Author Profiling in Social Media with Multimodal Information

Author Profiling in Social Media with Multimodal Information

Abstract: This paper summarizes the thesis: ”Author Profiling in Social Media with Multimodal Information.” Our solution uses a multimodal approach to extracting information from written messages and images shared by users. Previous work has shown the existence of useful information for this task in these modalities; however, our proposal goes further, demonstrating the complementarity of the modalities when merging these two sources of information. To do this, we propose to transform images to texts, and with them, to have the same framework of representation for both kinds of information, which allow to achieve their fusion. Our work explores different methods for extracting information either from the text and the images. To represent the extracted information, different distributional term representations approaches were explored in order to identify the topics addressed by the user. For this purpose, an evaluation framework was proposed in order to identify the most appropriate method for this task. The results show that the textual descriptions of the images contain useful information for the author profiling task, and that the fusion of textual information with information extracted from the images increases the accuracy of this task.

Saved in:
Bibliographic Details
Main Authors: Álvarez Carmona,Miguel Á., Villatoro Tello,Esaú, Montes y Gómez,Manuel, Vilaseñor Pineda,Luis
Format: Digital revista
Language:English
Published: Instituto Politécnico Nacional, Centro de Investigación en Computación 2020
Online Access:http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462020000301289
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:scielo:S1405-55462020000301289
record_format ojs
spelling oai:scielo:S1405-554620200003012892021-06-10Author Profiling in Social Media with Multimodal InformationÁlvarez Carmona,Miguel Á.Villatoro Tello,EsaúMontes y Gómez,ManuelVilaseñor Pineda,Luis Author profiling multimodal information natural language processing text classification Abstract: This paper summarizes the thesis: ”Author Profiling in Social Media with Multimodal Information.” Our solution uses a multimodal approach to extracting information from written messages and images shared by users. Previous work has shown the existence of useful information for this task in these modalities; however, our proposal goes further, demonstrating the complementarity of the modalities when merging these two sources of information. To do this, we propose to transform images to texts, and with them, to have the same framework of representation for both kinds of information, which allow to achieve their fusion. Our work explores different methods for extracting information either from the text and the images. To represent the extracted information, different distributional term representations approaches were explored in order to identify the topics addressed by the user. For this purpose, an evaluation framework was proposed in order to identify the most appropriate method for this task. The results show that the textual descriptions of the images contain useful information for the author profiling task, and that the fusion of textual information with information extracted from the images increases the accuracy of this task.info:eu-repo/semantics/openAccessInstituto Politécnico Nacional, Centro de Investigación en ComputaciónComputación y Sistemas v.24 n.3 20202020-09-01info:eu-repo/semantics/articletext/htmlhttp://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462020000301289en10.13053/cys-24-3-3488
institution SCIELO
collection OJS
country México
countrycode MX
component Revista
access En linea
databasecode rev-scielo-mx
tag revista
region America del Norte
libraryname SciELO
language English
format Digital
author Álvarez Carmona,Miguel Á.
Villatoro Tello,Esaú
Montes y Gómez,Manuel
Vilaseñor Pineda,Luis
spellingShingle Álvarez Carmona,Miguel Á.
Villatoro Tello,Esaú
Montes y Gómez,Manuel
Vilaseñor Pineda,Luis
Author Profiling in Social Media with Multimodal Information
author_facet Álvarez Carmona,Miguel Á.
Villatoro Tello,Esaú
Montes y Gómez,Manuel
Vilaseñor Pineda,Luis
author_sort Álvarez Carmona,Miguel Á.
title Author Profiling in Social Media with Multimodal Information
title_short Author Profiling in Social Media with Multimodal Information
title_full Author Profiling in Social Media with Multimodal Information
title_fullStr Author Profiling in Social Media with Multimodal Information
title_full_unstemmed Author Profiling in Social Media with Multimodal Information
title_sort author profiling in social media with multimodal information
description Abstract: This paper summarizes the thesis: ”Author Profiling in Social Media with Multimodal Information.” Our solution uses a multimodal approach to extracting information from written messages and images shared by users. Previous work has shown the existence of useful information for this task in these modalities; however, our proposal goes further, demonstrating the complementarity of the modalities when merging these two sources of information. To do this, we propose to transform images to texts, and with them, to have the same framework of representation for both kinds of information, which allow to achieve their fusion. Our work explores different methods for extracting information either from the text and the images. To represent the extracted information, different distributional term representations approaches were explored in order to identify the topics addressed by the user. For this purpose, an evaluation framework was proposed in order to identify the most appropriate method for this task. The results show that the textual descriptions of the images contain useful information for the author profiling task, and that the fusion of textual information with information extracted from the images increases the accuracy of this task.
publisher Instituto Politécnico Nacional, Centro de Investigación en Computación
publishDate 2020
url http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462020000301289
work_keys_str_mv AT alvarezcarmonamiguela authorprofilinginsocialmediawithmultimodalinformation
AT villatorotelloesau authorprofilinginsocialmediawithmultimodalinformation
AT montesygomezmanuel authorprofilinginsocialmediawithmultimodalinformation
AT vilasenorpinedaluis authorprofilinginsocialmediawithmultimodalinformation
_version_ 1756225836561727488

Similar Items