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.
Main Authors: | , |
---|---|
Format: | conferenceObject |
Language: | eng |
Published: |
2024
|
Subjects: | |
Online Access: | http://hdl.handle.net/11086/552488 |
_version_ | 1806012402144116736 |
---|---|
author | Celayes, Pablo Gabriel Domínguez, Martín Ariel |
author_facet | Celayes, Pablo Gabriel Domínguez, Martín Ariel |
author_sort | Celayes, Pablo Gabriel |
collection | Repositorio Digital Universitario |
description | Ponencia presentada en la 16th Mexican International Conference on Artificial Intelligence. October 23 to 28, Ensenada, Baja California, Mexico. |
format | conferenceObject |
id | rdu-unc.552488 |
institution | Universidad Nacional de Cordoba |
language | eng |
publishDate | 2024 |
record_format | dspace |
spelling | rdu-unc.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 |
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 |
title | 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_short | 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 |
topic | Machine learning Social networks Topic modelling Natural language processing |
url | http://hdl.handle.net/11086/552488 |
work_keys_str_mv | AT celayespablogabriel predictionofuserretweetsbasedonsocialneighborhoodinformationandtopicmodelling AT dominguezmartinariel predictionofuserretweetsbasedonsocialneighborhoodinformationandtopicmodelling |