Performance Study of N-grams in the Analysis of Sentiments

In this work, a study investigation was carried out using n-grams to classify sentiments with different machine learning and deep learning methods. We used this approach, which combines existing techniques, with the problem of predicting sequence tags to understand the advantages and problems confr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	O. E. Ojo, A. Gelbukh, H. Calvo, O. O. Adebanji
Formato:	article
Lenguaje:	EN
Publicado:	Nigerian Society of Physical Sciences 2021
Materias:	ngrams economic texts machine learning deep learning sentiment analysis Physics QC1-999
Acceso en línea:	https://doaj.org/article/c9218d7144f94c5d9b53e5401a12c6eb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c9218d7144f94c5d9b53e5401a12c6eb
record_format	dspace
spelling	oai:doaj.org-article:c9218d7144f94c5d9b53e5401a12c6eb2021-11-30T12:19:16ZPerformance Study of N-grams in the Analysis of Sentiments10.46481/jnsps.2021.2012714-28172714-4704https://doaj.org/article/c9218d7144f94c5d9b53e5401a12c6eb2021-11-01T00:00:00Zhttps://journal.nsps.org.ng/index.php/jnsps/article/view/201https://doaj.org/toc/2714-2817https://doaj.org/toc/2714-4704 In this work, a study investigation was carried out using n-grams to classify sentiments with different machine learning and deep learning methods. We used this approach, which combines existing techniques, with the problem of predicting sequence tags to understand the advantages and problems confronted with using unigrams, bigrams and trigrams to analyse economic texts. Our study aims to fill the gap by evaluating the performance of these n-grams features on different texts in the economic domain using nine sentiment analysis techniques and found more insights. We show that by comparing the performance of these features on different datasets and using multiple learning techniques, we extracted useful intelligence. The evaluation involves assessing the precision, recall, f1-score and accuracy of the function output of the several machine learning algorithms proposed. The methods were tested using Amazon, IMDB, Reuters, and Yelp economic review datasets and our comprehensive experiment shows the effectiveness of n-grams in the analysis of sentiments. O. E. OjoA. GelbukhH. CalvoO. O. AdebanjiNigerian Society of Physical Sciencesarticlengramseconomic textsmachine learningdeep learningsentiment analysisPhysicsQC1-999ENJournal of Nigerian Society of Physical Sciences, Vol 3, Iss 4 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ngrams economic texts machine learning deep learning sentiment analysis Physics QC1-999
spellingShingle	ngrams economic texts machine learning deep learning sentiment analysis Physics QC1-999 O. E. Ojo A. Gelbukh H. Calvo O. O. Adebanji Performance Study of N-grams in the Analysis of Sentiments
description	In this work, a study investigation was carried out using n-grams to classify sentiments with different machine learning and deep learning methods. We used this approach, which combines existing techniques, with the problem of predicting sequence tags to understand the advantages and problems confronted with using unigrams, bigrams and trigrams to analyse economic texts. Our study aims to fill the gap by evaluating the performance of these n-grams features on different texts in the economic domain using nine sentiment analysis techniques and found more insights. We show that by comparing the performance of these features on different datasets and using multiple learning techniques, we extracted useful intelligence. The evaluation involves assessing the precision, recall, f1-score and accuracy of the function output of the several machine learning algorithms proposed. The methods were tested using Amazon, IMDB, Reuters, and Yelp economic review datasets and our comprehensive experiment shows the effectiveness of n-grams in the analysis of sentiments.
format	article
author	O. E. Ojo A. Gelbukh H. Calvo O. O. Adebanji
author_facet	O. E. Ojo A. Gelbukh H. Calvo O. O. Adebanji
author_sort	O. E. Ojo
title	Performance Study of N-grams in the Analysis of Sentiments
title_short	Performance Study of N-grams in the Analysis of Sentiments
title_full	Performance Study of N-grams in the Analysis of Sentiments
title_fullStr	Performance Study of N-grams in the Analysis of Sentiments
title_full_unstemmed	Performance Study of N-grams in the Analysis of Sentiments
title_sort	performance study of n-grams in the analysis of sentiments
publisher	Nigerian Society of Physical Sciences
publishDate	2021
url	https://doaj.org/article/c9218d7144f94c5d9b53e5401a12c6eb
work_keys_str_mv	AT oeojo performancestudyofngramsintheanalysisofsentiments AT agelbukh performancestudyofngramsintheanalysisofsentiments AT hcalvo performancestudyofngramsintheanalysisofsentiments AT ooadebanji performancestudyofngramsintheanalysisofsentiments
_version_	1718406651576320000

Performance Study of N-grams in the Analysis of Sentiments

Ejemplares similares