A novel adaptable approach for sentiment analysis on big social data

Abstract Gathering public opinion by analyzing big social data has attracted wide attention due to its interactive and real time nature. For this, recent studies have relied on both social media and sentiment analysis in order to accompany big events by tracking people’s behavior. In this paper, we...

Full description

Bibliographic Details
Main Authors:	Imane El Alaoui, Youssef Gahi, Rochdi Messoussi, Youness Chaabi, Alexis Todoskoff, Abdessamad Kobi
Format:	Article
Language:	English
Published:	SpringerOpen 2018-03-01
Series:	Journal of Big Data
Online Access:	http://link.springer.com/article/10.1186/s40537-018-0120-0

id	doaj-d9554c03604a44ed97316636858494c6
record_format	Article
spelling	doaj-d9554c03604a44ed97316636858494c62020-11-24T22:03:53ZengSpringerOpenJournal of Big Data2196-11152018-03-015111810.1186/s40537-018-0120-0A novel adaptable approach for sentiment analysis on big social dataImane El Alaoui0Youssef Gahi1Rochdi Messoussi2Youness Chaabi3Alexis Todoskoff4Abdessamad Kobi5Laboratoire des Systèmes de Télécommunications et Ingénierie de la Décision, University of Ibn TofailLGS, Ecole Nationale des Sciences Appliquéees, University of Ibn TofailLaboratoire des Systèmes de Télécommunications et Ingénierie de la Décision, University of Ibn TofailLaboratoire des Systèmes de Télécommunications et Ingénierie de la Décision, University of Ibn TofailLaboratoire Angevin de Recherche en Ingénierie des Systèmes, University of AngersLaboratoire Angevin de Recherche en Ingénierie des Systèmes, University of AngersAbstract Gathering public opinion by analyzing big social data has attracted wide attention due to its interactive and real time nature. For this, recent studies have relied on both social media and sentiment analysis in order to accompany big events by tracking people’s behavior. In this paper, we propose an adaptable sentiment analysis approach that analyzes social media posts and extracts user’s opinion in real-time. The proposed approach consists of first constructing a dynamic dictionary of words’ polarity based on a selected set of hashtags related to a given topic, then, classifying the tweets under several classes by introducing new features that strongly fine-tune the polarity degree of a post. To validate our approach, we classified the tweets related to the 2016 US election. The results of prototype tests have performed a good accuracy in detecting positive and negative classes and their sub-classes.http://link.springer.com/article/10.1186/s40537-018-0120-0
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Imane El Alaoui Youssef Gahi Rochdi Messoussi Youness Chaabi Alexis Todoskoff Abdessamad Kobi
spellingShingle	Imane El Alaoui Youssef Gahi Rochdi Messoussi Youness Chaabi Alexis Todoskoff Abdessamad Kobi A novel adaptable approach for sentiment analysis on big social data Journal of Big Data
author_facet	Imane El Alaoui Youssef Gahi Rochdi Messoussi Youness Chaabi Alexis Todoskoff Abdessamad Kobi
author_sort	Imane El Alaoui
title	A novel adaptable approach for sentiment analysis on big social data
title_short	A novel adaptable approach for sentiment analysis on big social data
title_full	A novel adaptable approach for sentiment analysis on big social data
title_fullStr	A novel adaptable approach for sentiment analysis on big social data
title_full_unstemmed	A novel adaptable approach for sentiment analysis on big social data
title_sort	novel adaptable approach for sentiment analysis on big social data
publisher	SpringerOpen
series	Journal of Big Data
issn	2196-1115
publishDate	2018-03-01
description	Abstract Gathering public opinion by analyzing big social data has attracted wide attention due to its interactive and real time nature. For this, recent studies have relied on both social media and sentiment analysis in order to accompany big events by tracking people’s behavior. In this paper, we propose an adaptable sentiment analysis approach that analyzes social media posts and extracts user’s opinion in real-time. The proposed approach consists of first constructing a dynamic dictionary of words’ polarity based on a selected set of hashtags related to a given topic, then, classifying the tweets under several classes by introducing new features that strongly fine-tune the polarity degree of a post. To validate our approach, we classified the tweets related to the 2016 US election. The results of prototype tests have performed a good accuracy in detecting positive and negative classes and their sub-classes.
url	http://link.springer.com/article/10.1186/s40537-018-0120-0
work_keys_str_mv	AT imaneelalaoui anoveladaptableapproachforsentimentanalysisonbigsocialdata AT youssefgahi anoveladaptableapproachforsentimentanalysisonbigsocialdata AT rochdimessoussi anoveladaptableapproachforsentimentanalysisonbigsocialdata AT younesschaabi anoveladaptableapproachforsentimentanalysisonbigsocialdata AT alexistodoskoff anoveladaptableapproachforsentimentanalysisonbigsocialdata AT abdessamadkobi anoveladaptableapproachforsentimentanalysisonbigsocialdata AT imaneelalaoui noveladaptableapproachforsentimentanalysisonbigsocialdata AT youssefgahi noveladaptableapproachforsentimentanalysisonbigsocialdata AT rochdimessoussi noveladaptableapproachforsentimentanalysisonbigsocialdata AT younesschaabi noveladaptableapproachforsentimentanalysisonbigsocialdata AT alexistodoskoff noveladaptableapproachforsentimentanalysisonbigsocialdata AT abdessamadkobi noveladaptableapproachforsentimentanalysisonbigsocialdata
_version_	1725831641727762432

A novel adaptable approach for sentiment analysis on big social data

Similar Items