departament de Llengues i Literatures Modernes i d'Estudis Anglesos
      dt:
        @attributes:
          year: 2022
    holdings:
      @attributes:
        islocal: N