Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese

Cristian Muoz Villalobos; Leonardo Alfredo Forero Mendoza; Harold D. De Mello; Marco Pacheco Cavalcanti; Cesar H. Valencia; Alvaro D. Orjuela-Cañon

doi:10.1145/3582768.3582805

Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese

Cristian Muoz Villalobos, Leonardo Alfredo Forero Mendoza, Harold D. De Mello, Marco Pacheco Cavalcanti, Cesar H. Valencia, Alvaro D. Orjuela-Cañon

Research output: Contribution to conference › Paper

Abstract

Natural Language Processing (NLP) techniques are increasingly powerful for interpreting a person's feelings and reaction to a product or service. Sentiment analysis has become a fundamental tool for this interpretation, and it has studies in languages other than English. This type of application is uncommon and unheard of in Portuguese. This article presents a sentiment analysis classification based on Portuguese social media comments. Representation of word embeddings with both pre-trained Glove and Word2Vec models were generated through a corpus entirely in Portuguese. This article presents a set of results with different models of pre-trained layers and deep learning models exclusive to the Portuguese language on social networks. Two classification models were used and compared: (i) Bidirectional Long Short-Term Memory (BI-LSTM) and (ii) Bidirectional Gated Recurrent Unit (BI-GRU), achieving accuracy results of 99.1

Original language	English (US)
Pages	205-209
Number of pages	5
DOIs	https://doi.org/10.1145/3582768.3582805
State	Published - Dec 16 2022
Event	6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022 - Bangkok, Thailand Duration: Dec 16 2022 → Dec 18 2022

Conference

Conference	6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022
Country/Territory	Thailand
City	Bangkok
Period	12/16/22 → 12/18/22

All Science Journal Classification (ASJC) codes

Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3582768.3582805

Cite this

Muoz Villalobos, C., Mendoza, L. A. F., De Mello, H. D., Cavalcanti, M. P., Valencia, C. H., & Orjuela-Cañon, A. D. (2022). Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese. 205-209. Paper presented at 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022, Bangkok, Thailand. https://doi.org/10.1145/3582768.3582805

@conference{4b1945b1d8ed4e91bd79965871e74f64,

title = "Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese",

abstract = "Natural Language Processing (NLP) techniques are increasingly powerful for interpreting a person's feelings and reaction to a product or service. Sentiment analysis has become a fundamental tool for this interpretation, and it has studies in languages other than English. This type of application is uncommon and unheard of in Portuguese. This article presents a sentiment analysis classification based on Portuguese social media comments. Representation of word embeddings with both pre-trained Glove and Word2Vec models were generated through a corpus entirely in Portuguese. This article presents a set of results with different models of pre-trained layers and deep learning models exclusive to the Portuguese language on social networks. Two classification models were used and compared: (i) Bidirectional Long Short-Term Memory (BI-LSTM) and (ii) Bidirectional Gated Recurrent Unit (BI-GRU), achieving accuracy results of 99.1",

author = "{Muoz Villalobos}, Cristian and Mendoza, {Leonardo Alfredo Forero} and {De Mello}, {Harold D.} and Cavalcanti, {Marco Pacheco} and Valencia, {Cesar H.} and Orjuela-Ca{\~n}on, {Alvaro D.}",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022 ; Conference date: 16-12-2022 Through 18-12-2022",

year = "2022",

month = dec,

day = "16",

doi = "10.1145/3582768.3582805",

language = "English (US)",

pages = "205--209",

}

Muoz Villalobos, C, Mendoza, LAF, De Mello, HD, Cavalcanti, MP, Valencia, CH & Orjuela-Cañon, AD 2022, 'Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese', Paper presented at 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022, Bangkok, Thailand, 12/16/22 - 12/18/22 pp. 205-209. https://doi.org/10.1145/3582768.3582805

Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese. / Muoz Villalobos, Cristian; Mendoza, Leonardo Alfredo Forero; De Mello, Harold D. et al.
2022. 205-209 Paper presented at 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022, Bangkok, Thailand.

Research output: Contribution to conference › Paper

TY - CONF

T1 - Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese

AU - Muoz Villalobos, Cristian

AU - Mendoza, Leonardo Alfredo Forero

AU - De Mello, Harold D.

AU - Cavalcanti, Marco Pacheco

AU - Valencia, Cesar H.

AU - Orjuela-Cañon, Alvaro D.

PY - 2022/12/16

Y1 - 2022/12/16

N2 - Natural Language Processing (NLP) techniques are increasingly powerful for interpreting a person's feelings and reaction to a product or service. Sentiment analysis has become a fundamental tool for this interpretation, and it has studies in languages other than English. This type of application is uncommon and unheard of in Portuguese. This article presents a sentiment analysis classification based on Portuguese social media comments. Representation of word embeddings with both pre-trained Glove and Word2Vec models were generated through a corpus entirely in Portuguese. This article presents a set of results with different models of pre-trained layers and deep learning models exclusive to the Portuguese language on social networks. Two classification models were used and compared: (i) Bidirectional Long Short-Term Memory (BI-LSTM) and (ii) Bidirectional Gated Recurrent Unit (BI-GRU), achieving accuracy results of 99.1

AB - Natural Language Processing (NLP) techniques are increasingly powerful for interpreting a person's feelings and reaction to a product or service. Sentiment analysis has become a fundamental tool for this interpretation, and it has studies in languages other than English. This type of application is uncommon and unheard of in Portuguese. This article presents a sentiment analysis classification based on Portuguese social media comments. Representation of word embeddings with both pre-trained Glove and Word2Vec models were generated through a corpus entirely in Portuguese. This article presents a set of results with different models of pre-trained layers and deep learning models exclusive to the Portuguese language on social networks. Two classification models were used and compared: (i) Bidirectional Long Short-Term Memory (BI-LSTM) and (ii) Bidirectional Gated Recurrent Unit (BI-GRU), achieving accuracy results of 99.1

UR - http://www.scopus.com/inward/record.url?scp=85168774760&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85168774760&partnerID=8YFLogxK

U2 - 10.1145/3582768.3582805

DO - 10.1145/3582768.3582805

M3 - Paper

AN - SCOPUS:85168774760

SP - 205

EP - 209

T2 - 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022

Y2 - 16 December 2022 through 18 December 2022

ER -

Muoz Villalobos C, Mendoza LAF, De Mello HD, Cavalcanti MP, Valencia CH, Orjuela-Cañon AD. Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese. 2022. Paper presented at 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022, Bangkok, Thailand. doi: 10.1145/3582768.3582805

Sentimental Analysis on Social Media Comments with Recurring Models and Pretrained Word Embeddings in Portuguese

Abstract

Conference

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this