Prediction of user retweets based on social neighborhood information and topic modelling

Ponencia presentada en la 16th Mexican International Conference on Artificial Intelligence. October 23 to 28, Ensenada, Baja California, Mexico.

Guardado en:
Detalles Bibliográficos
Autores principales: Celayes, Pablo Gabriel, Domínguez, Martín Ariel
Formato: conferenceObject
Lenguaje:Inglés
Publicado: 2024
Materias:
Machine learning
Social networks
Topic modelling
Natural language processing
Acceso en línea:http://hdl.handle.net/11086/552488
Aporte de:
Repositorio Digital Universitario (UNC) de Universidad Nacional de Córdoba
id I10-R141-11086-552488
record_format dspace
spelling I10-R141-11086-5524882024-07-02T06:39:20Z Prediction of user retweets based on social neighborhood information and topic modelling Celayes, Pablo Gabriel Domínguez, Martín Ariel Machine learning Social networks Topic modelling Natural language processing Ponencia presentada en la 16th Mexican International Conference on Artificial Intelligence. October 23 to 28, Ensenada, Baja California, Mexico. Fil: Celayes, Pablo Gabriel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Domínguez, Martín Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Twitter and other social networks have become a fundamental source of information and a powerful tool to spread ideas and opinions. A crucial step in understanding the mechanisms that drive information diffusion in Twitter, is to study the influence of the social neighborhood of a user in the construction of her retweeting preferences. In particular, to what extent can the preferences of a user be predicted given the preferences of her neighborhood.We build our own sample graph of Twitter users and study the problem of pre- dicting retweets from a given user based on the retweeting behavior occurring in her second-degree social neighborhood (followed and followed-by-followed). We manage to train and evaluate user-centered binary classification models that predict retweets with an average F 1 score of 87.6%, based purely on social in- formation, that is, without analyzing the content of the tweets.For users getting low scores with such models (on a tuning dataset), we improve the results by adding features extracted from the content of tweets. To do so, we apply a Natural Language Processing (NLP) pipeline including a Twitter-specific adaptation of the Latent Dirichlet Allocation (LDA) probabilistic topic model. Fil: Celayes, Pablo Gabriel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Domínguez, Martín Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Otras Ciencias de la Computación e Información 2024-07-01T17:27:47Z 2024-07-01T17:27:47Z 2017 conferenceObject http://hdl.handle.net/11086/552488 eng Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Impreso
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-141
collection Repositorio Digital Universitario (UNC)
language Inglés
topic Machine learning
Social networks
Topic modelling
Natural language processing
spellingShingle Machine learning
Social networks
Topic modelling
Natural language processing
Celayes, Pablo Gabriel
Domínguez, Martín Ariel
Prediction of user retweets based on social neighborhood information and topic modelling
topic_facet Machine learning
Social networks
Topic modelling
Natural language processing
description Ponencia presentada en la 16th Mexican International Conference on Artificial Intelligence. October 23 to 28, Ensenada, Baja California, Mexico.
format conferenceObject
author Celayes, Pablo Gabriel
Domínguez, Martín Ariel
author_facet Celayes, Pablo Gabriel
Domínguez, Martín Ariel
author_sort Celayes, Pablo Gabriel
title Prediction of user retweets based on social neighborhood information and topic modelling
title_short Prediction of user retweets based on social neighborhood information and topic modelling
title_full Prediction of user retweets based on social neighborhood information and topic modelling
title_fullStr Prediction of user retweets based on social neighborhood information and topic modelling
title_full_unstemmed Prediction of user retweets based on social neighborhood information and topic modelling
title_sort prediction of user retweets based on social neighborhood information and topic modelling
publishDate 2024
url http://hdl.handle.net/11086/552488
work_keys_str_mv AT celayespablogabriel predictionofuserretweetsbasedonsocialneighborhoodinformationandtopicmodelling
AT dominguezmartinariel predictionofuserretweetsbasedonsocialneighborhoodinformationandtopicmodelling
_version_ 1806949655594926080

Ejemplares similares