Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Servicio de Difusión...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Time series causal inference between the political discourse on Twitter and opinion polls

Authors: Albanese, Federico; Baldonado, Juan Manuel; Feuerstein, Esteban;

Time series causal inference between the political discourse on Twitter and opinion polls

Abstract

Las redes sociales han sido utilizadas como medios para la discusión política de los ciudadanos. En este trabajo nos propusimos analizar la influencia que ejerce el discurso en las redes sociales sobre la opinión pública de los candidatos políticos en contextos electorales. Para ello conformamos un dataset con 4.4 millones de tweets políticos durante las elecciones presidenciales estadounidenses entre Trump y Biden del 2020 y analizamos 229 encuestas presidenciales realizadas por 29 encuestadores. Luego, armamos series temporales con los resultados de las encuestas y con la cantidad, tópico del que hablan y sentimiento (positividad / negatividad) de los tweets que mencionan a cada candidato, usando técnicas de procesamiento del lenguaje natural de forma similar a trabajos previos. Aplicando herramientas de inferencia causal en series de tiempo como la causalidad de Granger, Información Mutua Condicional y Base de Funciones Radiales, encontramos resultados estadísticamente significativos de una relación causal. En particular, el sentimiento con el que se habla de los candidato y ciertos tópicos particulares que se debaten en Twitter impactan sobre la intención de voto que finalmente recibe cada candidato presidencial.

In recent years, social networks have been the place where citizens exchange their political opinions. In this work, we analyzed the causal influence between the discourse in social networks on the opinion of political candidates in electoral contexts. Therefore, we created a dataset with 4.4 million political tweets during the 2020 US presidential election between Trump and Biden and analyzed 229 presidential polls conducted by 29 different pollsters. Then, we create time series with the poll’s results and with the quantity, topic and sentiment (positive / negative) of the tweets that mentioned the candidates, using natural language processing techniques similarly to previous works. Using time series causal inference tools such as Granger causality, conditional mutual information and radial basis function, we found significant results of causal relationships. In particular, the positivity / negativity of the tweets and some topics discussed on Twitter had a causal impact on each presidential candidate’s polling.

Sociedad Argentina de Informática e Investigación Operativa

Country
Argentina
Related Organizations
Subjects by Vocabulary

EOSC: Twitter Data

Keywords

inferencia causal, social media, Twitter, redes sociales, Ciencias Informáticas, series de tiempo, causal inference, time series, natural language processing, técnicas de procesamiento del lenguaje natural

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 4
    download downloads 3
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
  • 4
    views
    3
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
4
3
Related to Research communities
Digital Humanities and Cultural Heritage
moresidebar

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.