Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models

In this study, the authors present a novel methodology adept at decoding multilingual topic dynamics and identifying communication trends during crises. We focus on dialogues within Tunisian social networks during the coronavirus pandemic and other notable themes like sports and politics. We start b...

Full description

Saved in:
Bibliographic Details
Main Authors: Samawel Jaballi, Manar Joundy Hazar, Salah Zrigui, Azer Mahjoubi, Henri Nicolas, Mounir Zrigui
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2024/6669491
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226115909517312
author Samawel Jaballi
Manar Joundy Hazar
Salah Zrigui
Azer Mahjoubi
Henri Nicolas
Mounir Zrigui
author_facet Samawel Jaballi
Manar Joundy Hazar
Salah Zrigui
Azer Mahjoubi
Henri Nicolas
Mounir Zrigui
author_sort Samawel Jaballi
collection DOAJ
description In this study, the authors present a novel methodology adept at decoding multilingual topic dynamics and identifying communication trends during crises. We focus on dialogues within Tunisian social networks during the coronavirus pandemic and other notable themes like sports and politics. We start by aggregating a varied multilingual corpus of comments relevant to these subjects. This dataset undergoes rigorous refinement during data preprocessing. We then introduce our No-English-to-English Machine Translation approach to handle linguistic differences. Empirical tests of this method show high accuracy and F1 scores, highlighting its suitability for linguistically coherent tasks. Delving deeper, advanced modeling techniques, specifically LDA and HDP models, are employed to extract pertinent topics from the translated content. This leads to applying ARIMA time series analysis to decode evolving topic trends. Applying our method to a multilingual Tunisian dataset, we effectively identify key topics mirroring public sentiment. Such insights prove vital for organizations and governments striving to understand public perspectives during crises. Compared to standard approaches, our model outperforms, as confirmed by metrics like coherence score, U-mass, and topic coherence. Additionally, an in-depth assessment of the identified topics reveals notable thematic shifts in discussions, with the proposed trends’ identification indicating impressive accuracy, backed by RMSE-based analysis.
format Article
id doaj-art-52b78a1f0c024d388af2e9fecdf9ca84
institution OA Journals
issn 2090-0155
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-52b78a1f0c024d388af2e9fecdf9ca842025-08-20T02:05:10ZengWileyJournal of Electrical and Computer Engineering2090-01552024-01-01202410.1155/2024/6669491Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP ModelsSamawel Jaballi0Manar Joundy Hazar1Salah Zrigui2Azer Mahjoubi3Henri Nicolas4Mounir Zrigui5Faculty of Sciences of MonastirFaculty of Sciences of MonastirLaboratory LIGFaculty of Sciences of MonastirUniversity of BordeauxFaculty of Sciences of MonastirIn this study, the authors present a novel methodology adept at decoding multilingual topic dynamics and identifying communication trends during crises. We focus on dialogues within Tunisian social networks during the coronavirus pandemic and other notable themes like sports and politics. We start by aggregating a varied multilingual corpus of comments relevant to these subjects. This dataset undergoes rigorous refinement during data preprocessing. We then introduce our No-English-to-English Machine Translation approach to handle linguistic differences. Empirical tests of this method show high accuracy and F1 scores, highlighting its suitability for linguistically coherent tasks. Delving deeper, advanced modeling techniques, specifically LDA and HDP models, are employed to extract pertinent topics from the translated content. This leads to applying ARIMA time series analysis to decode evolving topic trends. Applying our method to a multilingual Tunisian dataset, we effectively identify key topics mirroring public sentiment. Such insights prove vital for organizations and governments striving to understand public perspectives during crises. Compared to standard approaches, our model outperforms, as confirmed by metrics like coherence score, U-mass, and topic coherence. Additionally, an in-depth assessment of the identified topics reveals notable thematic shifts in discussions, with the proposed trends’ identification indicating impressive accuracy, backed by RMSE-based analysis.http://dx.doi.org/10.1155/2024/6669491
spellingShingle Samawel Jaballi
Manar Joundy Hazar
Salah Zrigui
Azer Mahjoubi
Henri Nicolas
Mounir Zrigui
Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
Journal of Electrical and Computer Engineering
title Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
title_full Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
title_fullStr Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
title_full_unstemmed Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
title_short Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
title_sort decoding multilingual topic dynamics and trend identification through arima time series analysis on social networks a novel data translation framework enhanced by lda hdp models
url http://dx.doi.org/10.1155/2024/6669491
work_keys_str_mv AT samaweljaballi decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels
AT manarjoundyhazar decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels
AT salahzrigui decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels
AT azermahjoubi decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels
AT henrinicolas decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels
AT mounirzrigui decodingmultilingualtopicdynamicsandtrendidentificationthrougharimatimeseriesanalysisonsocialnetworksanoveldatatranslationframeworkenhancedbyldahdpmodels